deepof_model_evaluation.ipynb 1.45 MB
Newer Older
1
2
3
4
{
 "cells": [
  {
   "cell_type": "code",
5
   "execution_count": 1,
6
   "metadata": {},
7
   "outputs": [],
8
9
10
11
12
   "source": [
    "%load_ext autoreload\n",
    "%autoreload 2"
   ]
  },
13
14
  {
   "cell_type": "code",
15
   "execution_count": 2,
16
17
18
19
   "metadata": {},
   "outputs": [],
   "source": [
    "import warnings\n",
20
    "\n",
21
22
23
    "warnings.filterwarnings(\"ignore\")"
   ]
  },
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# deepOF model evaluation"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Given a dataset and a trained model, this notebook allows the user to \n",
    "\n",
    "* Load and inspect the different models (encoder, decoder, grouper, gmvaep)\n",
    "* Visualize reconstruction quality for a given model\n",
    "* Visualize a static latent space\n",
    "* Visualize trajectories on the latent space for a given video\n",
    "* sample from the latent space distributions and generate video clips showcasing generated data"
   ]
  },
  {
   "cell_type": "code",
46
   "execution_count": 3,
47
48
49
50
   "metadata": {},
   "outputs": [],
   "source": [
    "import os\n",
51
    "\n",
52
53
54
55
56
    "os.chdir(os.path.dirname(\"../\"))"
   ]
  },
  {
   "cell_type": "code",
lucas_miranda's avatar
lucas_miranda committed
57
   "execution_count": 4,
58
59
60
61
62
63
64
   "metadata": {},
   "outputs": [],
   "source": [
    "import deepof.data\n",
    "import deepof.utils\n",
    "import numpy as np\n",
    "import pandas as pd\n",
65
    "import re\n",
66
    "import tensorflow as tf\n",
67
    "from collections import Counter\n",
68
69
    "from sklearn.preprocessing import StandardScaler\n",
    "\n",
70
71
72
73
74
    "from sklearn.manifold import TSNE\n",
    "from sklearn.decomposition import PCA\n",
    "from sklearn.discriminant_analysis import LinearDiscriminantAnalysis\n",
    "import umap\n",
    "\n",
75
    "from ipywidgets import interactive, interact, HBox, Layout, VBox\n",
76
77
    "from IPython import display\n",
    "from matplotlib.animation import FuncAnimation\n",
lucas_miranda's avatar
lucas_miranda committed
78
    "from mpl_toolkits.mplot3d import Axes3D\n",
79
80
    "import matplotlib.pyplot as plt\n",
    "import seaborn as sns\n",
lucas_miranda's avatar
lucas_miranda committed
81
    "import tqdm.notebook as tqdm\n",
82
83
84
85
86
87
88
89
90
91
92
93
94
    "\n",
    "from ipywidgets import interact"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### 1. Define and run project"
   ]
  },
  {
   "cell_type": "code",
lucas_miranda's avatar
lucas_miranda committed
95
   "execution_count": 5,
96
97
98
   "metadata": {},
   "outputs": [],
   "source": [
99
    "path = os.path.join(\"..\", \"..\", \"Desktop\", \"deepof-data\", \"deepof_single_topview\")\n",
100
    "trained_network = os.path.join(\"..\", \"..\", \"Desktop\", \"deepof_trained_weights_280521\", \"var_annealing\")\n",
101
    "exclude_bodyparts = tuple([\"\"])\n",
102
    "window_size = 22\n",
103
    "batch_size = 32"
104
105
106
107
   ]
  },
  {
   "cell_type": "code",
lucas_miranda's avatar
lucas_miranda committed
108
   "execution_count": 6,
109
   "metadata": {},
110
111
112
113
114
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
lucas_miranda's avatar
lucas_miranda committed
115
116
      "CPU times: user 43.6 s, sys: 2.99 s, total: 46.6 s\n",
      "Wall time: 38.6 s\n"
117
118
119
     ]
    }
   ],
120
121
122
   "source": [
    "%%time\n",
    "proj = deepof.data.project(\n",
123
    "    path=path, smooth_alpha=0.999, exclude_bodyparts=exclude_bodyparts, arena_dims=[380],\n",
124
125
126
127
128
    ")"
   ]
  },
  {
   "cell_type": "code",
lucas_miranda's avatar
lucas_miranda committed
129
   "execution_count": 7,
130
131
132
   "metadata": {
    "scrolled": true
   },
133
134
135
136
137
138
139
140
141
142
143
144
145
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Loading trajectories...\n",
      "Smoothing trajectories...\n",
      "Interpolating outliers...\n",
      "Iterative imputation of ocluded bodyparts...\n",
      "Computing distances...\n",
      "Computing angles...\n",
      "Done!\n",
      "deepof analysis of 166 videos\n",
lucas_miranda's avatar
lucas_miranda committed
146
147
      "CPU times: user 9min, sys: 11.8 s, total: 9min 11s\n",
      "Wall time: 2min 1s\n"
148
149
150
     ]
    }
   ],
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
   "source": [
    "%%time\n",
    "proj = proj.run(verbose=True)\n",
    "print(proj)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### 2. Load pretrained deepof model"
   ]
  },
  {
   "cell_type": "code",
lucas_miranda's avatar
lucas_miranda committed
166
   "execution_count": 8,
167
168
169
   "metadata": {},
   "outputs": [],
   "source": [
170
    "coords = proj.get_coords(center=\"Center\", align=\"Spine_1\", align_inplace=True)\n",
171
    "data_prep = coords.preprocess(test_videos=0, window_step=1, window_size=window_size, shuffle=False)[\n",
172
173
    "    0\n",
    "]"
174
175
176
177
   ]
  },
  {
   "cell_type": "code",
lucas_miranda's avatar
lucas_miranda committed
178
   "execution_count": 9,
179
   "metadata": {},
180
181
182
183
   "outputs": [
    {
     "data": {
      "text/plain": [
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
       "['GMVAE_input_type=coords_window_size=22_NextSeqPred=0.15_PhenoPred=0.0_RuleBasedPred=0.15_loss=ELBO_loss_warmup=25_warmup_mode=linear_encoding=6_k=15_latreg=variance_entknn=100_run=4_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.0_PhenoPred=0.0_RuleBasedPred=0.0_loss=ELBO_loss_warmup=25_warmup_mode=linear_encoding=6_k=15_latreg=variance_entknn=100_run=6_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.15_PhenoPred=0.0_RuleBasedPred=0.0_loss=ELBO_loss_warmup=5_warmup_mode=linear_encoding=6_k=15_latreg=variance_entknn=100_run=1_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.15_PhenoPred=0.0_RuleBasedPred=0.0_loss=ELBO_loss_warmup=25_warmup_mode=sigmoid_encoding=6_k=15_latreg=variance_entknn=100_run=8_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.0_PhenoPred=0.0_RuleBasedPred=0.15_loss=ELBO_loss_warmup=20_warmup_mode=linear_encoding=6_k=15_latreg=variance_entknn=100_run=8_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.15_PhenoPred=0.0_RuleBasedPred=0.0_loss=ELBO_loss_warmup=15_warmup_mode=linear_encoding=6_k=15_latreg=variance_entknn=100_run=5_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.0_PhenoPred=0.0_RuleBasedPred=0.15_loss=ELBO_loss_warmup=5_warmup_mode=sigmoid_encoding=6_k=15_latreg=variance_entknn=100_run=5_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.15_PhenoPred=0.0_RuleBasedPred=0.15_loss=ELBO_loss_warmup=10_warmup_mode=sigmoid_encoding=6_k=15_latreg=variance_entknn=100_run=8_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.15_PhenoPred=0.0_RuleBasedPred=0.0_loss=ELBO_loss_warmup=25_warmup_mode=linear_encoding=6_k=15_latreg=variance_entknn=100_run=7_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.0_PhenoPred=0.0_RuleBasedPred=0.15_loss=ELBO_loss_warmup=25_warmup_mode=sigmoid_encoding=6_k=15_latreg=variance_entknn=100_run=6_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.0_PhenoPred=0.0_RuleBasedPred=0.0_loss=ELBO_loss_warmup=15_warmup_mode=linear_encoding=6_k=15_latreg=variance_entknn=100_run=4_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.0_PhenoPred=0.0_RuleBasedPred=0.15_loss=ELBO_loss_warmup=10_warmup_mode=sigmoid_encoding=6_k=15_latreg=variance_entknn=100_run=4_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.15_PhenoPred=0.0_RuleBasedPred=0.15_loss=ELBO_loss_warmup=15_warmup_mode=linear_encoding=6_k=15_latreg=variance_entknn=100_run=6_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.0_PhenoPred=0.0_RuleBasedPred=0.0_loss=ELBO_loss_warmup=10_warmup_mode=linear_encoding=6_k=15_latreg=variance_entknn=100_run=7_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.15_PhenoPred=0.0_RuleBasedPred=0.15_loss=ELBO_loss_warmup=10_warmup_mode=linear_encoding=6_k=15_latreg=variance_entknn=100_run=5_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.15_PhenoPred=0.0_RuleBasedPred=0.15_loss=ELBO_loss_warmup=20_warmup_mode=sigmoid_encoding=6_k=15_latreg=variance_entknn=100_run=1_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.15_PhenoPred=0.0_RuleBasedPred=0.0_loss=ELBO_loss_warmup=20_warmup_mode=sigmoid_encoding=6_k=15_latreg=variance_entknn=100_run=3_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.0_PhenoPred=0.0_RuleBasedPred=0.15_loss=ELBO_loss_warmup=25_warmup_mode=linear_encoding=6_k=15_latreg=variance_entknn=100_run=10_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.15_PhenoPred=0.0_RuleBasedPred=0.0_loss=ELBO_loss_warmup=5_warmup_mode=sigmoid_encoding=6_k=15_latreg=variance_entknn=100_run=9_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.15_PhenoPred=0.0_RuleBasedPred=0.0_loss=ELBO_loss_warmup=15_warmup_mode=sigmoid_encoding=6_k=15_latreg=variance_entknn=100_run=1_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.15_PhenoPred=0.0_RuleBasedPred=0.0_loss=ELBO_loss_warmup=20_warmup_mode=linear_encoding=6_k=15_latreg=variance_entknn=100_run=4_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.0_PhenoPred=0.0_RuleBasedPred=0.15_loss=ELBO_loss_warmup=15_warmup_mode=linear_encoding=6_k=15_latreg=variance_entknn=100_run=9_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.15_PhenoPred=0.0_RuleBasedPred=0.15_loss=ELBO_loss_warmup=15_warmup_mode=sigmoid_encoding=6_k=15_latreg=variance_entknn=100_run=3_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.15_PhenoPred=0.0_RuleBasedPred=0.0_loss=ELBO_loss_warmup=10_warmup_mode=linear_encoding=6_k=15_latreg=variance_entknn=100_run=6_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.0_PhenoPred=0.0_RuleBasedPred=0.15_loss=ELBO_loss_warmup=5_warmup_mode=linear_encoding=6_k=15_latreg=variance_entknn=100_run=1_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.0_PhenoPred=0.0_RuleBasedPred=0.0_loss=ELBO_loss_warmup=25_warmup_mode=sigmoid_encoding=6_k=15_latreg=variance_entknn=100_run=7_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.0_PhenoPred=0.0_RuleBasedPred=0.0_loss=ELBO_loss_warmup=5_warmup_mode=sigmoid_encoding=6_k=15_latreg=variance_entknn=100_run=8_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.15_PhenoPred=0.0_RuleBasedPred=0.15_loss=ELBO_loss_warmup=20_warmup_mode=linear_encoding=6_k=15_latreg=variance_entknn=100_run=7_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.0_PhenoPred=0.0_RuleBasedPred=0.0_loss=ELBO_loss_warmup=10_warmup_mode=sigmoid_encoding=6_k=15_latreg=variance_entknn=100_run=5_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.0_PhenoPred=0.0_RuleBasedPred=0.0_loss=ELBO_loss_warmup=20_warmup_mode=linear_encoding=6_k=15_latreg=variance_entknn=100_run=5_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.15_PhenoPred=0.0_RuleBasedPred=0.0_loss=ELBO_loss_warmup=10_warmup_mode=sigmoid_encoding=6_k=15_latreg=variance_entknn=100_run=10_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.0_PhenoPred=0.0_RuleBasedPred=0.0_loss=ELBO_loss_warmup=20_warmup_mode=sigmoid_encoding=6_k=15_latreg=variance_entknn=100_run=10_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.0_PhenoPred=0.0_RuleBasedPred=0.15_loss=ELBO_loss_warmup=10_warmup_mode=linear_encoding=6_k=15_latreg=variance_entknn=100_run=1_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.0_PhenoPred=0.0_RuleBasedPred=0.0_loss=ELBO_loss_warmup=20_warmup_mode=sigmoid_encoding=6_k=15_latreg=variance_entknn=100_run=7_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.0_PhenoPred=0.0_RuleBasedPred=0.0_loss=ELBO_loss_warmup=5_warmup_mode=linear_encoding=6_k=15_latreg=variance_entknn=100_run=1_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.0_PhenoPred=0.0_RuleBasedPred=0.0_loss=ELBO_loss_warmup=15_warmup_mode=sigmoid_encoding=6_k=15_latreg=variance_entknn=100_run=5_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.15_PhenoPred=0.0_RuleBasedPred=0.15_loss=ELBO_loss_warmup=25_warmup_mode=sigmoid_encoding=6_k=15_latreg=variance_entknn=100_run=1_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.15_PhenoPred=0.0_RuleBasedPred=0.0_loss=ELBO_loss_warmup=25_warmup_mode=sigmoid_encoding=6_k=15_latreg=variance_entknn=100_run=3_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.15_PhenoPred=0.0_RuleBasedPred=0.0_loss=ELBO_loss_warmup=10_warmup_mode=sigmoid_encoding=6_k=15_latreg=variance_entknn=100_run=1_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.0_PhenoPred=0.0_RuleBasedPred=0.15_loss=ELBO_loss_warmup=20_warmup_mode=linear_encoding=6_k=15_latreg=variance_entknn=100_run=10_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.0_PhenoPred=0.0_RuleBasedPred=0.15_loss=ELBO_loss_warmup=20_warmup_mode=linear_encoding=6_k=15_latreg=variance_entknn=100_run=3_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.15_PhenoPred=0.0_RuleBasedPred=0.15_loss=ELBO_loss_warmup=10_warmup_mode=sigmoid_encoding=6_k=15_latreg=variance_entknn=100_run=3_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.0_PhenoPred=0.0_RuleBasedPred=0.15_loss=ELBO_loss_warmup=20_warmup_mode=sigmoid_encoding=6_k=15_latreg=variance_entknn=100_run=6_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.15_PhenoPred=0.0_RuleBasedPred=0.15_loss=ELBO_loss_warmup=5_warmup_mode=sigmoid_encoding=6_k=15_latreg=variance_entknn=100_run=1_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.0_PhenoPred=0.0_RuleBasedPred=0.15_loss=ELBO_loss_warmup=15_warmup_mode=sigmoid_encoding=6_k=15_latreg=variance_entknn=100_run=4_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.0_PhenoPred=0.0_RuleBasedPred=0.0_loss=ELBO_loss_warmup=5_warmup_mode=sigmoid_encoding=6_k=15_latreg=variance_entknn=100_run=3_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.15_PhenoPred=0.0_RuleBasedPred=0.15_loss=ELBO_loss_warmup=25_warmup_mode=sigmoid_encoding=6_k=15_latreg=variance_entknn=100_run=10_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.15_PhenoPred=0.0_RuleBasedPred=0.0_loss=ELBO_loss_warmup=20_warmup_mode=sigmoid_encoding=6_k=15_latreg=variance_entknn=100_run=8_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.0_PhenoPred=0.0_RuleBasedPred=0.15_loss=ELBO_loss_warmup=15_warmup_mode=linear_encoding=6_k=15_latreg=variance_entknn=100_run=2_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.15_PhenoPred=0.0_RuleBasedPred=0.0_loss=ELBO_loss_warmup=5_warmup_mode=sigmoid_encoding=6_k=15_latreg=variance_entknn=100_run=2_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.15_PhenoPred=0.0_RuleBasedPred=0.15_loss=ELBO_loss_warmup=15_warmup_mode=sigmoid_encoding=6_k=15_latreg=variance_entknn=100_run=8_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.15_PhenoPred=0.0_RuleBasedPred=0.15_loss=ELBO_loss_warmup=5_warmup_mode=sigmoid_encoding=6_k=15_latreg=variance_entknn=100_run=5_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.15_PhenoPred=0.0_RuleBasedPred=0.15_loss=ELBO_loss_warmup=20_warmup_mode=linear_encoding=6_k=15_latreg=variance_entknn=100_run=8_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.0_PhenoPred=0.0_RuleBasedPred=0.0_loss=ELBO_loss_warmup=5_warmup_mode=sigmoid_encoding=6_k=15_latreg=variance_entknn=100_run=7_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.0_PhenoPred=0.0_RuleBasedPred=0.0_loss=ELBO_loss_warmup=25_warmup_mode=sigmoid_encoding=6_k=15_latreg=variance_entknn=100_run=8_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.0_PhenoPred=0.0_RuleBasedPred=0.15_loss=ELBO_loss_warmup=20_warmup_mode=sigmoid_encoding=6_k=15_latreg=variance_entknn=100_run=2_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.0_PhenoPred=0.0_RuleBasedPred=0.15_loss=ELBO_loss_warmup=25_warmup_mode=linear_encoding=6_k=15_latreg=variance_entknn=100_run=4_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.15_PhenoPred=0.0_RuleBasedPred=0.0_loss=ELBO_loss_warmup=10_warmup_mode=linear_encoding=6_k=15_latreg=variance_entknn=100_run=9_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.0_PhenoPred=0.0_RuleBasedPred=0.15_loss=ELBO_loss_warmup=15_warmup_mode=linear_encoding=6_k=15_latreg=variance_entknn=100_run=6_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.15_PhenoPred=0.0_RuleBasedPred=0.0_loss=ELBO_loss_warmup=5_warmup_mode=sigmoid_encoding=6_k=15_latreg=variance_entknn=100_run=6_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.0_PhenoPred=0.0_RuleBasedPred=0.0_loss=ELBO_loss_warmup=10_warmup_mode=linear_encoding=6_k=15_latreg=variance_entknn=100_run=8_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.15_PhenoPred=0.0_RuleBasedPred=0.15_loss=ELBO_loss_warmup=15_warmup_mode=linear_encoding=6_k=15_latreg=variance_entknn=100_run=9_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.0_PhenoPred=0.0_RuleBasedPred=0.0_loss=ELBO_loss_warmup=5_warmup_mode=linear_encoding=6_k=15_latreg=variance_entknn=100_run=5_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.0_PhenoPred=0.0_RuleBasedPred=0.0_loss=ELBO_loss_warmup=15_warmup_mode=sigmoid_encoding=6_k=15_latreg=variance_entknn=100_run=1_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.0_PhenoPred=0.0_RuleBasedPred=0.0_loss=ELBO_loss_warmup=20_warmup_mode=sigmoid_encoding=6_k=15_latreg=variance_entknn=100_run=3_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.15_PhenoPred=0.0_RuleBasedPred=0.0_loss=ELBO_loss_warmup=5_warmup_mode=linear_encoding=6_k=15_latreg=variance_entknn=100_run=10_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.0_PhenoPred=0.0_RuleBasedPred=0.15_loss=ELBO_loss_warmup=25_warmup_mode=sigmoid_encoding=6_k=15_latreg=variance_entknn=100_run=9_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.15_PhenoPred=0.0_RuleBasedPred=0.0_loss=ELBO_loss_warmup=25_warmup_mode=linear_encoding=6_k=15_latreg=variance_entknn=100_run=8_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.0_PhenoPred=0.0_RuleBasedPred=0.15_loss=ELBO_loss_warmup=10_warmup_mode=linear_encoding=6_k=15_latreg=variance_entknn=100_run=5_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.15_PhenoPred=0.0_RuleBasedPred=0.15_loss=ELBO_loss_warmup=10_warmup_mode=sigmoid_encoding=6_k=15_latreg=variance_entknn=100_run=7_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.15_PhenoPred=0.0_RuleBasedPred=0.15_loss=ELBO_loss_warmup=20_warmup_mode=sigmoid_encoding=6_k=15_latreg=variance_entknn=100_run=10_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.15_PhenoPred=0.0_RuleBasedPred=0.0_loss=ELBO_loss_warmup=10_warmup_mode=sigmoid_encoding=6_k=15_latreg=variance_entknn=100_run=5_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.0_PhenoPred=0.0_RuleBasedPred=0.15_loss=ELBO_loss_warmup=20_warmup_mode=linear_encoding=6_k=15_latreg=variance_entknn=100_run=7_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.15_PhenoPred=0.0_RuleBasedPred=0.0_loss=ELBO_loss_warmup=25_warmup_mode=sigmoid_encoding=6_k=15_latreg=variance_entknn=100_run=7_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.15_PhenoPred=0.0_RuleBasedPred=0.15_loss=ELBO_loss_warmup=25_warmup_mode=sigmoid_encoding=6_k=15_latreg=variance_entknn=100_run=5_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.0_PhenoPred=0.0_RuleBasedPred=0.0_loss=ELBO_loss_warmup=25_warmup_mode=linear_encoding=6_k=15_latreg=variance_entknn=100_run=9_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.0_PhenoPred=0.0_RuleBasedPred=0.15_loss=ELBO_loss_warmup=5_warmup_mode=sigmoid_encoding=6_k=15_latreg=variance_entknn=100_run=10_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.15_PhenoPred=0.0_RuleBasedPred=0.15_loss=ELBO_loss_warmup=15_warmup_mode=sigmoid_encoding=6_k=15_latreg=variance_entknn=100_run=7_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.15_PhenoPred=0.0_RuleBasedPred=0.0_loss=ELBO_loss_warmup=15_warmup_mode=sigmoid_encoding=6_k=15_latreg=variance_entknn=100_run=5_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.15_PhenoPred=0.0_RuleBasedPred=0.15_loss=ELBO_loss_warmup=5_warmup_mode=linear_encoding=6_k=15_latreg=variance_entknn=100_run=4_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.15_PhenoPred=0.0_RuleBasedPred=0.0_loss=ELBO_loss_warmup=20_warmup_mode=sigmoid_encoding=6_k=15_latreg=variance_entknn=100_run=7_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.0_PhenoPred=0.0_RuleBasedPred=0.0_loss=ELBO_loss_warmup=10_warmup_mode=linear_encoding=6_k=15_latreg=variance_entknn=100_run=3_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.15_PhenoPred=0.0_RuleBasedPred=0.15_loss=ELBO_loss_warmup=10_warmup_mode=linear_encoding=6_k=15_latreg=variance_entknn=100_run=1_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.15_PhenoPred=0.0_RuleBasedPred=0.15_loss=ELBO_loss_warmup=20_warmup_mode=sigmoid_encoding=6_k=15_latreg=variance_entknn=100_run=5_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.15_PhenoPred=0.0_RuleBasedPred=0.15_loss=ELBO_loss_warmup=20_warmup_mode=linear_encoding=6_k=15_latreg=variance_entknn=100_run=3_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.0_PhenoPred=0.0_RuleBasedPred=0.0_loss=ELBO_loss_warmup=10_warmup_mode=sigmoid_encoding=6_k=15_latreg=variance_entknn=100_run=1_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.0_PhenoPred=0.0_RuleBasedPred=0.0_loss=ELBO_loss_warmup=20_warmup_mode=linear_encoding=6_k=15_latreg=variance_entknn=100_run=1_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.0_PhenoPred=0.0_RuleBasedPred=0.15_loss=ELBO_loss_warmup=20_warmup_mode=sigmoid_encoding=6_k=15_latreg=variance_entknn=100_run=9_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.0_PhenoPred=0.0_RuleBasedPred=0.15_loss=ELBO_loss_warmup=5_warmup_mode=linear_encoding=6_k=15_latreg=variance_entknn=100_run=5_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.0_PhenoPred=0.0_RuleBasedPred=0.0_loss=ELBO_loss_warmup=25_warmup_mode=sigmoid_encoding=6_k=15_latreg=variance_entknn=100_run=3_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.15_PhenoPred=0.0_RuleBasedPred=0.0_loss=ELBO_loss_warmup=10_warmup_mode=linear_encoding=6_k=15_latreg=variance_entknn=100_run=2_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.0_PhenoPred=0.0_RuleBasedPred=0.0_loss=ELBO_loss_warmup=25_warmup_mode=sigmoid_encoding=6_k=15_latreg=variance_entknn=100_run=10_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.15_PhenoPred=0.0_RuleBasedPred=0.0_loss=ELBO_loss_warmup=15_warmup_mode=linear_encoding=6_k=15_latreg=variance_entknn=100_run=1_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.15_PhenoPred=0.0_RuleBasedPred=0.0_loss=ELBO_loss_warmup=15_warmup_mode=sigmoid_encoding=6_k=15_latreg=variance_entknn=100_run=10_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.0_PhenoPred=0.0_RuleBasedPred=0.15_loss=ELBO_loss_warmup=5_warmup_mode=sigmoid_encoding=6_k=15_latreg=variance_entknn=100_run=1_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.15_PhenoPred=0.0_RuleBasedPred=0.0_loss=ELBO_loss_warmup=5_warmup_mode=linear_encoding=6_k=15_latreg=variance_entknn=100_run=5_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.0_PhenoPred=0.0_RuleBasedPred=0.0_loss=ELBO_loss_warmup=25_warmup_mode=linear_encoding=6_k=15_latreg=variance_entknn=100_run=2_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.15_PhenoPred=0.0_RuleBasedPred=0.15_loss=ELBO_loss_warmup=15_warmup_mode=linear_encoding=6_k=15_latreg=variance_entknn=100_run=2_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.0_PhenoPred=0.0_RuleBasedPred=0.15_loss=ELBO_loss_warmup=25_warmup_mode=sigmoid_encoding=6_k=15_latreg=variance_entknn=100_run=2_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.0_PhenoPred=0.0_RuleBasedPred=0.0_loss=ELBO_loss_warmup=20_warmup_mode=sigmoid_encoding=6_k=15_latreg=variance_entknn=100_run=8_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.15_PhenoPred=0.0_RuleBasedPred=0.0_loss=ELBO_loss_warmup=25_warmup_mode=linear_encoding=6_k=15_latreg=variance_entknn=100_run=3_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.0_PhenoPred=0.0_RuleBasedPred=0.0_loss=ELBO_loss_warmup=20_warmup_mode=linear_encoding=6_k=15_latreg=variance_entknn=100_run=4_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.0_PhenoPred=0.0_RuleBasedPred=0.0_loss=ELBO_loss_warmup=10_warmup_mode=sigmoid_encoding=6_k=15_latreg=variance_entknn=100_run=4_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.0_PhenoPred=0.0_RuleBasedPred=0.0_loss=ELBO_loss_warmup=5_warmup_mode=sigmoid_encoding=6_k=15_latreg=variance_entknn=100_run=9_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.15_PhenoPred=0.0_RuleBasedPred=0.15_loss=ELBO_loss_warmup=20_warmup_mode=linear_encoding=6_k=15_latreg=variance_entknn=100_run=6_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.15_PhenoPred=0.0_RuleBasedPred=0.0_loss=ELBO_loss_warmup=10_warmup_mode=linear_encoding=6_k=15_latreg=variance_entknn=100_run=7_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.0_PhenoPred=0.0_RuleBasedPred=0.0_loss=ELBO_loss_warmup=25_warmup_mode=sigmoid_encoding=6_k=15_latreg=variance_entknn=100_run=6_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.0_PhenoPred=0.0_RuleBasedPred=0.15_loss=ELBO_loss_warmup=15_warmup_mode=linear_encoding=6_k=15_latreg=variance_entknn=100_run=8_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.15_PhenoPred=0.0_RuleBasedPred=0.0_loss=ELBO_loss_warmup=20_warmup_mode=linear_encoding=6_k=15_latreg=variance_entknn=100_run=5_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.15_PhenoPred=0.0_RuleBasedPred=0.0_loss=ELBO_loss_warmup=5_warmup_mode=sigmoid_encoding=6_k=15_latreg=variance_entknn=100_run=8_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.15_PhenoPred=0.0_RuleBasedPred=0.15_loss=ELBO_loss_warmup=15_warmup_mode=sigmoid_encoding=6_k=15_latreg=variance_entknn=100_run=2_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.15_PhenoPred=0.0_RuleBasedPred=0.15_loss=ELBO_loss_warmup=10_warmup_mode=linear_encoding=6_k=15_latreg=variance_entknn=100_run=4_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.0_PhenoPred=0.0_RuleBasedPred=0.0_loss=ELBO_loss_warmup=10_warmup_mode=linear_encoding=6_k=15_latreg=variance_entknn=100_run=6_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.15_PhenoPred=0.0_RuleBasedPred=0.0_loss=ELBO_loss_warmup=20_warmup_mode=sigmoid_encoding=6_k=15_latreg=variance_entknn=100_run=2_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.15_PhenoPred=0.0_RuleBasedPred=0.15_loss=ELBO_loss_warmup=5_warmup_mode=linear_encoding=6_k=15_latreg=variance_entknn=100_run=1_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.0_PhenoPred=0.0_RuleBasedPred=0.15_loss=ELBO_loss_warmup=10_warmup_mode=sigmoid_encoding=6_k=15_latreg=variance_entknn=100_run=5_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.15_PhenoPred=0.0_RuleBasedPred=0.15_loss=ELBO_loss_warmup=15_warmup_mode=linear_encoding=6_k=15_latreg=variance_entknn=100_run=7_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.0_PhenoPred=0.0_RuleBasedPred=0.0_loss=ELBO_loss_warmup=15_warmup_mode=linear_encoding=6_k=15_latreg=variance_entknn=100_run=5_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.15_PhenoPred=0.0_RuleBasedPred=0.0_loss=ELBO_loss_warmup=25_warmup_mode=linear_encoding=6_k=15_latreg=variance_entknn=100_run=6_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.0_PhenoPred=0.0_RuleBasedPred=0.15_loss=ELBO_loss_warmup=25_warmup_mode=sigmoid_encoding=6_k=15_latreg=variance_entknn=100_run=7_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.0_PhenoPred=0.0_RuleBasedPred=0.15_loss=ELBO_loss_warmup=5_warmup_mode=sigmoid_encoding=6_k=15_latreg=variance_entknn=100_run=4_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.15_PhenoPred=0.0_RuleBasedPred=0.0_loss=ELBO_loss_warmup=15_warmup_mode=linear_encoding=6_k=15_latreg=variance_entknn=100_run=4_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.0_PhenoPred=0.0_RuleBasedPred=0.0_loss=ELBO_loss_warmup=25_warmup_mode=linear_encoding=6_k=15_latreg=variance_entknn=100_run=10_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.0_PhenoPred=0.0_RuleBasedPred=0.15_loss=ELBO_loss_warmup=20_warmup_mode=linear_encoding=6_k=15_latreg=variance_entknn=100_run=9_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.15_PhenoPred=0.0_RuleBasedPred=0.15_loss=ELBO_loss_warmup=10_warmup_mode=sigmoid_encoding=6_k=15_latreg=variance_entknn=100_run=9_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.0_PhenoPred=0.0_RuleBasedPred=0.0_loss=ELBO_loss_warmup=25_warmup_mode=linear_encoding=6_k=15_latreg=variance_entknn=100_run=7_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.15_PhenoPred=0.0_RuleBasedPred=0.15_loss=ELBO_loss_warmup=25_warmup_mode=linear_encoding=6_k=15_latreg=variance_entknn=100_run=5_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.15_PhenoPred=0.0_RuleBasedPred=0.0_loss=ELBO_loss_warmup=25_warmup_mode=sigmoid_encoding=6_k=15_latreg=variance_entknn=100_run=9_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.0_PhenoPred=0.0_RuleBasedPred=0.0_loss=ELBO_loss_warmup=20_warmup_mode=linear_encoding=6_k=15_latreg=variance_entknn=100_run=10_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.15_PhenoPred=0.0_RuleBasedPred=0.0_loss=ELBO_loss_warmup=5_warmup_mode=sigmoid_encoding=6_k=15_latreg=variance_entknn=100_run=3_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.0_PhenoPred=0.0_RuleBasedPred=0.15_loss=ELBO_loss_warmup=15_warmup_mode=linear_encoding=6_k=15_latreg=variance_entknn=100_run=3_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.15_PhenoPred=0.0_RuleBasedPred=0.15_loss=ELBO_loss_warmup=15_warmup_mode=sigmoid_encoding=6_k=15_latreg=variance_entknn=100_run=9_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.15_PhenoPred=0.0_RuleBasedPred=0.0_loss=ELBO_loss_warmup=20_warmup_mode=sigmoid_encoding=6_k=15_latreg=variance_entknn=100_run=9_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.0_PhenoPred=0.0_RuleBasedPred=0.0_loss=ELBO_loss_warmup=5_warmup_mode=sigmoid_encoding=6_k=15_latreg=variance_entknn=100_run=2_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.0_PhenoPred=0.0_RuleBasedPred=0.15_loss=ELBO_loss_warmup=15_warmup_mode=sigmoid_encoding=6_k=15_latreg=variance_entknn=100_run=5_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.15_PhenoPred=0.0_RuleBasedPred=0.0_loss=ELBO_loss_warmup=5_warmup_mode=sigmoid_encoding=6_k=15_latreg=variance_entknn=100_run=10_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.0_PhenoPred=0.0_RuleBasedPred=0.15_loss=ELBO_loss_warmup=25_warmup_mode=linear_encoding=6_k=15_latreg=variance_entknn=100_run=1_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.0_PhenoPred=0.0_RuleBasedPred=0.15_loss=ELBO_loss_warmup=20_warmup_mode=sigmoid_encoding=6_k=15_latreg=variance_entknn=100_run=7_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.0_PhenoPred=0.0_RuleBasedPred=0.15_loss=ELBO_loss_warmup=20_warmup_mode=linear_encoding=6_k=15_latreg=variance_entknn=100_run=2_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.0_PhenoPred=0.0_RuleBasedPred=0.15_loss=ELBO_loss_warmup=15_warmup_mode=sigmoid_encoding=6_k=15_latreg=variance_entknn=100_run=10_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.15_PhenoPred=0.0_RuleBasedPred=0.15_loss=ELBO_loss_warmup=10_warmup_mode=sigmoid_encoding=6_k=15_latreg=variance_entknn=100_run=2_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.15_PhenoPred=0.0_RuleBasedPred=0.0_loss=ELBO_loss_warmup=25_warmup_mode=sigmoid_encoding=6_k=15_latreg=variance_entknn=100_run=2_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.0_PhenoPred=0.0_RuleBasedPred=0.0_loss=ELBO_loss_warmup=15_warmup_mode=sigmoid_encoding=6_k=15_latreg=variance_entknn=100_run=4_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.0_PhenoPred=0.0_RuleBasedPred=0.0_loss=ELBO_loss_warmup=20_warmup_mode=sigmoid_encoding=6_k=15_latreg=variance_entknn=100_run=6_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.0_PhenoPred=0.0_RuleBasedPred=0.0_loss=ELBO_loss_warmup=5_warmup_mode=linear_encoding=6_k=15_latreg=variance_entknn=100_run=10_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.15_PhenoPred=0.0_RuleBasedPred=0.0_loss=ELBO_loss_warmup=25_warmup_mode=sigmoid_encoding=6_k=15_latreg=variance_entknn=100_run=6_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.0_PhenoPred=0.0_RuleBasedPred=0.0_loss=ELBO_loss_warmup=25_warmup_mode=linear_encoding=6_k=15_latreg=variance_entknn=100_run=8_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.15_PhenoPred=0.0_RuleBasedPred=0.15_loss=ELBO_loss_warmup=25_warmup_mode=sigmoid_encoding=6_k=15_latreg=variance_entknn=100_run=4_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.15_PhenoPred=0.0_RuleBasedPred=0.15_loss=ELBO_loss_warmup=10_warmup_mode=sigmoid_encoding=6_k=15_latreg=variance_entknn=100_run=6_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.0_PhenoPred=0.0_RuleBasedPred=0.15_loss=ELBO_loss_warmup=20_warmup_mode=linear_encoding=6_k=15_latreg=variance_entknn=100_run=6_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.15_PhenoPred=0.0_RuleBasedPred=0.0_loss=ELBO_loss_warmup=10_warmup_mode=sigmoid_encoding=6_k=15_latreg=variance_entknn=100_run=4_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.0_PhenoPred=0.0_RuleBasedPred=0.15_loss=ELBO_loss_warmup=25_warmup_mode=sigmoid_encoding=6_k=15_latreg=variance_entknn=100_run=8_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.0_PhenoPred=0.0_RuleBasedPred=0.0_loss=ELBO_loss_warmup=20_warmup_mode=sigmoid_encoding=6_k=15_latreg=variance_entknn=100_run=2_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.0_PhenoPred=0.0_RuleBasedPred=0.15_loss=ELBO_loss_warmup=10_warmup_mode=linear_encoding=6_k=15_latreg=variance_entknn=100_run=4_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.15_PhenoPred=0.0_RuleBasedPred=0.0_loss=ELBO_loss_warmup=25_warmup_mode=linear_encoding=6_k=15_latreg=variance_entknn=100_run=9_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.15_PhenoPred=0.0_RuleBasedPred=0.15_loss=ELBO_loss_warmup=15_warmup_mode=linear_encoding=6_k=15_latreg=variance_entknn=100_run=8_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.0_PhenoPred=0.0_RuleBasedPred=0.0_loss=ELBO_loss_warmup=5_warmup_mode=linear_encoding=6_k=15_latreg=variance_entknn=100_run=4_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.0_PhenoPred=0.0_RuleBasedPred=0.0_loss=ELBO_loss_warmup=10_warmup_mode=linear_encoding=6_k=15_latreg=variance_entknn=100_run=9_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.15_PhenoPred=0.0_RuleBasedPred=0.0_loss=ELBO_loss_warmup=5_warmup_mode=sigmoid_encoding=6_k=15_latreg=variance_entknn=100_run=7_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.0_PhenoPred=0.0_RuleBasedPred=0.15_loss=ELBO_loss_warmup=15_warmup_mode=linear_encoding=6_k=15_latreg=variance_entknn=100_run=7_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.0_PhenoPred=0.0_RuleBasedPred=0.15_loss=ELBO_loss_warmup=20_warmup_mode=sigmoid_encoding=6_k=15_latreg=variance_entknn=100_run=3_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.0_PhenoPred=0.0_RuleBasedPred=0.0_loss=ELBO_loss_warmup=25_warmup_mode=sigmoid_encoding=6_k=15_latreg=variance_entknn=100_run=9_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.15_PhenoPred=0.0_RuleBasedPred=0.0_loss=ELBO_loss_warmup=10_warmup_mode=linear_encoding=6_k=15_latreg=variance_entknn=100_run=8_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.15_PhenoPred=0.0_RuleBasedPred=0.15_loss=ELBO_loss_warmup=10_warmup_mode=linear_encoding=6_k=15_latreg=variance_entknn=100_run=10_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.0_PhenoPred=0.0_RuleBasedPred=0.15_loss=ELBO_loss_warmup=25_warmup_mode=linear_encoding=6_k=15_latreg=variance_entknn=100_run=5_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.15_PhenoPred=0.0_RuleBasedPred=0.15_loss=ELBO_loss_warmup=20_warmup_mode=linear_encoding=6_k=15_latreg=variance_entknn=100_run=9_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.0_PhenoPred=0.0_RuleBasedPred=0.0_loss=ELBO_loss_warmup=5_warmup_mode=sigmoid_encoding=6_k=15_latreg=variance_entknn=100_run=6_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.0_PhenoPred=0.0_RuleBasedPred=0.15_loss=ELBO_loss_warmup=10_warmup_mode=sigmoid_encoding=6_k=15_latreg=variance_entknn=100_run=10_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.15_PhenoPred=0.0_RuleBasedPred=0.0_loss=ELBO_loss_warmup=25_warmup_mode=linear_encoding=6_k=15_latreg=variance_entknn=100_run=10_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.0_PhenoPred=0.0_RuleBasedPred=0.15_loss=ELBO_loss_warmup=15_warmup_mode=sigmoid_encoding=6_k=15_latreg=variance_entknn=100_run=1_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.15_PhenoPred=0.0_RuleBasedPred=0.15_loss=ELBO_loss_warmup=5_warmup_mode=sigmoid_encoding=6_k=15_latreg=variance_entknn=100_run=4_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.0_PhenoPred=0.0_RuleBasedPred=0.0_loss=ELBO_loss_warmup=20_warmup_mode=sigmoid_encoding=6_k=15_latreg=variance_entknn=100_run=9_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.0_PhenoPred=0.0_RuleBasedPred=0.15_loss=ELBO_loss_warmup=25_warmup_mode=sigmoid_encoding=6_k=15_latreg=variance_entknn=100_run=3_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.15_PhenoPred=0.0_RuleBasedPred=0.0_loss=ELBO_loss_warmup=25_warmup_mode=linear_encoding=6_k=15_latreg=variance_entknn=100_run=2_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.15_PhenoPred=0.0_RuleBasedPred=0.15_loss=ELBO_loss_warmup=15_warmup_mode=linear_encoding=6_k=15_latreg=variance_entknn=100_run=10_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.0_PhenoPred=0.0_RuleBasedPred=0.15_loss=ELBO_loss_warmup=10_warmup_mode=sigmoid_encoding=6_k=15_latreg=variance_entknn=100_run=1_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.15_PhenoPred=0.0_RuleBasedPred=0.15_loss=ELBO_loss_warmup=15_warmup_mode=linear_encoding=6_k=15_latreg=variance_entknn=100_run=3_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.15_PhenoPred=0.0_RuleBasedPred=0.0_loss=ELBO_loss_warmup=20_warmup_mode=linear_encoding=6_k=15_latreg=variance_entknn=100_run=10_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.0_PhenoPred=0.0_RuleBasedPred=0.0_loss=ELBO_loss_warmup=15_warmup_mode=linear_encoding=6_k=15_latreg=variance_entknn=100_run=1_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.15_PhenoPred=0.0_RuleBasedPred=0.0_loss=ELBO_loss_warmup=5_warmup_mode=linear_encoding=6_k=15_latreg=variance_entknn=100_run=4_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.0_PhenoPred=0.0_RuleBasedPred=0.0_loss=ELBO_loss_warmup=25_warmup_mode=linear_encoding=6_k=15_latreg=variance_entknn=100_run=3_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.15_PhenoPred=0.0_RuleBasedPred=0.15_loss=ELBO_loss_warmup=25_warmup_mode=linear_encoding=6_k=15_latreg=variance_entknn=100_run=1_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.0_PhenoPred=0.0_RuleBasedPred=0.0_loss=ELBO_loss_warmup=5_warmup_mode=sigmoid_encoding=6_k=15_latreg=variance_entknn=100_run=10_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.0_PhenoPred=0.0_RuleBasedPred=0.0_loss=ELBO_loss_warmup=25_warmup_mode=sigmoid_encoding=6_k=15_latreg=variance_entknn=100_run=2_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.0_PhenoPred=0.0_RuleBasedPred=0.15_loss=ELBO_loss_warmup=20_warmup_mode=sigmoid_encoding=6_k=15_latreg=variance_entknn=100_run=8_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.0_PhenoPred=0.0_RuleBasedPred=0.15_loss=ELBO_loss_warmup=5_warmup_mode=linear_encoding=6_k=15_latreg=variance_entknn=100_run=4_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.15_PhenoPred=0.0_RuleBasedPred=0.0_loss=ELBO_loss_warmup=10_warmup_mode=linear_encoding=6_k=15_latreg=variance_entknn=100_run=3_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.15_PhenoPred=0.0_RuleBasedPred=0.15_loss=ELBO_loss_warmup=20_warmup_mode=linear_encoding=6_k=15_latreg=variance_entknn=100_run=2_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.15_PhenoPred=0.0_RuleBasedPred=0.0_loss=ELBO_loss_warmup=20_warmup_mode=sigmoid_encoding=6_k=15_latreg=variance_entknn=100_run=6_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.15_PhenoPred=0.0_RuleBasedPred=0.15_loss=ELBO_loss_warmup=5_warmup_mode=linear_encoding=6_k=15_latreg=variance_entknn=100_run=5_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.15_PhenoPred=0.0_RuleBasedPred=0.15_loss=ELBO_loss_warmup=20_warmup_mode=sigmoid_encoding=6_k=15_latreg=variance_entknn=100_run=4_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.0_PhenoPred=0.0_RuleBasedPred=0.0_loss=ELBO_loss_warmup=10_warmup_mode=linear_encoding=6_k=15_latreg=variance_entknn=100_run=2_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.15_PhenoPred=0.0_RuleBasedPred=0.15_loss=ELBO_loss_warmup=15_warmup_mode=sigmoid_encoding=6_k=15_latreg=variance_entknn=100_run=6_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.15_PhenoPred=0.0_RuleBasedPred=0.0_loss=ELBO_loss_warmup=20_warmup_mode=linear_encoding=6_k=15_latreg=variance_entknn=100_run=1_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.15_PhenoPred=0.0_RuleBasedPred=0.0_loss=ELBO_loss_warmup=15_warmup_mode=sigmoid_encoding=6_k=15_latreg=variance_entknn=100_run=4_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.15_PhenoPred=0.0_RuleBasedPred=0.15_loss=ELBO_loss_warmup=5_warmup_mode=linear_encoding=6_k=15_latreg=variance_entknn=100_run=9_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.15_PhenoPred=0.0_RuleBasedPred=0.15_loss=ELBO_loss_warmup=20_warmup_mode=sigmoid_encoding=6_k=15_latreg=variance_entknn=100_run=8_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.15_PhenoPred=0.0_RuleBasedPred=0.0_loss=ELBO_loss_warmup=15_warmup_mode=sigmoid_encoding=6_k=15_latreg=variance_entknn=100_run=8_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.0_PhenoPred=0.0_RuleBasedPred=0.15_loss=ELBO_loss_warmup=20_warmup_mode=sigmoid_encoding=6_k=15_latreg=variance_entknn=100_run=4_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.0_PhenoPred=0.0_RuleBasedPred=0.15_loss=ELBO_loss_warmup=5_warmup_mode=linear_encoding=6_k=15_latreg=variance_entknn=100_run=8_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.0_PhenoPred=0.0_RuleBasedPred=0.15_loss=ELBO_loss_warmup=25_warmup_mode=linear_encoding=6_k=15_latreg=variance_entknn=100_run=2_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.0_PhenoPred=0.0_RuleBasedPred=0.0_loss=ELBO_loss_warmup=5_warmup_mode=sigmoid_encoding=6_k=15_latreg=variance_entknn=100_run=1_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.15_PhenoPred=0.0_RuleBasedPred=0.15_loss=ELBO_loss_warmup=5_warmup_mode=sigmoid_encoding=6_k=15_latreg=variance_entknn=100_run=3_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.0_PhenoPred=0.0_RuleBasedPred=0.15_loss=ELBO_loss_warmup=15_warmup_mode=sigmoid_encoding=6_k=15_latreg=variance_entknn=100_run=6_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.0_PhenoPred=0.0_RuleBasedPred=0.15_loss=ELBO_loss_warmup=15_warmup_mode=linear_encoding=6_k=15_latreg=variance_entknn=100_run=10_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.15_PhenoPred=0.0_RuleBasedPred=0.0_loss=ELBO_loss_warmup=5_warmup_mode=linear_encoding=6_k=15_latreg=variance_entknn=100_run=8_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.15_PhenoPred=0.0_RuleBasedPred=0.0_loss=ELBO_loss_warmup=25_warmup_mode=sigmoid_encoding=6_k=15_latreg=variance_entknn=100_run=1_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.15_PhenoPred=0.0_RuleBasedPred=0.15_loss=ELBO_loss_warmup=25_warmup_mode=sigmoid_encoding=6_k=15_latreg=variance_entknn=100_run=3_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.15_PhenoPred=0.0_RuleBasedPred=0.15_loss=ELBO_loss_warmup=10_warmup_mode=sigmoid_encoding=6_k=15_latreg=variance_entknn=100_run=1_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.0_PhenoPred=0.0_RuleBasedPred=0.15_loss=ELBO_loss_warmup=20_warmup_mode=linear_encoding=6_k=15_latreg=variance_entknn=100_run=1_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.15_PhenoPred=0.0_RuleBasedPred=0.0_loss=ELBO_loss_warmup=10_warmup_mode=sigmoid_encoding=6_k=15_latreg=variance_entknn=100_run=3_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.0_PhenoPred=0.0_RuleBasedPred=0.0_loss=ELBO_loss_warmup=20_warmup_mode=sigmoid_encoding=6_k=15_latreg=variance_entknn=100_run=5_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.0_PhenoPred=0.0_RuleBasedPred=0.15_loss=ELBO_loss_warmup=10_warmup_mode=linear_encoding=6_k=15_latreg=variance_entknn=100_run=3_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.0_PhenoPred=0.0_RuleBasedPred=0.0_loss=ELBO_loss_warmup=5_warmup_mode=linear_encoding=6_k=15_latreg=variance_entknn=100_run=3_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.0_PhenoPred=0.0_RuleBasedPred=0.0_loss=ELBO_loss_warmup=15_warmup_mode=sigmoid_encoding=6_k=15_latreg=variance_entknn=100_run=7_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.0_PhenoPred=0.0_RuleBasedPred=0.15_loss=ELBO_loss_warmup=5_warmup_mode=linear_encoding=6_k=15_latreg=variance_entknn=100_run=3_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.0_PhenoPred=0.0_RuleBasedPred=0.0_loss=ELBO_loss_warmup=25_warmup_mode=sigmoid_encoding=6_k=15_latreg=variance_entknn=100_run=5_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.15_PhenoPred=0.0_RuleBasedPred=0.0_loss=ELBO_loss_warmup=10_warmup_mode=linear_encoding=6_k=15_latreg=variance_entknn=100_run=4_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.0_PhenoPred=0.0_RuleBasedPred=0.15_loss=ELBO_loss_warmup=25_warmup_mode=linear_encoding=6_k=15_latreg=variance_entknn=100_run=9_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.0_PhenoPred=0.0_RuleBasedPred=0.0_loss=ELBO_loss_warmup=10_warmup_mode=sigmoid_encoding=6_k=15_latreg=variance_entknn=100_run=7_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.15_PhenoPred=0.0_RuleBasedPred=0.15_loss=ELBO_loss_warmup=5_warmup_mode=sigmoid_encoding=6_k=15_latreg=variance_entknn=100_run=8_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.0_PhenoPred=0.0_RuleBasedPred=0.0_loss=ELBO_loss_warmup=20_warmup_mode=linear_encoding=6_k=15_latreg=variance_entknn=100_run=7_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.15_PhenoPred=0.0_RuleBasedPred=0.15_loss=ELBO_loss_warmup=20_warmup_mode=linear_encoding=6_k=15_latreg=variance_entknn=100_run=5_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.15_PhenoPred=0.0_RuleBasedPred=0.15_loss=ELBO_loss_warmup=5_warmup_mode=linear_encoding=6_k=15_latreg=variance_entknn=100_run=2_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.15_PhenoPred=0.0_RuleBasedPred=0.0_loss=ELBO_loss_warmup=20_warmup_mode=sigmoid_encoding=6_k=15_latreg=variance_entknn=100_run=1_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.0_PhenoPred=0.0_RuleBasedPred=0.15_loss=ELBO_loss_warmup=10_warmup_mode=linear_encoding=6_k=15_latreg=variance_entknn=100_run=10_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.15_PhenoPred=0.0_RuleBasedPred=0.15_loss=ELBO_loss_warmup=10_warmup_mode=linear_encoding=6_k=15_latreg=variance_entknn=100_run=7_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.15_PhenoPred=0.0_RuleBasedPred=0.15_loss=ELBO_loss_warmup=20_warmup_mode=sigmoid_encoding=6_k=15_latreg=variance_entknn=100_run=3_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.0_PhenoPred=0.0_RuleBasedPred=0.0_loss=ELBO_loss_warmup=10_warmup_mode=linear_encoding=6_k=15_latreg=variance_entknn=100_run=5_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.15_PhenoPred=0.0_RuleBasedPred=0.15_loss=ELBO_loss_warmup=15_warmup_mode=sigmoid_encoding=6_k=15_latreg=variance_entknn=100_run=1_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.15_PhenoPred=0.0_RuleBasedPred=0.0_loss=ELBO_loss_warmup=15_warmup_mode=sigmoid_encoding=6_k=15_latreg=variance_entknn=100_run=3_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.15_PhenoPred=0.0_RuleBasedPred=0.0_loss=ELBO_loss_warmup=20_warmup_mode=linear_encoding=6_k=15_latreg=variance_entknn=100_run=6_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.0_PhenoPred=0.0_RuleBasedPred=0.15_loss=ELBO_loss_warmup=20_warmup_mode=sigmoid_encoding=6_k=15_latreg=variance_entknn=100_run=10_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.0_PhenoPred=0.0_RuleBasedPred=0.15_loss=ELBO_loss_warmup=25_warmup_mode=sigmoid_encoding=6_k=15_latreg=variance_entknn=100_run=4_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.0_PhenoPred=0.0_RuleBasedPred=0.15_loss=ELBO_loss_warmup=10_warmup_mode=linear_encoding=6_k=15_latreg=variance_entknn=100_run=8_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.15_PhenoPred=0.0_RuleBasedPred=0.0_loss=ELBO_loss_warmup=25_warmup_mode=linear_encoding=6_k=15_latreg=variance_entknn=100_run=5_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.15_PhenoPred=0.0_RuleBasedPred=0.15_loss=ELBO_loss_warmup=15_warmup_mode=linear_encoding=6_k=15_latreg=variance_entknn=100_run=4_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.0_PhenoPred=0.0_RuleBasedPred=0.0_loss=ELBO_loss_warmup=5_warmup_mode=linear_encoding=6_k=15_latreg=variance_entknn=100_run=8_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.0_PhenoPred=0.0_RuleBasedPred=0.15_loss=ELBO_loss_warmup=10_warmup_mode=sigmoid_encoding=6_k=15_latreg=variance_entknn=100_run=6_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.0_PhenoPred=0.0_RuleBasedPred=0.0_loss=ELBO_loss_warmup=15_warmup_mode=linear_encoding=6_k=15_latreg=variance_entknn=100_run=6_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.15_PhenoPred=0.0_RuleBasedPred=0.0_loss=ELBO_loss_warmup=5_warmup_mode=linear_encoding=6_k=15_latreg=variance_entknn=100_run=3_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.0_PhenoPred=0.0_RuleBasedPred=0.0_loss=ELBO_loss_warmup=25_warmup_mode=linear_encoding=6_k=15_latreg=variance_entknn=100_run=4_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.15_PhenoPred=0.0_RuleBasedPred=0.15_loss=ELBO_loss_warmup=25_warmup_mode=sigmoid_encoding=6_k=15_latreg=variance_entknn=100_run=8_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.15_PhenoPred=0.0_RuleBasedPred=0.15_loss=ELBO_loss_warmup=25_warmup_mode=linear_encoding=6_k=15_latreg=variance_entknn=100_run=6_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.15_PhenoPred=0.0_RuleBasedPred=0.0_loss=ELBO_loss_warmup=10_warmup_mode=sigmoid_encoding=6_k=15_latreg=variance_entknn=100_run=8_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.0_PhenoPred=0.0_RuleBasedPred=0.15_loss=ELBO_loss_warmup=5_warmup_mode=sigmoid_encoding=6_k=15_latreg=variance_entknn=100_run=7_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.15_PhenoPred=0.0_RuleBasedPred=0.0_loss=ELBO_loss_warmup=15_warmup_mode=linear_encoding=6_k=15_latreg=variance_entknn=100_run=7_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.0_PhenoPred=0.0_RuleBasedPred=0.0_loss=ELBO_loss_warmup=15_warmup_mode=sigmoid_encoding=6_k=15_latreg=variance_entknn=100_run=8_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.0_PhenoPred=0.0_RuleBasedPred=0.15_loss=ELBO_loss_warmup=25_warmup_mode=sigmoid_encoding=6_k=15_latreg=variance_entknn=100_run=10_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.0_PhenoPred=0.0_RuleBasedPred=0.15_loss=ELBO_loss_warmup=10_warmup_mode=sigmoid_encoding=6_k=15_latreg=variance_entknn=100_run=2_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.0_PhenoPred=0.0_RuleBasedPred=0.0_loss=ELBO_loss_warmup=15_warmup_mode=linear_encoding=6_k=15_latreg=variance_entknn=100_run=2_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.15_PhenoPred=0.0_RuleBasedPred=0.0_loss=ELBO_loss_warmup=25_warmup_mode=linear_encoding=6_k=15_latreg=variance_entknn=100_run=1_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.0_PhenoPred=0.0_RuleBasedPred=0.15_loss=ELBO_loss_warmup=5_warmup_mode=sigmoid_encoding=6_k=15_latreg=variance_entknn=100_run=3_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.15_PhenoPred=0.0_RuleBasedPred=0.0_loss=ELBO_loss_warmup=15_warmup_mode=linear_encoding=6_k=15_latreg=variance_entknn=100_run=3_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.15_PhenoPred=0.0_RuleBasedPred=0.15_loss=ELBO_loss_warmup=25_warmup_mode=linear_encoding=6_k=15_latreg=variance_entknn=100_run=2_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.15_PhenoPred=0.0_RuleBasedPred=0.0_loss=ELBO_loss_warmup=5_warmup_mode=linear_encoding=6_k=15_latreg=variance_entknn=100_run=7_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.0_PhenoPred=0.0_RuleBasedPred=0.0_loss=ELBO_loss_warmup=10_warmup_mode=sigmoid_encoding=6_k=15_latreg=variance_entknn=100_run=3_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.0_PhenoPred=0.0_RuleBasedPred=0.15_loss=ELBO_loss_warmup=15_warmup_mode=sigmoid_encoding=6_k=15_latreg=variance_entknn=100_run=9_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.0_PhenoPred=0.0_RuleBasedPred=0.0_loss=ELBO_loss_warmup=20_warmup_mode=linear_encoding=6_k=15_latreg=variance_entknn=100_run=3_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.15_PhenoPred=0.0_RuleBasedPred=0.15_loss=ELBO_loss_warmup=20_warmup_mode=linear_encoding=6_k=15_latreg=variance_entknn=100_run=1_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.0_PhenoPred=0.0_RuleBasedPred=0.15_loss=ELBO_loss_warmup=5_warmup_mode=linear_encoding=6_k=15_latreg=variance_entknn=100_run=7_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.0_PhenoPred=0.0_RuleBasedPred=0.0_loss=ELBO_loss_warmup=25_warmup_mode=sigmoid_encoding=6_k=15_latreg=variance_entknn=100_run=1_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.15_PhenoPred=0.0_RuleBasedPred=0.0_loss=ELBO_loss_warmup=20_warmup_mode=linear_encoding=6_k=15_latreg=variance_entknn=100_run=2_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.15_PhenoPred=0.0_RuleBasedPred=0.0_loss=ELBO_loss_warmup=15_warmup_mode=sigmoid_encoding=6_k=15_latreg=variance_entknn=100_run=7_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.15_PhenoPred=0.0_RuleBasedPred=0.15_loss=ELBO_loss_warmup=15_warmup_mode=sigmoid_encoding=6_k=15_latreg=variance_entknn=100_run=5_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.15_PhenoPred=0.0_RuleBasedPred=0.15_loss=ELBO_loss_warmup=10_warmup_mode=linear_encoding=6_k=15_latreg=variance_entknn=100_run=3_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.15_PhenoPred=0.0_RuleBasedPred=0.15_loss=ELBO_loss_warmup=20_warmup_mode=sigmoid_encoding=6_k=15_latreg=variance_entknn=100_run=7_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.0_PhenoPred=0.0_RuleBasedPred=0.0_loss=ELBO_loss_warmup=10_warmup_mode=linear_encoding=6_k=15_latreg=variance_entknn=100_run=1_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.15_PhenoPred=0.0_RuleBasedPred=0.15_loss=ELBO_loss_warmup=5_warmup_mode=linear_encoding=6_k=15_latreg=variance_entknn=100_run=6_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.15_PhenoPred=0.0_RuleBasedPred=0.0_loss=ELBO_loss_warmup=20_warmup_mode=sigmoid_encoding=6_k=15_latreg=variance_entknn=100_run=5_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.15_PhenoPred=0.0_RuleBasedPred=0.0_loss=ELBO_loss_warmup=15_warmup_mode=linear_encoding=6_k=15_latreg=variance_entknn=100_run=8_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.0_PhenoPred=0.0_RuleBasedPred=0.15_loss=ELBO_loss_warmup=20_warmup_mode=linear_encoding=6_k=15_latreg=variance_entknn=100_run=5_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.0_PhenoPred=0.0_RuleBasedPred=0.15_loss=ELBO_loss_warmup=5_warmup_mode=sigmoid_encoding=6_k=15_latreg=variance_entknn=100_run=8_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.15_PhenoPred=0.0_RuleBasedPred=0.0_loss=ELBO_loss_warmup=10_warmup_mode=sigmoid_encoding=6_k=15_latreg=variance_entknn=100_run=7_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.15_PhenoPred=0.0_RuleBasedPred=0.15_loss=ELBO_loss_warmup=10_warmup_mode=sigmoid_encoding=6_k=15_latreg=variance_entknn=100_run=5_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.15_PhenoPred=0.0_RuleBasedPred=0.15_loss=ELBO_loss_warmup=25_warmup_mode=linear_encoding=6_k=15_latreg=variance_entknn=100_run=9_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.15_PhenoPred=0.0_RuleBasedPred=0.15_loss=ELBO_loss_warmup=25_warmup_mode=sigmoid_encoding=6_k=15_latreg=variance_entknn=100_run=7_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.15_PhenoPred=0.0_RuleBasedPred=0.0_loss=ELBO_loss_warmup=25_warmup_mode=sigmoid_encoding=6_k=15_latreg=variance_entknn=100_run=5_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.0_PhenoPred=0.0_RuleBasedPred=0.0_loss=ELBO_loss_warmup=15_warmup_mode=linear_encoding=6_k=15_latreg=variance_entknn=100_run=9_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.0_PhenoPred=0.0_RuleBasedPred=0.15_loss=ELBO_loss_warmup=10_warmup_mode=sigmoid_encoding=6_k=15_latreg=variance_entknn=100_run=9_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.0_PhenoPred=0.0_RuleBasedPred=0.0_loss=ELBO_loss_warmup=5_warmup_mode=linear_encoding=6_k=15_latreg=variance_entknn=100_run=7_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.0_PhenoPred=0.0_RuleBasedPred=0.0_loss=ELBO_loss_warmup=15_warmup_mode=sigmoid_encoding=6_k=15_latreg=variance_entknn=100_run=3_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.0_PhenoPred=0.0_RuleBasedPred=0.15_loss=ELBO_loss_warmup=10_warmup_mode=linear_encoding=6_k=15_latreg=variance_entknn=100_run=7_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.0_PhenoPred=0.0_RuleBasedPred=0.0_loss=ELBO_loss_warmup=20_warmup_mode=sigmoid_encoding=6_k=15_latreg=variance_entknn=100_run=1_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.15_PhenoPred=0.0_RuleBasedPred=0.0_loss=ELBO_loss_warmup=5_warmup_mode=sigmoid_encoding=6_k=15_latreg=variance_entknn=100_run=4_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.0_PhenoPred=0.0_RuleBasedPred=0.15_loss=ELBO_loss_warmup=15_warmup_mode=linear_encoding=6_k=15_latreg=variance_entknn=100_run=4_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.15_PhenoPred=0.0_RuleBasedPred=0.0_loss=ELBO_loss_warmup=20_warmup_mode=linear_encoding=6_k=15_latreg=variance_entknn=100_run=9_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.15_PhenoPred=0.0_RuleBasedPred=0.15_loss=ELBO_loss_warmup=10_warmup_mode=linear_encoding=6_k=15_latreg=variance_entknn=100_run=8_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.0_PhenoPred=0.0_RuleBasedPred=0.0_loss=ELBO_loss_warmup=5_warmup_mode=sigmoid_encoding=6_k=15_latreg=variance_entknn=100_run=5_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.0_PhenoPred=0.0_RuleBasedPred=0.15_loss=ELBO_loss_warmup=15_warmup_mode=sigmoid_encoding=6_k=15_latreg=variance_entknn=100_run=2_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.0_PhenoPred=0.0_RuleBasedPred=0.0_loss=ELBO_loss_warmup=20_warmup_mode=linear_encoding=6_k=15_latreg=variance_entknn=100_run=8_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.15_PhenoPred=0.0_RuleBasedPred=0.15_loss=ELBO_loss_warmup=5_warmup_mode=sigmoid_encoding=6_k=15_latreg=variance_entknn=100_run=7_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.0_PhenoPred=0.0_RuleBasedPred=0.0_loss=ELBO_loss_warmup=10_warmup_mode=sigmoid_encoding=6_k=15_latreg=variance_entknn=100_run=8_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.0_PhenoPred=0.0_RuleBasedPred=0.15_loss=ELBO_loss_warmup=25_warmup_mode=linear_encoding=6_k=15_latreg=variance_entknn=100_run=6_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.0_PhenoPred=0.0_RuleBasedPred=0.0_loss=ELBO_loss_warmup=15_warmup_mode=sigmoid_encoding=6_k=15_latreg=variance_entknn=100_run=10_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.0_PhenoPred=0.0_RuleBasedPred=0.0_loss=ELBO_loss_warmup=15_warmup_mode=sigmoid_encoding=6_k=15_latreg=variance_entknn=100_run=6_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.0_PhenoPred=0.0_RuleBasedPred=0.0_loss=ELBO_loss_warmup=5_warmup_mode=linear_encoding=6_k=15_latreg=variance_entknn=100_run=2_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.15_PhenoPred=0.0_RuleBasedPred=0.0_loss=ELBO_loss_warmup=25_warmup_mode=sigmoid_encoding=6_k=15_latreg=variance_entknn=100_run=10_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.0_PhenoPred=0.0_RuleBasedPred=0.0_loss=ELBO_loss_warmup=20_warmup_mode=sigmoid_encoding=6_k=15_latreg=variance_entknn=100_run=4_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.0_PhenoPred=0.0_RuleBasedPred=0.15_loss=ELBO_loss_warmup=10_warmup_mode=linear_encoding=6_k=15_latreg=variance_entknn=100_run=2_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.15_PhenoPred=0.0_RuleBasedPred=0.0_loss=ELBO_loss_warmup=10_warmup_mode=sigmoid_encoding=6_k=15_latreg=variance_entknn=100_run=2_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.15_PhenoPred=0.0_RuleBasedPred=0.0_loss=ELBO_loss_warmup=5_warmup_mode=linear_encoding=6_k=15_latreg=variance_entknn=100_run=9_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.15_PhenoPred=0.0_RuleBasedPred=0.15_loss=ELBO_loss_warmup=25_warmup_mode=sigmoid_encoding=6_k=15_latreg=variance_entknn=100_run=2_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.15_PhenoPred=0.0_RuleBasedPred=0.15_loss=ELBO_loss_warmup=5_warmup_mode=sigmoid_encoding=6_k=15_latreg=variance_entknn=100_run=2_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.0_PhenoPred=0.0_RuleBasedPred=0.15_loss=ELBO_loss_warmup=15_warmup_mode=sigmoid_encoding=6_k=15_latreg=variance_entknn=100_run=7_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.15_PhenoPred=0.0_RuleBasedPred=0.15_loss=ELBO_loss_warmup=5_warmup_mode=sigmoid_encoding=6_k=15_latreg=variance_entknn=100_run=10_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.0_PhenoPred=0.0_RuleBasedPred=0.15_loss=ELBO_loss_warmup=20_warmup_mode=sigmoid_encoding=6_k=15_latreg=variance_entknn=100_run=5_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.0_PhenoPred=0.0_RuleBasedPred=0.15_loss=ELBO_loss_warmup=5_warmup_mode=linear_encoding=6_k=15_latreg=variance_entknn=100_run=9_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.0_PhenoPred=0.0_RuleBasedPred=0.15_loss=ELBO_loss_warmup=25_warmup_mode=linear_encoding=6_k=15_latreg=variance_entknn=100_run=3_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.15_PhenoPred=0.0_RuleBasedPred=0.0_loss=ELBO_loss_warmup=15_warmup_mode=sigmoid_encoding=6_k=15_latreg=variance_entknn=100_run=9_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.0_PhenoPred=0.0_RuleBasedPred=0.15_loss=ELBO_loss_warmup=15_warmup_mode=linear_encoding=6_k=15_latreg=variance_entknn=100_run=1_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.15_PhenoPred=0.0_RuleBasedPred=0.0_loss=ELBO_loss_warmup=5_warmup_mode=sigmoid_encoding=6_k=15_latreg=variance_entknn=100_run=1_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.15_PhenoPred=0.0_RuleBasedPred=0.15_loss=ELBO_loss_warmup=5_warmup_mode=linear_encoding=6_k=15_latreg=variance_entknn=100_run=8_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.0_PhenoPred=0.0_RuleBasedPred=0.0_loss=ELBO_loss_warmup=15_warmup_mode=linear_encoding=6_k=15_latreg=variance_entknn=100_run=10_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.15_PhenoPred=0.0_RuleBasedPred=0.15_loss=ELBO_loss_warmup=20_warmup_mode=sigmoid_encoding=6_k=15_latreg=variance_entknn=100_run=9_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.15_PhenoPred=0.0_RuleBasedPred=0.0_loss=ELBO_loss_warmup=15_warmup_mode=linear_encoding=6_k=15_latreg=variance_entknn=100_run=6_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.0_PhenoPred=0.0_RuleBasedPred=0.15_loss=ELBO_loss_warmup=5_warmup_mode=sigmoid_encoding=6_k=15_latreg=variance_entknn=100_run=6_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.15_PhenoPred=0.0_RuleBasedPred=0.0_loss=ELBO_loss_warmup=10_warmup_mode=sigmoid_encoding=6_k=15_latreg=variance_entknn=100_run=9_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.15_PhenoPred=0.0_RuleBasedPred=0.0_loss=ELBO_loss_warmup=5_warmup_mode=linear_encoding=6_k=15_latreg=variance_entknn=100_run=2_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.0_PhenoPred=0.0_RuleBasedPred=0.0_loss=ELBO_loss_warmup=10_warmup_mode=linear_encoding=6_k=15_latreg=variance_entknn=100_run=10_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.15_PhenoPred=0.0_RuleBasedPred=0.15_loss=ELBO_loss_warmup=25_warmup_mode=linear_encoding=6_k=15_latreg=variance_entknn=100_run=7_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.15_PhenoPred=0.0_RuleBasedPred=0.15_loss=ELBO_loss_warmup=25_warmup_mode=sigmoid_encoding=6_k=15_latreg=variance_entknn=100_run=9_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.0_PhenoPred=0.0_RuleBasedPred=0.0_loss=ELBO_loss_warmup=25_warmup_mode=linear_encoding=6_k=15_latreg=variance_entknn=100_run=5_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.15_PhenoPred=0.0_RuleBasedPred=0.15_loss=ELBO_loss_warmup=10_warmup_mode=sigmoid_encoding=6_k=15_latreg=variance_entknn=100_run=10_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.0_PhenoPred=0.0_RuleBasedPred=0.0_loss=ELBO_loss_warmup=15_warmup_mode=linear_encoding=6_k=15_latreg=variance_entknn=100_run=7_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.15_PhenoPred=0.0_RuleBasedPred=0.15_loss=ELBO_loss_warmup=15_warmup_mode=linear_encoding=6_k=15_latreg=variance_entknn=100_run=5_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.0_PhenoPred=0.0_RuleBasedPred=0.0_loss=ELBO_loss_warmup=5_warmup_mode=linear_encoding=6_k=15_latreg=variance_entknn=100_run=9_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.0_PhenoPred=0.0_RuleBasedPred=0.15_loss=ELBO_loss_warmup=10_warmup_mode=sigmoid_encoding=6_k=15_latreg=variance_entknn=100_run=7_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.0_PhenoPred=0.0_RuleBasedPred=0.15_loss=ELBO_loss_warmup=25_warmup_mode=sigmoid_encoding=6_k=15_latreg=variance_entknn=100_run=5_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.15_PhenoPred=0.0_RuleBasedPred=0.0_loss=ELBO_loss_warmup=25_warmup_mode=linear_encoding=6_k=15_latreg=variance_entknn=100_run=4_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.0_PhenoPred=0.0_RuleBasedPred=0.15_loss=ELBO_loss_warmup=10_warmup_mode=linear_encoding=6_k=15_latreg=variance_entknn=100_run=9_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.15_PhenoPred=0.0_RuleBasedPred=0.0_loss=ELBO_loss_warmup=15_warmup_mode=sigmoid_encoding=6_k=15_latreg=variance_entknn=100_run=2_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.15_PhenoPred=0.0_RuleBasedPred=0.0_loss=ELBO_loss_warmup=20_warmup_mode=linear_encoding=6_k=15_latreg=variance_entknn=100_run=7_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.15_PhenoPred=0.0_RuleBasedPred=0.15_loss=ELBO_loss_warmup=5_warmup_mode=linear_encoding=6_k=15_latreg=variance_entknn=100_run=3_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.0_PhenoPred=0.0_RuleBasedPred=0.0_loss=ELBO_loss_warmup=10_warmup_mode=linear_encoding=6_k=15_latreg=variance_entknn=100_run=4_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.15_PhenoPred=0.0_RuleBasedPred=0.15_loss=ELBO_loss_warmup=20_warmup_mode=sigmoid_encoding=6_k=15_latreg=variance_entknn=100_run=2_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.15_PhenoPred=0.0_RuleBasedPred=0.15_loss=ELBO_loss_warmup=10_warmup_mode=linear_encoding=6_k=15_latreg=variance_entknn=100_run=6_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.15_PhenoPred=0.0_RuleBasedPred=0.15_loss=ELBO_loss_warmup=20_warmup_mode=linear_encoding=6_k=15_latreg=variance_entknn=100_run=4_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.15_PhenoPred=0.0_RuleBasedPred=0.15_loss=ELBO_loss_warmup=5_warmup_mode=sigmoid_encoding=6_k=15_latreg=variance_entknn=100_run=9_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.0_PhenoPred=0.0_RuleBasedPred=0.0_loss=ELBO_loss_warmup=20_warmup_mode=linear_encoding=6_k=15_latreg=variance_entknn=100_run=6_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.0_PhenoPred=0.0_RuleBasedPred=0.0_loss=ELBO_loss_warmup=10_warmup_mode=sigmoid_encoding=6_k=15_latreg=variance_entknn=100_run=6_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.0_PhenoPred=0.0_RuleBasedPred=0.15_loss=ELBO_loss_warmup=5_warmup_mode=linear_encoding=6_k=15_latreg=variance_entknn=100_run=10_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.0_PhenoPred=0.0_RuleBasedPred=0.0_loss=ELBO_loss_warmup=25_warmup_mode=sigmoid_encoding=6_k=15_latreg=variance_entknn=100_run=4_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.0_PhenoPred=0.0_RuleBasedPred=0.15_loss=ELBO_loss_warmup=5_warmup_mode=linear_encoding=6_k=15_latreg=variance_entknn=100_run=2_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.0_PhenoPred=0.0_RuleBasedPred=0.15_loss=ELBO_loss_warmup=25_warmup_mode=linear_encoding=6_k=15_latreg=variance_entknn=100_run=8_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.15_PhenoPred=0.0_RuleBasedPred=0.0_loss=ELBO_loss_warmup=10_warmup_mode=linear_encoding=6_k=15_latreg=variance_entknn=100_run=5_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.15_PhenoPred=0.0_RuleBasedPred=0.15_loss=ELBO_loss_warmup=20_warmup_mode=sigmoid_encoding=6_k=15_latreg=variance_entknn=100_run=6_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.15_PhenoPred=0.0_RuleBasedPred=0.15_loss=ELBO_loss_warmup=10_warmup_mode=linear_encoding=6_k=15_latreg=variance_entknn=100_run=2_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.15_PhenoPred=0.0_RuleBasedPred=0.0_loss=ELBO_loss_warmup=20_warmup_mode=sigmoid_encoding=6_k=15_latreg=variance_entknn=100_run=4_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.15_PhenoPred=0.0_RuleBasedPred=0.15_loss=ELBO_loss_warmup=5_warmup_mode=linear_encoding=6_k=15_latreg=variance_entknn=100_run=7_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.15_PhenoPred=0.0_RuleBasedPred=0.0_loss=ELBO_loss_warmup=20_warmup_mode=linear_encoding=6_k=15_latreg=variance_entknn=100_run=3_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.15_PhenoPred=0.0_RuleBasedPred=0.0_loss=ELBO_loss_warmup=15_warmup_mode=sigmoid_encoding=6_k=15_latreg=variance_entknn=100_run=6_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.15_PhenoPred=0.0_RuleBasedPred=0.15_loss=ELBO_loss_warmup=15_warmup_mode=sigmoid_encoding=6_k=15_latreg=variance_entknn=100_run=10_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.15_PhenoPred=0.0_RuleBasedPred=0.15_loss=ELBO_loss_warmup=15_warmup_mode=sigmoid_encoding=6_k=15_latreg=variance_entknn=100_run=4_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.15_PhenoPred=0.0_RuleBasedPred=0.0_loss=ELBO_loss_warmup=10_warmup_mode=linear_encoding=6_k=15_latreg=variance_entknn=100_run=1_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.0_PhenoPred=0.0_RuleBasedPred=0.15_loss=ELBO_loss_warmup=5_warmup_mode=linear_encoding=6_k=15_latreg=variance_entknn=100_run=6_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.0_PhenoPred=0.0_RuleBasedPred=0.15_loss=ELBO_loss_warmup=15_warmup_mode=sigmoid_encoding=6_k=15_latreg=variance_entknn=100_run=8_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.0_PhenoPred=0.0_RuleBasedPred=0.0_loss=ELBO_loss_warmup=20_warmup_mode=linear_encoding=6_k=15_latreg=variance_entknn=100_run=2_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.0_PhenoPred=0.0_RuleBasedPred=0.0_loss=ELBO_loss_warmup=10_warmup_mode=sigmoid_encoding=6_k=15_latreg=variance_entknn=100_run=2_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.15_PhenoPred=0.0_RuleBasedPred=0.15_loss=ELBO_loss_warmup=25_warmup_mode=linear_encoding=6_k=15_latreg=variance_entknn=100_run=3_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.0_PhenoPred=0.0_RuleBasedPred=0.0_loss=ELBO_loss_warmup=25_warmup_mode=linear_encoding=6_k=15_latreg=variance_entknn=100_run=1_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.15_PhenoPred=0.0_RuleBasedPred=0.0_loss=ELBO_loss_warmup=5_warmup_mode=linear_encoding=6_k=15_latreg=variance_entknn=100_run=6_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.15_PhenoPred=0.0_RuleBasedPred=0.0_loss=ELBO_loss_warmup=15_warmup_mode=linear_encoding=6_k=15_latreg=variance_entknn=100_run=2_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.0_PhenoPred=0.0_RuleBasedPred=0.15_loss=ELBO_loss_warmup=5_warmup_mode=sigmoid_encoding=6_k=15_latreg=variance_entknn=100_run=2_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.15_PhenoPred=0.0_RuleBasedPred=0.0_loss=ELBO_loss_warmup=15_warmup_mode=linear_encoding=6_k=15_latreg=variance_entknn=100_run=10_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.0_PhenoPred=0.0_RuleBasedPred=0.15_loss=ELBO_loss_warmup=25_warmup_mode=sigmoid_encoding=6_k=15_latreg=variance_entknn=100_run=1_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.0_PhenoPred=0.0_RuleBasedPred=0.0_loss=ELBO_loss_warmup=15_warmup_mode=linear_encoding=6_k=15_latreg=variance_entknn=100_run=3_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.15_PhenoPred=0.0_RuleBasedPred=0.15_loss=ELBO_loss_warmup=15_warmup_mode=linear_encoding=6_k=15_latreg=variance_entknn=100_run=1_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.0_PhenoPred=0.0_RuleBasedPred=0.15_loss=ELBO_loss_warmup=10_warmup_mode=sigmoid_encoding=6_k=15_latreg=variance_entknn=100_run=3_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.0_PhenoPred=0.0_RuleBasedPred=0.0_loss=ELBO_loss_warmup=15_warmup_mode=sigmoid_encoding=6_k=15_latreg=variance_entknn=100_run=9_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.15_PhenoPred=0.0_RuleBasedPred=0.15_loss=ELBO_loss_warmup=20_warmup_mode=linear_encoding=6_k=15_latreg=variance_entknn=100_run=10_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.0_PhenoPred=0.0_RuleBasedPred=0.15_loss=ELBO_loss_warmup=25_warmup_mode=linear_encoding=6_k=15_latreg=variance_entknn=100_run=7_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.0_PhenoPred=0.0_RuleBasedPred=0.15_loss=ELBO_loss_warmup=20_warmup_mode=sigmoid_encoding=6_k=15_latreg=variance_entknn=100_run=1_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.15_PhenoPred=0.0_RuleBasedPred=0.0_loss=ELBO_loss_warmup=10_warmup_mode=linear_encoding=6_k=15_latreg=variance_entknn=100_run=10_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.0_PhenoPred=0.0_RuleBasedPred=0.0_loss=ELBO_loss_warmup=10_warmup_mode=sigmoid_encoding=6_k=15_latreg=variance_entknn=100_run=9_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.0_PhenoPred=0.0_RuleBasedPred=0.15_loss=ELBO_loss_warmup=15_warmup_mode=sigmoid_encoding=6_k=15_latreg=variance_entknn=100_run=3_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.0_PhenoPred=0.0_RuleBasedPred=0.0_loss=ELBO_loss_warmup=20_warmup_mode=linear_encoding=6_k=15_latreg=variance_entknn=100_run=9_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.15_PhenoPred=0.0_RuleBasedPred=0.15_loss=ELBO_loss_warmup=5_warmup_mode=sigmoid_encoding=6_k=15_latreg=variance_entknn=100_run=6_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.0_PhenoPred=0.0_RuleBasedPred=0.0_loss=ELBO_loss_warmup=5_warmup_mode=sigmoid_encoding=6_k=15_latreg=variance_entknn=100_run=4_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.15_PhenoPred=0.0_RuleBasedPred=0.15_loss=ELBO_loss_warmup=25_warmup_mode=linear_encoding=6_k=15_latreg=variance_entknn=100_run=10_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.15_PhenoPred=0.0_RuleBasedPred=0.15_loss=ELBO_loss_warmup=10_warmup_mode=linear_encoding=6_k=15_latreg=variance_entknn=100_run=9_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.15_PhenoPred=0.0_RuleBasedPred=0.0_loss=ELBO_loss_warmup=20_warmup_mode=sigmoid_encoding=6_k=15_latreg=variance_entknn=100_run=10_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.15_PhenoPred=0.0_RuleBasedPred=0.0_loss=ELBO_loss_warmup=20_warmup_mode=linear_encoding=6_k=15_latreg=variance_entknn=100_run=8_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.0_PhenoPred=0.0_RuleBasedPred=0.15_loss=ELBO_loss_warmup=15_warmup_mode=linear_encoding=6_k=15_latreg=variance_entknn=100_run=5_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.15_PhenoPred=0.0_RuleBasedPred=0.0_loss=ELBO_loss_warmup=5_warmup_mode=sigmoid_encoding=6_k=15_latreg=variance_entknn=100_run=5_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.0_PhenoPred=0.0_RuleBasedPred=0.0_loss=ELBO_loss_warmup=10_warmup_mode=sigmoid_encoding=6_k=15_latreg=variance_entknn=100_run=10_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.0_PhenoPred=0.0_RuleBasedPred=0.15_loss=ELBO_loss_warmup=10_warmup_mode=linear_encoding=6_k=15_latreg=variance_entknn=100_run=6_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.0_PhenoPred=0.0_RuleBasedPred=0.0_loss=ELBO_loss_warmup=15_warmup_mode=sigmoid_encoding=6_k=15_latreg=variance_entknn=100_run=2_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.0_PhenoPred=0.0_RuleBasedPred=0.15_loss=ELBO_loss_warmup=10_warmup_mode=sigmoid_encoding=6_k=15_latreg=variance_entknn=100_run=8_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.0_PhenoPred=0.0_RuleBasedPred=0.0_loss=ELBO_loss_warmup=5_warmup_mode=linear_encoding=6_k=15_latreg=variance_entknn=100_run=6_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.0_PhenoPred=0.0_RuleBasedPred=0.0_loss=ELBO_loss_warmup=15_warmup_mode=linear_encoding=6_k=15_latreg=variance_entknn=100_run=8_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.15_PhenoPred=0.0_RuleBasedPred=0.15_loss=ELBO_loss_warmup=25_warmup_mode=sigmoid_encoding=6_k=15_latreg=variance_entknn=100_run=6_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.15_PhenoPred=0.0_RuleBasedPred=0.15_loss=ELBO_loss_warmup=25_warmup_mode=linear_encoding=6_k=15_latreg=variance_entknn=100_run=8_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.15_PhenoPred=0.0_RuleBasedPred=0.0_loss=ELBO_loss_warmup=25_warmup_mode=sigmoid_encoding=6_k=15_latreg=variance_entknn=100_run=4_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.15_PhenoPred=0.0_RuleBasedPred=0.15_loss=ELBO_loss_warmup=5_warmup_mode=linear_encoding=6_k=15_latreg=variance_entknn=100_run=10_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.15_PhenoPred=0.0_RuleBasedPred=0.0_loss=ELBO_loss_warmup=10_warmup_mode=sigmoid_encoding=6_k=15_latreg=variance_entknn=100_run=6_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.0_PhenoPred=0.0_RuleBasedPred=0.15_loss=ELBO_loss_warmup=5_warmup_mode=sigmoid_encoding=6_k=15_latreg=variance_entknn=100_run=9_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.0_PhenoPred=0.0_RuleBasedPred=0.15_loss=ELBO_loss_warmup=20_warmup_mode=linear_encoding=6_k=15_latreg=variance_entknn=100_run=4_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.15_PhenoPred=0.0_RuleBasedPred=0.0_loss=ELBO_loss_warmup=15_warmup_mode=linear_encoding=6_k=15_latreg=variance_entknn=100_run=9_final_weights.h5',\n",
       " 'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.15_PhenoPred=0.0_RuleBasedPred=0.15_loss=ELBO_loss_warmup=10_warmup_mode=sigmoid_encoding=6_k=15_latreg=variance_entknn=100_run=4_final_weights.h5']"
584
585
      ]
     },
lucas_miranda's avatar
lucas_miranda committed
586
     "execution_count": 9,
587
588
589
590
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
591
592
593
594
595
596
   "source": [
    "[i for i in os.listdir(trained_network) if i.endswith(\"h5\")]"
   ]
  },
  {
   "cell_type": "code",
lucas_miranda's avatar
lucas_miranda committed
597
   "execution_count": 10,
598
   "metadata": {},
599
600
601
602
   "outputs": [
    {
     "data": {
      "text/plain": [
603
       "'GMVAE_input_type=coords_window_size=22_NextSeqPred=0.0_PhenoPred=0.0_RuleBasedPred=0.0_loss=ELBO_loss_warmup=25_warmup_mode=linear_encoding=6_k=15_latreg=variance_entknn=100_run=6_final_weights.h5'"
604
605
      ]
     },
lucas_miranda's avatar
lucas_miranda committed
606
     "execution_count": 10,
607
608
609
610
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
611
   "source": [
612
    "deepof_weights = [i for i in os.listdir(trained_network) if i.endswith(\"h5\")][1]\n",
613
614
615
616
617
    "deepof_weights"
   ]
  },
  {
   "cell_type": "code",
lucas_miranda's avatar
lucas_miranda committed
618
   "execution_count": 11,
619
620
621
   "metadata": {},
   "outputs": [],
   "source": [
622
623
624
625
    "# Set model parameters\n",
    "encoding = int(re.findall(\"encoding=(\\d+)_\", deepof_weights)[0])\n",
    "k = int(re.findall(\"k=(\\d+)_\", deepof_weights)[0])\n",
    "loss = re.findall(\"loss=(.+?)_\", deepof_weights)[0]\n",
626
627
628
    "NextSeqPred = float(re.findall(\"NextSeqPred=(.+?)_\", deepof_weights)[0])\n",
    "PhenoPred = float(re.findall(\"PhenoPred=(.+?)_\", deepof_weights)[0])\n",
    "RuleBasedPred = float(re.findall(\"RuleBasedPred=(.+?)_\", deepof_weights)[0])"
629
630
631
632
   ]
  },
  {
   "cell_type": "code",
lucas_miranda's avatar
lucas_miranda committed
633
   "execution_count": 15,
634
   "metadata": {},
635
   "outputs": [],
636
   "source": [
637
    "(\n",
638
    "    encoder,\n",
639
640
641
642
643
    "    decoder,\n",
    "    grouper,\n",
    "    gmvaep,\n",
    "    prior,\n",
    "    posterior,\n",
644
    ") = deepof.models.GMVAE(\n",
645
646
647
    "    loss=loss,\n",
    "    number_of_components=k,\n",
    "    compile_model=True,\n",
648
    "    batch_size=batch_size,\n",
649
    "    encoding=encoding,\n",
650
651
652
    "    next_sequence_prediction=NextSeqPred,\n",
    "    phenotype_prediction=PhenoPred,\n",
    "    rule_based_prediction=RuleBasedPred,\n",
653
654
655
    ").build(\n",
    "    data_prep.shape\n",
    ")\n",
656
    "gmvaep.load_weights(os.path.join(trained_network, deepof_weights))"
657
658
   ]
  },
lucas_miranda's avatar
lucas_miranda committed
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {},
   "outputs": [
    {
     "ename": "InvalidArgumentError",
     "evalue": " slice index 15 of dimension 0 out of bounds.\n\t [[{{node SEQ_2_SEQ_GMVAE/cluster_overlap_1/map/while/body/_10/SEQ_2_SEQ_GMVAE/cluster_overlap_1/map/while/PartitionedCall/PartitionedCall/strided_slice}}]] [Op:__inference_predict_function_37314]\n\nFunction call stack:\npredict_function\n",
     "output_type": "error",
     "traceback": [
      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[0;31mInvalidArgumentError\u001b[0m                      Traceback (most recent call last)",
      "\u001b[0;32m<ipython-input-16-9722ae5ef3e8>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m\u001b[0m\n\u001b[0;32m----> 1\u001b[0;31m \u001b[0mgmvaep\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mpredict\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mdata_prep\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;36m10\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m",
      "\u001b[0;32m~/opt/anaconda3/envs/Machine_Learning/lib/python3.6/site-packages/tensorflow/python/keras/engine/training.py\u001b[0m in \u001b[0;36mpredict\u001b[0;34m(self, x, batch_size, verbose, steps, callbacks, max_queue_size, workers, use_multiprocessing)\u001b[0m\n\u001b[1;32m   1627\u001b[0m           \u001b[0;32mfor\u001b[0m \u001b[0mstep\u001b[0m \u001b[0;32min\u001b[0m \u001b[0mdata_handler\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0msteps\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   1628\u001b[0m             \u001b[0mcallbacks\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mon_predict_batch_begin\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mstep\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 1629\u001b[0;31m             \u001b[0mtmp_batch_outputs\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mpredict_function\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0miterator\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m   1630\u001b[0m             \u001b[0;32mif\u001b[0m \u001b[0mdata_handler\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mshould_sync\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   1631\u001b[0m               \u001b[0mcontext\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0masync_wait\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m~/opt/anaconda3/envs/Machine_Learning/lib/python3.6/site-packages/tensorflow/python/eager/def_function.py\u001b[0m in \u001b[0;36m__call__\u001b[0;34m(self, *args, **kwds)\u001b[0m\n\u001b[1;32m    826\u001b[0m     \u001b[0mtracing_count\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mexperimental_get_tracing_count\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    827\u001b[0m     \u001b[0;32mwith\u001b[0m \u001b[0mtrace\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mTrace\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_name\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;32mas\u001b[0m \u001b[0mtm\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 828\u001b[0;31m       \u001b[0mresult\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_call\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m*\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mkwds\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    829\u001b[0m       \u001b[0mcompiler\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;34m\"xla\"\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_experimental_compile\u001b[0m \u001b[0;32melse\u001b[0m \u001b[0;34m\"nonXla\"\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    830\u001b[0m       \u001b[0mnew_tracing_count\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mexperimental_get_tracing_count\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m~/opt/anaconda3/envs/Machine_Learning/lib/python3.6/site-packages/tensorflow/python/eager/def_function.py\u001b[0m in \u001b[0;36m_call\u001b[0;34m(self, *args, **kwds)\u001b[0m\n\u001b[1;32m    893\u001b[0m       \u001b[0;31m# If we did not create any variables the trace we have is good enough.\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    894\u001b[0m       return self._concrete_stateful_fn._call_flat(\n\u001b[0;32m--> 895\u001b[0;31m           filtered_flat_args, self._concrete_stateful_fn.captured_inputs)  # pylint: disable=protected-access\n\u001b[0m\u001b[1;32m    896\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    897\u001b[0m     \u001b[0;32mdef\u001b[0m \u001b[0mfn_with_cond\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0minner_args\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0minner_kwds\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0minner_filtered_flat_args\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m~/opt/anaconda3/envs/Machine_Learning/lib/python3.6/site-packages/tensorflow/python/eager/function.py\u001b[0m in \u001b[0;36m_call_flat\u001b[0;34m(self, args, captured_inputs, cancellation_manager)\u001b[0m\n\u001b[1;32m   1917\u001b[0m       \u001b[0;31m# No tape is watching; skip to running the function.\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   1918\u001b[0m       return self._build_call_outputs(self._inference_function.call(\n\u001b[0;32m-> 1919\u001b[0;31m           ctx, args, cancellation_manager=cancellation_manager))\n\u001b[0m\u001b[1;32m   1920\u001b[0m     forward_backward = self._select_forward_and_backward_functions(\n\u001b[1;32m   1921\u001b[0m         \u001b[0margs\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m~/opt/anaconda3/envs/Machine_Learning/lib/python3.6/site-packages/tensorflow/python/eager/function.py\u001b[0m in \u001b[0;36mcall\u001b[0;34m(self, ctx, args, cancellation_manager)\u001b[0m\n\u001b[1;32m    558\u001b[0m               \u001b[0minputs\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    559\u001b[0m               \u001b[0mattrs\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mattrs\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 560\u001b[0;31m               ctx=ctx)\n\u001b[0m\u001b[1;32m    561\u001b[0m         \u001b[0;32melse\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    562\u001b[0m           outputs = execute.execute_with_cancellation(\n",
      "\u001b[0;32m~/opt/anaconda3/envs/Machine_Learning/lib/python3.6/site-packages/tensorflow/python/eager/execute.py\u001b[0m in \u001b[0;36mquick_execute\u001b[0;34m(op_name, num_outputs, inputs, attrs, ctx, name)\u001b[0m\n\u001b[1;32m     58\u001b[0m     \u001b[0mctx\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mensure_initialized\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m     59\u001b[0m     tensors = pywrap_tfe.TFE_Py_Execute(ctx._handle, device_name, op_name,\n\u001b[0;32m---> 60\u001b[0;31m                                         inputs, attrs, num_outputs)\n\u001b[0m\u001b[1;32m     61\u001b[0m   \u001b[0;32mexcept\u001b[0m \u001b[0mcore\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_NotOkStatusException\u001b[0m \u001b[0;32mas\u001b[0m \u001b[0me\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m     62\u001b[0m     \u001b[0;32mif\u001b[0m \u001b[0mname\u001b[0m \u001b[0;32mis\u001b[0m \u001b[0;32mnot\u001b[0m \u001b[0;32mNone\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;31mInvalidArgumentError\u001b[0m:  slice index 15 of dimension 0 out of bounds.\n\t [[{{node SEQ_2_SEQ_GMVAE/cluster_overlap_1/map/while/body/_10/SEQ_2_SEQ_GMVAE/cluster_overlap_1/map/while/PartitionedCall/PartitionedCall/strided_slice}}]] [Op:__inference_predict_function_37314]\n\nFunction call stack:\npredict_function\n"
     ]
    }
   ],
   "source": [
    "gmvaep.predict(data_prep[:10])"
   ]
  },
686
687
688
  {
   "cell_type": "code",
   "execution_count": 84,
689
690
691
692
693
694
695
696
697
698
699
700
701
702
   "metadata": {
    "scrolled": true
   },
   "outputs": [],
   "source": [
    "# Uncomment to see model summaries\n",
    "# encoder.summary()\n",
    "# decoder.summary()\n",
    "# grouper.summary()\n",
    "# gmvaep.summary()"
   ]
  },
  {
   "cell_type": "code",
703
   "execution_count": 190,
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
   "metadata": {},
   "outputs": [],
   "source": [
    "# Uncomment to plot model structure\n",
    "def plot_model(model, name):\n",
    "    tf.keras.utils.plot_model(\n",
    "        model,\n",
    "        to_file=os.path.join(\n",
    "            path,\n",
    "            \"deepof_{}_{}.png\".format(name, datetime.now().strftime(\"%Y%m%d-%H%M%S\")),\n",
    "        ),\n",
    "        show_shapes=True,\n",
    "        show_dtype=False,\n",
    "        show_layer_names=True,\n",
    "        rankdir=\"TB\",\n",
    "        expand_nested=True,\n",
    "        dpi=200,\n",
    "    )\n",
    "\n",
    "\n",
    "# plot_model(encoder, \"encoder\")\n",
    "# plot_model(decoder, \"decoder\")\n",
    "# plot_model(grouper, \"grouper\")\n",
    "# plot_model(gmvaep, \"gmvaep\")"
   ]
  },
lucas_miranda's avatar
lucas_miranda committed
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### 3. Visualize priors"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 314,
   "metadata": {},
   "outputs": [],
   "source": [
    "import tensorflow_probability as tfp\n",
    "\n",
    "tfb = tfp.bijectors\n",
    "tfd = tfp.distributions\n",
    "tfpl = tfp.layers"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 310,
   "metadata": {},
   "outputs": [],
   "source": [
    "def get_prior(number_of_components, encoding, init):\n",
    "\n",
    "    prior = tfd.MixtureSameFamily(\n",
    "        mixture_distribution=tfd.categorical.Categorical(\n",
    "            probs=tf.ones(number_of_components) / number_of_components\n",
    "        ),\n",
    "        components_distribution=tfd.MultivariateNormalDiag(\n",
    "            loc=tf.Variable(\n",
    "                init([number_of_components, encoding],),\n",
    "                name=\"prior_means\",\n",
    "            ),\n",
    "            scale_diag=tfp.util.TransformedVariable(\n",
    "                tf.ones([number_of_components, encoding]) / number_of_components,\n",
    "                tfb.Softplus(),\n",
    "                name=\"prior_scales\",\n",
    "            ),\n",
    "        ),\n",
    "    )\n",
    "    \n",
    "    return prior"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 422,
   "metadata": {},
   "outputs": [],
   "source": [
    "def sample_and_plot(prior, samples, ax, label):\n",
    "    \"\"\"Sample from the prior and plot with colours corresponding to different clusters\"\"\"\n",
    "    \n",
    "    samples = prior.sample(samples)\n",
    "    means = prior.components_distribution.mean()\n",
    "    samples = tf.concat([samples, means], axis=0)\n",
    "    pca = PCA(n_components=2)\n",
    "    prior = pca.fit_transform(samples)\n",
    "    \n",
    "    samples = prior[:-number_of_components, :]\n",
    "    means = prior[-number_of_components:, :]\n",
    "    \n",
    "    ax.scatter(prior[:,0], prior[:,1])\n",
    "    ax.scatter(means[:,0], means[:,1], label=label)\n",
    "    ax.set_xlabel(\"PC1\")\n",
    "    ax.set_ylabel(\"PC2\")\n",
    "    ax.legend()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 429,
   "metadata": {
    "scrolled": false
   },
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 720x1080 with 12 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "number_of_components = 15\n",
    "encoding = 6\n",
    "\n",
    "initializers = [\n",
    "    tf.keras.initializers.Constant(),\n",
    "    tf.keras.initializers.GlorotNormal(),\n",
    "    tf.keras.initializers.GlorotUniform(),\n",
    "    tf.keras.initializers.HeNormal(),\n",
    "    tf.keras.initializers.HeUniform(),\n",
    "    tf.keras.initializers.LecunNormal(),\n",
    "    tf.keras.initializers.LecunUniform(),\n",
    "    tf.keras.initializers.Orthogonal(),\n",
    "    tf.keras.initializers.RandomNormal(),\n",
    "    tf.keras.initializers.RandomUniform(),\n",
    "    tf.keras.initializers.TruncatedNormal(),\n",
    "    tf.keras.initializers.VarianceScaling(),\n",
    "]\n",
    "\n",
    "fig, ax = plt.subplots(4, 3, figsize=(10, 15), sharex=True, sharey=True)\n",
    "ax = [item for sublist in ax for item in sublist]\n",
    "\n",
    "for i, x in enumerate(ax):\n",
    "    prior = get_prior(number_of_components, encoding, initializers[i])\n",
    "    sample_and_plot(\n",
    "        prior,\n",
    "        1000,\n",
    "        x,\n",
    "        label=re.findall(\"initializers_v2.(.*?) \", str(initializers[i]))[0],\n",
    "    )\n",
    "\n",
    "fig.tight_layout(rect=[0.0, 0.0, 1.0, 0.97])\n",
    "plt.suptitle(\"effect of initialization on deepOF prior\")\n",
    "\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 466,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "4028e0d66e0a406cb475c02fc36cfa2e",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "HBox(children=(HTML(value=''), FloatProgress(value=0.0, max=12.0), HTML(value='')))"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n"
     ]
    }
   ],
   "source": [
    "from scipy.spatial.distance import pdist\n",
    "\n",
    "\n",
    "def quantify_separation(init, samples):\n",
    "\n",
    "    distances = []\n",
    "\n",
    "    for i in range(samples):\n",
    "        means = get_prior(\n",
    "            number_of_components, encoding, init\n",
    "        ).components_distribution.mean()\n",
    "        mean_dist = np.mean(pdist(means))\n",
    "        distances.append(mean_dist)\n",
    "\n",
    "    return (\n",
    "        np.mean(distances),\n",
    "        np.min(distances),\n",
    "        np.max(distances),\n",
    "        1.96 * np.std(distances),\n",
    "    )\n",
    "\n",
    "\n",
    "prior_init_eval_dict = {}\n",
    "for init in tqdm.tqdm(initializers):\n",
    "    prior_init_eval_dict[\n",
    "        re.findall(\"initializers_v2.(.*?) \", str(init))[0]\n",
    "    ] = quantify_separation(init, 10000)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 467,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>mean</th>\n",
       "      <th>min</th>\n",
       "      <th>max</th>\n",
       "      <th>CI95</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>HeUniform</th>\n",
       "      <td>1.226405</td>\n",
       "      <td>0.960102</td>\n",
       "      <td>1.459773</td>\n",
       "      <td>0.126309</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>HeNormal</th>\n",
       "      <td>1.219197</td>\n",
       "      <td>0.942844</td>\n",
       "      <td>1.499798</td>\n",
       "      <td>0.157326</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>GlorotUniform</th>\n",
       "      <td>1.035450</td>\n",
       "      <td>0.827028</td>\n",
       "      <td>1.245835</td>\n",
       "      <td>0.107209</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>GlorotNormal</th>\n",
       "      <td>1.030482</td>\n",
       "      <td>0.787457</td>\n",
       "      <td>1.286663</td>\n",
       "      <td>0.134244</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Orthogonal</th>\n",
       "      <td>0.872452</td>\n",
       "      <td>0.817305</td>\n",
       "      <td>0.906359</td>\n",
       "      <td>0.027980</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>LecunUniform</th>\n",
       "      <td>0.866810</td>\n",
       "      <td>0.672543</td>\n",
       "      <td>1.050145</td>\n",
       "      <td>0.089646</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>VarianceScaling</th>\n",
       "      <td>0.862960</td>\n",
       "      <td>0.646741</td>\n",
       "      <td>1.076390</td>\n",
       "      <td>0.112245</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>LecunNormal</th>\n",
       "      <td>0.862048</td>\n",
       "      <td>0.670952</td>\n",
       "      <td>1.081604</td>\n",
       "      <td>0.110810</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>RandomNormal</th>\n",
       "      <td>0.166069</td>\n",
       "      <td>0.121185</td>\n",
       "      <td>0.222380</td>\n",
       "      <td>0.025313</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>TruncatedNormal</th>\n",
       "      <td>0.146904</td>\n",
       "      <td>0.112296</td>\n",
       "      <td>0.186717</td>\n",
       "      <td>0.018968</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>RandomUniform</th>\n",
       "      <td>0.096923</td>\n",
       "      <td>0.077750</td>\n",
       "      <td>0.114661</td>\n",
       "      <td>0.010104</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Constant</th>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                     mean       min       max      CI95\n",
       "HeUniform        1.226405  0.960102  1.459773  0.126309\n",
       "HeNormal         1.219197  0.942844  1.499798  0.157326\n",
       "GlorotUniform    1.035450  0.827028  1.245835  0.107209\n",
       "GlorotNormal     1.030482  0.787457  1.286663  0.134244\n",
       "Orthogonal       0.872452  0.817305  0.906359  0.027980\n",
       "LecunUniform     0.866810  0.672543  1.050145  0.089646\n",
       "VarianceScaling  0.862960  0.646741  1.076390  0.112245\n",
       "LecunNormal      0.862048  0.670952  1.081604  0.110810\n",
       "RandomNormal     0.166069  0.121185  0.222380  0.025313\n",
       "TruncatedNormal  0.146904  0.112296  0.186717  0.018968\n",
       "RandomUniform    0.096923  0.077750  0.114661  0.010104\n",
       "Constant         0.000000  0.000000  0.000000  0.000000"
      ]
     },
     "execution_count": 467,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "prior_init_eval = pd.DataFrame(prior_init_eval_dict).T\n",
    "prior_init_eval.rename(columns={0:\"mean\", 1:\"min\", 2:\"max\", 3:\"CI95\"}, inplace=True)\n",
    "prior_init_eval.sort_values(\"mean\", ascending=False)"
   ]
  },
1065
1066
1067
1068
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
1069
    "### 4. Evaluate reconstruction (to be incorporated into deepof.evaluate)"
1070
1071
1072
1073
   ]
  },
  {
   "cell_type": "code",
1074
   "execution_count": 191,
1075
1076
1077
   "metadata": {},
   "outputs": [],
   "source": [
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
    "# Auxiliary animation functions\n",
    "\n",
    "\n",
    "def plot_mouse_graph(instant_x, instant_y, instant_rec_x, instant_rec_y, ax, edges):\n",
    "    \"\"\"Generates a graph plot of the mouse\"\"\"\n",
    "    plots = []\n",
    "    rec_plots = []\n",
    "    for edge in edges:\n",
    "        (temp_plot,) = ax.plot(\n",
    "            [float(instant_x[edge[0]]), float(instant_x[edge[1]])],\n",
    "            [float(instant_y[edge[0]]), float(instant_y[edge[1]])],\n",
    "            color=\"#006699\",\n",
1090
    "            linewidth=2.0,\n",
1091
1092
1093
1094
    "        )\n",
    "        (temp_rec_plot,) = ax.plot(\n",
    "            [float(instant_rec_x[edge[0]]), float(instant_rec_x[edge[1]])],\n",
    "            [float(instant_rec_y[edge[0]]), float(instant_rec_y[edge[1]])],\n",
1095
1096
    "            color=\"red\",\n",
    "            linewidth=2.0,\n",
1097
1098
1099
    "        )\n",
    "        plots.append(temp_plot)\n",
    "        rec_plots.append(temp_rec_plot)\n",
1100
    "    return plots, rec_plots\n",
1101
1102
    "\n",
    "\n",
1103
    "def update_mouse_graph(x, y, rec_x, rec_y, plots, rec_plots, edges):\n",
1104
1105
1106
1107
1108
1109
    "    \"\"\"Updates the graph plot to enable animation\"\"\"\n",
    "\n",
    "    for plot, edge in zip(plots, edges):\n",
    "        plot.set_data(\n",
    "            [float(x[edge[0]]), float(x[edge[1]])],\n",
    "            [float(y[edge[0]]), float(y[edge[1]])],\n",
1110
1111
1112
1113
1114
    "        )\n",
    "    for plot, edge in zip(rec_plots, edges):\n",
    "        plot.set_data(\n",
    "            [float(rec_x[edge[0]]), float(rec_x[edge[1]])],\n",
    "            [float(rec_y[edge[0]]), float(rec_y[edge[1]])],\n",
1115
1116
1117
1118
1119
    "        )"
   ]
  },
  {
   "cell_type": "code",
1120
   "execution_count": 192,
1121
1122
1123
   "metadata": {
    "scrolled": false
   },
1124
1125
1126
1127
1128
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
1129
      "Test 11_s11\n"
1130
1131
1132
1133
     ]
    },
    {
     "data": {
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
1778
1779
1780
1781
1782
1783
1784
1785
1786
1787
1788
1789
1790
1791
1792
1793
1794
1795
1796
1797
1798
1799
1800
1801
1802
1803
1804
1805
1806
1807
1808
1809
1810
1811
1812
1813
1814
1815
1816
1817
1818
1819
1820
1821
1822
1823
1824
1825
1826
1827
1828
1829
1830
1831
1832
1833
1834
1835
1836
1837
1838
1839
1840
1841
1842
1843
1844
1845
1846
1847
1848
1849
1850
1851
1852
1853
1854
1855
1856
1857
1858
1859
1860
1861
1862
1863
1864
1865
1866
1867
1868
1869
1870
1871
1872
1873
1874
1875
1876
1877
1878
1879
1880
1881
1882
1883
1884
1885
1886
1887
1888
1889
1890
1891
1892
1893
1894
1895
1896
1897
1898
1899
1900
1901
1902
1903
1904
1905
1906
1907
1908
1909
1910
1911
1912
1913
1914
1915
1916
1917
1918
1919
1920
1921
1922
1923
1924
1925
1926
1927
1928
1929
1930
1931
1932
1933
1934
1935
1936
1937
1938
1939
1940
1941
1942
1943
1944
1945
1946
1947
1948
1949
1950
1951
1952
1953
1954
1955
1956
1957
1958
1959
1960
1961
1962
1963
1964
1965
1966
1967
1968
1969
1970
1971
1972
1973
1974
1975
1976
1977
1978
1979
1980
1981
1982
1983
1984
1985
1986
1987
1988
1989
1990
1991
1992
1993
1994
1995
1996
1997
1998
1999
2000
2001
2002
2003
2004
2005
2006
2007
2008
2009
2010
2011
2012
2013
2014
2015
2016
2017
2018
2019
2020
2021
2022
2023
2024
2025
2026
2027
2028
2029
2030
2031
2032
2033
2034
2035
2036
2037
2038
2039
2040
2041
2042
2043
2044
2045
2046
2047
2048
2049
2050
2051
2052
2053
2054
2055
2056
2057
2058
2059
2060
2061
2062
2063
2064
2065
2066
2067
2068
2069
2070
2071
2072
2073
2074
2075
2076
2077
2078
2079
2080
2081
2082
2083
2084
2085
2086
2087
2088
2089
2090
2091
2092
2093
2094
2095
2096
2097
2098
2099
2100
2101
2102
2103
2104
2105
2106
2107
2108
2109
2110
2111
2112
2113
2114
2115
2116
2117
2118
2119
2120
2121
2122
2123
2124
2125
2126
2127
2128
2129
2130
2131
2132
2133
2134
2135
2136
2137
2138
2139
2140
2141
2142
2143
2144
2145
2146
2147
2148
2149
2150
2151
2152
2153
2154
2155
2156
2157
2158
2159
2160
2161
2162
2163
2164
2165
2166
2167
2168
2169
2170
2171
2172
2173
2174
2175
2176
2177
2178
2179
2180
2181
2182
2183
2184
2185
2186
2187
2188
2189
2190
2191
2192
2193
2194
2195
2196
2197
2198
2199
2200
2201
2202
2203
2204
2205
2206
2207
2208
2209
2210
2211
2212
2213
2214
2215
2216
2217
2218
2219
2220
2221
2222
2223
2224
2225
2226
2227
2228
2229
2230
2231
2232
2233
2234
2235
2236
2237
2238
2239
2240
2241
2242
2243
2244
2245
2246
2247
2248
2249
2250
2251
2252
2253
2254
2255
2256
2257
2258
2259
2260
2261
2262
2263
2264
2265
2266
2267
2268
2269
2270
2271
2272
2273
2274
2275
2276
2277
2278
2279
2280
2281
2282
2283
2284
2285
2286
2287
2288
2289
2290
2291
2292
2293
2294
2295
2296
2297
2298
2299
2300
2301
2302
2303
2304
2305
2306
2307
2308
2309
2310
2311
2312
2313
2314
2315
2316
2317
2318
2319
2320
2321
2322
2323
2324
2325
2326
2327
2328
2329
2330
2331
2332
2333
2334
2335
2336
2337
2338
2339
2340
2341
2342
2343
2344
2345
2346
2347
2348
2349
2350
2351
2352
2353
2354
2355
2356
2357
2358
2359
2360
2361
2362
2363
2364
2365
2366
2367
2368
2369
2370
2371
2372
2373
2374
2375
2376
2377
2378
2379
2380
2381
2382
2383
2384
2385
2386
2387
2388
2389
2390
2391
2392
2393
2394
2395
2396
2397
2398
2399
2400
2401
2402
2403
2404
2405
2406
2407
2408
2409
2410
2411
2412
2413
2414
2415
2416
2417
2418
2419
2420
2421
2422
2423
2424
2425
2426
2427
2428
2429
2430
2431
2432
2433
2434
2435
2436
2437
2438
2439
2440
2441
2442
2443
2444
2445
2446
2447
2448
2449
2450
2451
2452
2453
2454
2455
2456
2457
2458
2459
2460
2461
2462
2463
2464
2465
2466
2467
2468
2469
2470
2471
2472
2473
2474
2475
2476
2477
2478
2479
2480
2481
2482
2483
2484
2485
2486
2487
2488
2489
2490
2491
2492
2493
2494
2495
2496
2497
2498
2499
2500
2501
2502
2503
2504
2505
2506
2507
2508
2509
2510
2511
2512
2513
2514
2515
2516
2517
2518
2519
2520
2521
2522
2523
2524
2525
2526
2527
2528
2529
2530
2531
2532
2533
2534
2535
2536
2537
2538
2539
2540
2541
2542
2543
2544
2545
2546
2547
2548
2549
2550
2551
2552
2553
2554
2555
2556
2557
2558
2559
2560
2561
2562
2563
2564
2565
2566
2567
2568
2569
2570
2571
2572
2573
2574
2575
2576
2577
2578
2579
2580
2581
2582
2583
2584
2585
2586
2587
2588
2589
2590
2591
2592
2593
2594
2595
2596
2597
2598
2599
2600
2601
2602
2603
2604
2605
2606
2607
2608
2609
2610
2611
2612
2613
2614
2615
2616
2617
2618
2619
2620
2621
2622
2623
2624
2625
2626
2627
2628
2629
2630
2631
2632
2633
2634
2635
2636
2637
2638
2639
2640
2641
2642
2643
2644
2645
2646
2647
2648
2649
2650
2651
2652
2653
2654
2655
2656
2657
2658
2659
2660
2661
2662
2663
2664
2665
2666
2667
2668
2669
2670
2671
2672
2673
2674
2675
2676
2677
2678
2679
2680
2681
2682
2683
2684
2685
2686
2687
2688
2689
2690
2691
2692
2693
2694
2695
2696
2697
2698
2699
2700
2701
2702
2703
2704
2705
2706
2707
2708
2709
2710
2711
2712
2713
2714
2715
2716
2717
2718
2719
2720
2721
2722
2723
2724
2725
2726
2727
2728
2729
2730
2731
2732
2733
2734
2735
2736
2737
2738
2739
2740
2741
2742
2743
2744
2745
2746
2747
2748
2749
2750
2751
2752
2753
2754
2755
2756
2757
2758
2759
2760
2761
2762
2763
2764
2765
2766
2767
2768
2769
2770
2771
2772
2773
2774
2775
2776
2777
2778
2779
2780
2781
2782
2783
2784
2785
2786
2787
2788
2789
2790
2791
2792
2793
2794
2795
2796
2797
2798
2799
2800
2801
2802
2803
2804
2805
2806
2807
2808
2809
2810
2811
2812
2813
2814
2815
2816
2817
2818
2819
2820
2821
2822
2823
2824
2825
2826
2827
2828
2829
2830
2831
2832
2833
2834
2835
2836
2837
2838
2839
2840
2841
2842
2843
2844
2845
2846
2847
2848
2849
2850
2851
2852
2853
2854
2855
2856
2857
2858
2859
2860
2861
2862
2863
2864
2865
2866
2867
2868
2869
2870
2871
2872
2873
2874
2875
2876
2877
2878
2879
2880
2881
2882
2883
2884
2885
2886
2887
2888
2889
2890
2891
2892
2893
2894
2895
2896
2897
2898
2899
2900
2901
2902
2903
2904
2905
2906
2907
2908
2909
2910
2911
2912
2913
2914
2915
2916
2917
2918
2919
2920
2921
2922
2923
2924
2925
2926
2927
2928
2929
2930
2931
2932
2933
2934
2935
2936
2937
2938
2939
2940
2941
2942
2943
2944
2945
2946
2947
2948
2949
2950
2951
2952
2953
2954
2955
2956
2957
2958
2959
2960
2961
2962
2963
2964
2965
2966
2967
2968
2969
2970
2971
2972
2973
2974
2975
2976
2977
2978
2979
2980
2981
2982
2983
2984
2985
2986
2987
2988
2989
2990
2991
2992
2993
2994
2995
2996
2997
2998
2999
3000
3001
3002
3003
3004
3005
3006
3007
3008
3009
3010
3011
3012
3013
3014
3015
3016
3017
3018
3019
3020
3021
3022
3023
3024
3025
3026
3027
3028
3029
3030
3031
3032
3033
3034
3035
3036
3037
3038
3039
3040
3041
3042
3043
3044
3045
3046
3047
3048
3049
3050
3051
3052
3053
3054
3055
3056
3057
3058
3059
3060
3061
3062
3063
3064
3065
3066
3067
3068
3069
3070
3071
3072
3073
3074
3075
3076
3077
3078
3079
3080
3081
3082
3083
3084
3085
3086
3087
3088
3089
3090
3091
3092
3093
3094
3095
3096
3097
3098
3099
3100
3101
3102
3103
3104
3105
3106
3107
3108
3109
3110
3111
3112
3113
3114
3115
3116
3117
3118
3119
3120
3121
3122
3123
3124
3125
3126
3127
3128
3129
3130
3131
3132
3133
3134
3135
3136
3137
3138
3139
3140
3141
3142
3143
3144
3145
3146
3147
3148
3149
3150
3151
3152
3153
3154
3155
3156
3157
3158
3159
3160
3161
3162
3163
3164
3165
3166
3167
3168
3169
3170
3171
3172
3173
3174
3175
3176
3177
3178
3179
3180
3181
3182
3183
3184
3185
3186
3187
3188
3189
3190
3191
3192
3193
3194
3195
3196
3197
3198
3199
3200
3201
3202
3203
3204
3205
3206
3207
3208
3209
3210
3211
3212
3213
3214
3215
3216
3217
3218
3219
3220
3221
3222
3223
3224
3225
3226
3227
3228
3229
3230
3231
3232
3233
3234
3235
3236
32