train_utils.py 10 KB
Newer Older
1
2
3
4
5
6
7
8
9
# @author lucasmiranda42
# encoding: utf-8
# module deepof

"""

Simple utility functions used in deepof example scripts. These are not part of the main package

"""
10
from datetime import date, datetime
11

12
from kerastuner import BayesianOptimization, Hyperband
13
from kerastuner import HyperParameters
14
from kerastuner_tensorboard_logger import TensorBoardLogger
15
from tensorboard.plugins.hparams import api as hp
16
from typing import Tuple, Union, Any, List
17
18
19
20
21
22
23
import deepof.hypermodels
import deepof.model_utils
import numpy as np
import os
import pickle
import tensorflow as tf

24
25
hp = HyperParameters()

26

27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
class CustomStopper(tf.keras.callbacks.EarlyStopping):
    """ Custom callback for """

    def __init__(self, start_epoch, *args, **kwargs):
        super(CustomStopper, self).__init__(*args, **kwargs)
        self.start_epoch = start_epoch

    def get_config(self):  # pragma: no cover
        """Updates callback metadata"""

        config = super().get_config().copy()
        config.update({"start_epoch": self.start_epoch})
        return config

    def on_epoch_end(self, epoch, logs=None):
        if epoch > self.start_epoch:
            super().on_epoch_end(epoch, logs)


46
def load_hparams(hparams):
47
48
49
50
51
52
53
54
    """Loads hyperparameters from a custom dictionary pickled on disc.
    Thought to be used with the output of hyperparameter_tuning.py"""

    if hparams is not None:
        with open(hparams, "rb") as handle:
            hparams = pickle.load(handle)
    else:
        hparams = {
55
56
57
58
59
            "bidirectional_merge": "ave",
            "clipvalue": 1.0,
            "dense_activation": "relu",
            "dense_layers_per_branch": 1,
            "dropout_rate": 1e-3,
60
            "learning_rate": 1e-3,
61
62
63
            "units_conv": 160,
            "units_dense2": 120,
            "units_lstm": 300,
64
65
66
67
68
69
70
71
72
73
74
        }
    return hparams


def load_treatments(train_path):
    """Loads a dictionary containing the treatments per individual,
    to be loaded as metadata in the coordinates class"""
    try:
        with open(
            os.path.join(
                train_path,
75
                [i for i in os.listdir(train_path) if i.endswith(".pkl")][0],
76
77
78
79
80
81
82
83
84
85
86
            ),
            "rb",
        ) as handle:
            treatment_dict = pickle.load(handle)
    except IndexError:
        treatment_dict = None

    return treatment_dict


def get_callbacks(
lucas_miranda's avatar
lucas_miranda committed
87
88
89
90
    X_train: np.array,
    batch_size: int,
    cp: bool,
    variational: bool,
91
    phenotype_class: float,
lucas_miranda's avatar
lucas_miranda committed
92
93
    predictor: float,
    loss: str,
94
    logparam: dict = None,
95
    outpath: str = ".",
96
) -> List[Union[Any]]:
97
    """Generates callbacks for model training, including:
98
99
100
101
    - run_ID: run name, with coarse parameter details;
    - tensorboard_callback: for real-time visualization;
    - cp_callback: for checkpoint saving,
    - onecycle: for learning rate scheduling"""
102

103
    run_ID = "{}{}{}{}{}{}_{}".format(
104
105
        ("GMVAE" if variational else "AE"),
        ("P" if predictor > 0 and variational else ""),
106
        ("_Pheno" if phenotype_class > 0 else ""),
107
        ("_loss={}".format(loss) if variational else ""),
108
109
        ("_encoding={}".format(logparam["encoding"]) if logparam is not None else ""),
        ("_k={}".format(logparam["k"]) if logparam is not None else ""),
110
        (datetime.now().strftime("%Y%m%d-%H%M%S")),
111
112
    )

113
    log_dir = os.path.abspath(os.path.join(outpath, "fit", run_ID))
114
    tensorboard_callback = tf.keras.callbacks.TensorBoard(
115
116
117
        log_dir=log_dir,
        histogram_freq=1,
        profile_batch=2,
118
119
120
    )

    onecycle = deepof.model_utils.one_cycle_scheduler(
121
122
        X_train.shape[0] // batch_size * 250,
        max_rate=0.005,
123
124
    )

125
126
127
128
    callbacks = [run_ID, tensorboard_callback, onecycle]

    if cp:
        cp_callback = tf.keras.callbacks.ModelCheckpoint(
129
            os.path.join(outpath, "checkpoints", run_ID + "/cp-{epoch:04d}.ckpt"),
130
131
132
133
134
135
136
137
            verbose=1,
            save_best_only=False,
            save_weights_only=True,
            save_freq="epoch",
        )
        callbacks.append(cp_callback)

    return callbacks
138
139


140
141
142
143
144
145
# noinspection PyUnboundLocalVariable
def tensorboard_metric_logging(
    run_dir: str,
    hpms: Any,
    X: np.ndarray,
    y: np.ndarray,
lucas_miranda's avatar
lucas_miranda committed
146
    model: tf.python.keras.engine.functional.Functional,
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
    predictor: float,
    pheno_class: float,
    rec: str,
):
    output = model.predict(X)
    if pheno_class or predictor:
        reconstruction = output[0]
        prediction = output[1]
        pheno = output[-1]
    else:
        reconstruction = output

    with tf.summary.create_file_writer(run_dir).as_default():
        hp.hparams(hpms)  # record the values used in this trial
        val_mae = tf.reduce_mean(
            tf.keras.metrics.mean_absolute_error(X, reconstruction)
        )
        val_mse = tf.reduce_mean(tf.keras.metrics.mean_squared_error(X, reconstruction))
        tf.summary.scalar("val_{}mae".format(rec), val_mae, step=1)
        tf.summary.scalar("val_{}mse".format(rec), val_mse, step=1)

        if predictor:
            pred_mae = tf.reduce_mean(
                tf.keras.metrics.mean_absolute_error(X, prediction)
            )
            pred_mse = tf.reduce_mean(
                tf.keras.metrics.mean_squared_error(X, prediction)
            )
            tf.summary.scalar("val_prediction_mae".format(rec), pred_mae, step=1)
            tf.summary.scalar("val_prediction_mse".format(rec), pred_mse, step=1)

        if pheno_class:
            pheno_acc = tf.keras.metrics.Accuracy(y, pheno)
            pheno_auc = tf.keras.metrics.AUC(y, pheno)

            tf.summary.scalar("phenotype_prediction_accuracy", pheno_acc, step=1)
            tf.summary.scalar("phenotype_prediction_auc", pheno_auc, step=1)


186
def tune_search(
187
    data: List[np.array],
188
    encoding_size: int,
189
190
    hypertun_trials: int,
    hpt_type: str,
191
192
    hypermodel: str,
    k: int,
193
    kl_warmup_epochs: int,
194
    loss: str,
195
    mmd_warmup_epochs: int,
196
    overlap_loss: float,
197
    pheno_class: float,
198
199
    predictor: float,
    project_name: str,
200
    callbacks: List,
201
    n_epochs: int = 30,
202
    n_replicas: int = 1,
203
) -> Union[bool, Tuple[Any, Any]]:
204
205
    """Define the search space using keras-tuner and bayesian optimization

206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
    Parameters:
        - train (np.array): dataset to train the model on
        - test (np.array): dataset to validate the model on
        - hypertun_trials (int): number of Bayesian optimization iterations to run
        - hpt_type (str): specify one of Bayesian Optimization (bayopt) and Hyperband (hyperband)
        - hypermodel (str): hypermodel to load. Must be one of S2SAE (plain autoencoder)
        or S2SGMVAE (Gaussian Mixture Variational autoencoder).
        - k (int) number of components of the Gaussian Mixture
        - loss (str): one of [ELBO, MMD, ELBO+MMD]
        - overlap_loss (float): assigns as weight to an extra loss term which
        penalizes overlap between GM components
        - pheno_class (float): adds an extra regularizing neural network to the model,
        which tries to predict the phenotype of the animal from which the sequence comes
        - predictor (float): adds an extra regularizing neural network to the model,
        which tries to predict the next frame from the current one
        - project_name (str): ID of the current run
        - callbacks (list): list of callbacks for the training loop
        - n_epochs (int): optional. Number of epochs to train each run for
        - n_replicas (int): optional. Number of replicas per parameter set. Higher values
         will yield more robust results, but will affect performance severely

    Returns:
        - best_hparams (dict): dictionary with the best retrieved hyperparameters
        - best_run (tf.keras.Model): trained instance of the best model found
230
231
232

    """

233
234
    X_train, y_train, X_val, y_val = data

235
236
237
238
    assert hpt_type in ["bayopt", "hyperband"], (
        "Invalid hyperparameter tuning framework. " "Select one of bayopt and hyperband"
    )

lucas_miranda's avatar
lucas_miranda committed
239
    if hypermodel == "S2SAE":  # pragma: no cover
240
241
242
        assert (
            predictor == 0.0 and pheno_class == 0.0
        ), "Prediction branches are only available for variational models. See documentation for more details"
243
        hypermodel = deepof.hypermodels.SEQ_2_SEQ_AE(input_shape=X_train.shape)
244
245
246

    elif hypermodel == "S2SGMVAE":
        hypermodel = deepof.hypermodels.SEQ_2_SEQ_GMVAE(
247
            input_shape=X_train.shape,
248
            encoding=encoding_size,
249
            kl_warmup_epochs=kl_warmup_epochs,
250
            loss=loss,
251
            mmd_warmup_epochs=mmd_warmup_epochs,
252
            number_of_components=k,
253
            overlap_loss=overlap_loss,
254
            phenotype_predictor=pheno_class,
255
            predictor=predictor,
256
        )
lucas_miranda's avatar
lucas_miranda committed
257

258
259
260
    else:
        return False

261
262
263
264
265
266
267
268
269
270
271
272
273
274
    hpt_params = {
        "hypermodel": hypermodel,
        "executions_per_trial": n_replicas,
        "logger": TensorBoardLogger(metrics=["val_mae"], logdir="./logs/hparams"),
        "objective": "val_mae",
        "project_name": project_name,
        "seed": 42,
        "tune_new_entries": True,
    }

    if hpt_type == "hyperband":
        tuner = Hyperband(
            directory="HyperBandx_{}_{}".format(loss, str(date.today())),
            max_epochs=hypertun_trials,
275
            hyperband_iterations=3,
lucas_miranda's avatar
lucas_miranda committed
276
            factor=2,
277
278
279
280
281
282
283
284
            **hpt_params
        )
    else:
        tuner = BayesianOptimization(
            directory="BayOpt_{}_{}".format(loss, str(date.today())),
            max_trials=hypertun_trials,
            **hpt_params
        )
285
286
287

    print(tuner.search_space_summary())

288
289
290
291
292
293
294
295
296
297
298
    Xs, ys = [X_train], [X_train]
    Xvals, yvals = [X_val], [X_val]

    if predictor > 0.0:
        Xs, ys = X_train[:-1], [X_train[:-1], X_train[1:]]
        Xvals, yvals = X_val[:-1], [X_val[:-1], X_val[1:]]

    if pheno_class > 0.0:
        ys += [y_train]
        yvals += [y_val]

299
    tuner.search(
300
301
        Xs,
        ys,
302
        epochs=n_epochs,
303
        validation_data=(Xvals, yvals),
304
305
        verbose=1,
        batch_size=256,
lucas_miranda's avatar
lucas_miranda committed
306
        callbacks=callbacks,
307
308
309
310
311
    )

    best_hparams = tuner.get_best_hyperparameters(num_trials=1)[0]
    best_run = tuner.hypermodel.build(best_hparams)

lucas_miranda's avatar
lucas_miranda committed
312
313
    print(tuner.results_summary())

314
    return best_hparams, best_run