train_utils.py 8.34 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 typing import Tuple, Union, Any, List
16
17
18
19
20
21
22
import deepof.hypermodels
import deepof.model_utils
import numpy as np
import os
import pickle
import tensorflow as tf

23
24
hp = HyperParameters()

25

26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
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)


45
def load_hparams(hparams):
46
47
48
49
50
51
52
53
    """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 = {
54
55
56
57
58
            "bidirectional_merge": "ave",
            "clipvalue": 1.0,
            "dense_activation": "relu",
            "dense_layers_per_branch": 1,
            "dropout_rate": 1e-3,
59
            "learning_rate": 1e-3,
60
61
62
            "units_conv": 160,
            "units_dense2": 120,
            "units_lstm": 300,
63
64
65
66
67
68
69
70
71
72
73
        }
    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,
74
                [i for i in os.listdir(train_path) if i.endswith(".pkl")][0],
75
76
77
78
79
80
81
82
83
84
85
            ),
            "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
86
87
88
89
    X_train: np.array,
    batch_size: int,
    cp: bool,
    variational: bool,
90
    phenotype_class: float,
lucas_miranda's avatar
lucas_miranda committed
91
92
    predictor: float,
    loss: str,
93
    logparam: dict = None,
94
    outpath: str = ".",
95
) -> List[Union[Any]]:
96
    """Generates callbacks for model training, including:
97
98
99
100
    - run_ID: run name, with coarse parameter details;
    - tensorboard_callback: for real-time visualization;
    - cp_callback: for checkpoint saving,
    - onecycle: for learning rate scheduling"""
101

102
    run_ID = "{}{}{}{}{}_{}".format(
103
104
        ("GMVAE" if variational else "AE"),
        ("P" if predictor > 0 and variational else ""),
105
        ("_Pheno" if phenotype_class > 0 else ""),
106
        ("_loss={}".format(loss) if variational else ""),
107
108
109
110
111
        (
            "_{}={}".format(list(logparam.keys())[0], list(logparam.values())[0])
            if logparam is not None
            else ""
        ),
112
113
114
        datetime.now().strftime("%Y%m%d-%H%M%S"),
    )

115
    log_dir = os.path.abspath(os.path.join(outpath, "fit", run_ID))
116
    tensorboard_callback = tf.keras.callbacks.TensorBoard(
117
118
119
        log_dir=log_dir,
        histogram_freq=1,
        profile_batch=2,
120
121
122
    )

    onecycle = deepof.model_utils.one_cycle_scheduler(
123
124
        X_train.shape[0] // batch_size * 250,
        max_rate=0.005,
125
126
    )

127
128
129
130
    callbacks = [run_ID, tensorboard_callback, onecycle]

    if cp:
        cp_callback = tf.keras.callbacks.ModelCheckpoint(
131
            os.path.join(outpath, "checkpoints", run_ID + "/cp-{epoch:04d}.ckpt"),
132
133
134
135
136
137
138
139
            verbose=1,
            save_best_only=False,
            save_weights_only=True,
            save_freq="epoch",
        )
        callbacks.append(cp_callback)

    return callbacks
140
141
142


def tune_search(
143
    data: List[np.array],
144
    encoding_size: int,
145
146
    hypertun_trials: int,
    hpt_type: str,
147
148
    hypermodel: str,
    k: int,
149
    kl_warmup_epochs: int,
150
    loss: str,
151
    mmd_warmup_epochs: int,
152
    overlap_loss: float,
153
    pheno_class: float,
154
155
    predictor: float,
    project_name: str,
156
    callbacks: List,
157
    n_epochs: int = 30,
158
    n_replicas: int = 1,
159
) -> Union[bool, Tuple[Any, Any]]:
160
161
    """Define the search space using keras-tuner and bayesian optimization

162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
    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
186
187
188

    """

189
190
    X_train, y_train, X_val, y_val = data

191
192
193
194
    assert hpt_type in ["bayopt", "hyperband"], (
        "Invalid hyperparameter tuning framework. " "Select one of bayopt and hyperband"
    )

lucas_miranda's avatar
lucas_miranda committed
195
    if hypermodel == "S2SAE":  # pragma: no cover
196
197
198
        assert (
            predictor == 0.0 and pheno_class == 0.0
        ), "Prediction branches are only available for variational models. See documentation for more details"
199
        hypermodel = deepof.hypermodels.SEQ_2_SEQ_AE(input_shape=X_train.shape)
200
201
202

    elif hypermodel == "S2SGMVAE":
        hypermodel = deepof.hypermodels.SEQ_2_SEQ_GMVAE(
203
            input_shape=X_train.shape,
204
            encoding=encoding_size,
205
            kl_warmup_epochs=kl_warmup_epochs,
206
            loss=loss,
207
            mmd_warmup_epochs=mmd_warmup_epochs,
208
            number_of_components=k,
209
            overlap_loss=overlap_loss,
210
            phenotype_predictor=pheno_class,
211
            predictor=predictor,
212
        )
lucas_miranda's avatar
lucas_miranda committed
213

214
215
216
    else:
        return False

217
218
219
220
221
222
223
224
225
226
227
228
229
230
    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,
231
            hyperband_iterations=3,
lucas_miranda's avatar
lucas_miranda committed
232
            factor=2,
233
234
235
236
237
238
239
240
            **hpt_params
        )
    else:
        tuner = BayesianOptimization(
            directory="BayOpt_{}_{}".format(loss, str(date.today())),
            max_trials=hypertun_trials,
            **hpt_params
        )
241
242
243

    print(tuner.search_space_summary())

244
245
246
247
248
249
250
251
252
253
254
    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]

255
    tuner.search(
256
257
        Xs,
        ys,
258
        epochs=n_epochs,
259
        validation_data=(Xvals, yvals),
260
261
        verbose=1,
        batch_size=256,
lucas_miranda's avatar
lucas_miranda committed
262
        callbacks=callbacks,
263
264
265
266
267
    )

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

lucas_miranda's avatar
lucas_miranda committed
268
269
    print(tuner.results_summary())

270
    return best_hparams, best_run