train_utils.py 7.33 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
def load_hparams(hparams):
27
28
29
30
31
32
33
34
35
36
37
38
    """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 = {
            "units_conv": 256,
            "units_lstm": 256,
            "units_dense2": 64,
            "dropout_rate": 0.25,
39
            "encoding": 16,
40
41
42
43
44
45
46
47
48
49
50
51
            "learning_rate": 1e-3,
        }
    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,
52
                [i for i in os.listdir(train_path) if i.endswith(".pkl")][0],
53
54
55
56
57
58
59
60
61
62
63
            ),
            "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
64
65
66
67
68
69
    X_train: np.array,
    batch_size: int,
    cp: bool,
    variational: bool,
    predictor: float,
    loss: str,
70
) -> List[Union[Any]]:
71
    """Generates callbacks for model training, including:
72
73
74
75
    - run_ID: run name, with coarse parameter details;
    - tensorboard_callback: for real-time visualization;
    - cp_callback: for checkpoint saving,
    - onecycle: for learning rate scheduling"""
76

77
    run_ID = "{}{}{}_{}".format(
78
79
80
81
82
83
84
        ("GMVAE" if variational else "AE"),
        ("P" if predictor > 0 and variational else ""),
        ("_loss={}".format(loss) if variational else ""),
        datetime.now().strftime("%Y%m%d-%H%M%S"),
    )

    log_dir = os.path.abspath("logs/fit/{}".format(run_ID))
85
    tensorboard_callback = tf.keras.callbacks.TensorBoard(
86
87
88
        log_dir=log_dir,
        histogram_freq=1,
        profile_batch=2,
89
90
91
    )

    onecycle = deepof.model_utils.one_cycle_scheduler(
92
93
        X_train.shape[0] // batch_size * 250,
        max_rate=0.005,
94
95
    )

96
97
98
99
100
101
102
103
104
105
106
107
108
    callbacks = [run_ID, tensorboard_callback, onecycle]

    if cp:
        cp_callback = tf.keras.callbacks.ModelCheckpoint(
            "./logs/checkpoints/" + run_ID + "/cp-{epoch:04d}.ckpt",
            verbose=1,
            save_best_only=False,
            save_weights_only=True,
            save_freq="epoch",
        )
        callbacks.append(cp_callback)

    return callbacks
109
110
111


def tune_search(
112
    data: List[np.array],
113
    encoding_size: int,
114
115
    hypertun_trials: int,
    hpt_type: str,
116
117
    hypermodel: str,
    k: int,
118
    kl_warmup_epochs: int,
119
    loss: str,
120
    mmd_warmup_epochs: int,
121
    overlap_loss: float,
122
    pheno_class: float,
123
124
    predictor: float,
    project_name: str,
125
    callbacks: List,
126
    n_epochs: int = 30,
127
    n_replicas: int = 1,
128
) -> Union[bool, Tuple[Any, Any]]:
129
130
    """Define the search space using keras-tuner and bayesian optimization

131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
    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
155
156
157

    """

158
159
    X_train, y_train, X_val, y_val = data

160
161
162
163
    assert hpt_type in ["bayopt", "hyperband"], (
        "Invalid hyperparameter tuning framework. " "Select one of bayopt and hyperband"
    )

lucas_miranda's avatar
lucas_miranda committed
164
    if hypermodel == "S2SAE":  # pragma: no cover
165
166
167
        assert (
            predictor == 0.0 and pheno_class == 0.0
        ), "Prediction branches are only available for variational models. See documentation for more details"
168
        hypermodel = deepof.hypermodels.SEQ_2_SEQ_AE(input_shape=X_train.shape)
169
170
171

    elif hypermodel == "S2SGMVAE":
        hypermodel = deepof.hypermodels.SEQ_2_SEQ_GMVAE(
172
            input_shape=X_train.shape,
173
            encoding=encoding_size,
174
            kl_warmup_epochs=kl_warmup_epochs,
175
            loss=loss,
176
            mmd_warmup_epochs=mmd_warmup_epochs,
177
            number_of_components=k,
178
            overlap_loss=overlap_loss,
179
            phenotype_predictor=pheno_class,
180
            predictor=predictor,
181
        )
lucas_miranda's avatar
lucas_miranda committed
182

183
184
185
    else:
        return False

186
187
188
189
190
191
192
193
194
195
196
197
198
199
    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,
200
            hyperband_iterations=3,
lucas_miranda's avatar
lucas_miranda committed
201
            factor=2,
202
203
204
205
206
207
208
209
            **hpt_params
        )
    else:
        tuner = BayesianOptimization(
            directory="BayOpt_{}_{}".format(loss, str(date.today())),
            max_trials=hypertun_trials,
            **hpt_params
        )
210
211
212

    print(tuner.search_space_summary())

213
214
215
216
217
218
219
220
221
222
223
    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]

224
    tuner.search(
225
226
        Xs,
        ys,
227
        epochs=n_epochs,
228
        validation_data=(Xvals, yvals),
229
230
        verbose=1,
        batch_size=256,
lucas_miranda's avatar
lucas_miranda committed
231
        callbacks=callbacks,
232
233
234
235
236
    )

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

lucas_miranda's avatar
lucas_miranda committed
237
238
    print(tuner.results_summary())

lucas_miranda's avatar
lucas_miranda committed
239
    return best_hparams, best_run