train_utils.py 6.88 KB
Newer Older
1
2
3
4
5
6
7
8
9
10
11
12
# @author lucasmiranda42
# encoding: utf-8
# module deepof

"""

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

"""
from datetime import datetime

from kerastuner import BayesianOptimization
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(
64
    X_train: np.array, batch_size: int, variational: bool, predictor: float, loss: str,
65
66
67
68
69
70
71
) -> Tuple:
    """Generates callbacks for model training, including:
        - run_ID: run name, with coarse parameter details;
        - tensorboard_callback: for real-time visualization;
        - cp_callback: for checkpoint saving,
        - onecycle: for learning rate scheduling"""

72
    run_ID = "{}{}{}_{}".format(
73
74
75
76
77
78
79
        ("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))
80
    tensorboard_callback = tf.keras.callbacks.TensorBoard(
81
82
83
        log_dir=log_dir, histogram_freq=1, profile_batch=2,
    )

84
85
86
87
88
89
    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",
90
91
92
93
94
95
96
97
98
99
    )

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

    return run_ID, tensorboard_callback, cp_callback, onecycle


def tune_search(
100
    data: List[np.array],
101
102
103
    bayopt_trials: int,
    hypermodel: str,
    k: int,
104
    kl_warmup_epochs: int,
105
    loss: str,
106
    mmd_warmup_epochs: int,
107
    overlap_loss: float,
108
    pheno_class: float,
109
110
    predictor: float,
    project_name: str,
111
    callbacks: List,
112
    n_epochs: int = 30,
113
    n_replicas: int = 1,
114
) -> Union[bool, Tuple[Any, Any]]:
115
116
117
118
119
120
    """Define the search space using keras-tuner and bayesian optimization

        Parameters:
            - train (np.array): dataset to train the model on
            - test (np.array): dataset to validate the model on
            - bayopt_trials (int): number of Bayesian optimization iterations to run
121
122
            - hypermodel (str): hypermodel to load. Must be one of S2SAE (plain autoencoder)
            or S2SGMVAE (Gaussian Mixture Variational autoencoder).
123
124
125
126
            - 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
127
128
            - 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
129
130
131
132
            - 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
133
134
135
            - 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
136
137
138
139
140
141
142

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

    """

143
144
    X_train, y_train, X_val, y_val = data

lucas_miranda's avatar
lucas_miranda committed
145
    if hypermodel == "S2SAE":  # pragma: no cover
146
147
148
        assert (
            predictor == 0.0 and pheno_class == 0.0
        ), "Prediction branches are only available for variational models. See documentation for more details"
149
        hypermodel = deepof.hypermodels.SEQ_2_SEQ_AE(input_shape=X_train.shape)
150
151
152

    elif hypermodel == "S2SGMVAE":
        hypermodel = deepof.hypermodels.SEQ_2_SEQ_GMVAE(
153
            input_shape=X_train.shape,
154
            kl_warmup_epochs=kl_warmup_epochs,
155
            loss=loss,
156
            mmd_warmup_epochs=mmd_warmup_epochs,
157
            number_of_components=k,
158
            overlap_loss=overlap_loss,
159
            phenotype_predictor=pheno_class,
160
            predictor=predictor,
161
        )
lucas_miranda's avatar
lucas_miranda committed
162

163
164
165
166
167
    else:
        return False

    tuner = BayesianOptimization(
        hypermodel,
168
        directory="BayesianOptx",
169
        executions_per_trial=n_replicas,
170
171
        logger=TensorBoardLogger(metrics=["val_mae"], logdir="./logs/hparams"),
        max_trials=bayopt_trials,
172
173
        objective="val_mae",
        project_name=project_name,
174
        seed=42,
175
        tune_new_entries=True,
176
177
178
179
    )

    print(tuner.search_space_summary())

180
181
182
183
184
185
186
187
188
189
190
    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]

191
    tuner.search(
192
193
        Xs,
        ys,
194
        epochs=n_epochs,
195
        validation_data=(Xvals, yvals),
196
197
        verbose=1,
        batch_size=256,
lucas_miranda's avatar
lucas_miranda committed
198
        callbacks=callbacks,
199
200
201
202
203
    )

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

lucas_miranda's avatar
lucas_miranda committed
204
205
    print(tuner.results_summary())

206
207
208
209
210
211
212
213
    return best_hparams, best_run


# TODO:
#    - load_treatments should be part of the main data module. If available in the main directory,
#    a table (preferrable in csv) should be loaded as metadata of the coordinates automatically.
#    This becomes particularly important por the supervised models that include phenotype classification
#    alongside the encoding.