train_utils.py 6.16 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
100
101
102
103
104
105
106
107
108
    )

    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(
    train: np.array,
    test: np.array,
    bayopt_trials: int,
    hypermodel: str,
    k: int,
    loss: str,
    overlap_loss: float,
    predictor: float,
    project_name: str,
109
    callbacks: List,
110
    n_epochs: int = 40,
111
    n_replicas: int = 1,
112
) -> Union[bool, Tuple[Any, Any]]:
113
114
115
116
117
118
    """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
119
120
            - hypermodel (str): hypermodel to load. Must be one of S2SAE (plain autoencoder)
            or S2SGMVAE (Gaussian Mixture Variational autoencoder).
121
122
123
124
125
126
127
128
            - 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
            - 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
129
130
131
            - 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
132
133
134
135
136
137
138

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

    """

lucas_miranda's avatar
lucas_miranda committed
139
    if hypermodel == "S2SAE":  # pragma: no cover
140
141
142
143
144
        hypermodel = deepof.hypermodels.SEQ_2_SEQ_AE(input_shape=train.shape)

    elif hypermodel == "S2SGMVAE":
        hypermodel = deepof.hypermodels.SEQ_2_SEQ_GMVAE(
            input_shape=train.shape,
145
146
            loss=loss,
            number_of_components=k,
147
            overlap_loss=overlap_loss,
148
            predictor=predictor,
149
        )
lucas_miranda's avatar
lucas_miranda committed
150

151
152
153
154
155
    else:
        return False

    tuner = BayesianOptimization(
        hypermodel,
156
        directory="BayesianOptx",
157
        executions_per_trial=n_replicas,
158
159
        logger=TensorBoardLogger(metrics=["val_mae"], logdir="./logs/hparams"),
        max_trials=bayopt_trials,
160
161
        objective="val_mae",
        project_name=project_name,
162
        seed=42,
163
        tune_new_entries=True,
164
165
166
167
168
    )

    print(tuner.search_space_summary())

    tuner.search(
lucas_miranda's avatar
lucas_miranda committed
169
        train if predictor == 0 else [train[:-1]],
lucas_miranda's avatar
lucas_miranda committed
170
        train if predictor == 0 else [train[:-1], train[1:]],
171
        epochs=n_epochs,
lucas_miranda's avatar
lucas_miranda committed
172
173
174
        validation_data=(
            (test, test) if predictor == 0 else (test[:-1], [test[:-1], test[1:]])
        ),
175
176
        verbose=1,
        batch_size=256,
lucas_miranda's avatar
lucas_miranda committed
177
        callbacks=callbacks,
178
179
180
181
182
    )

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

lucas_miranda's avatar
lucas_miranda committed
183
184
    print(tuner.results_summary())

185
186
187
188
189
190
191
192
    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.