train_utils.py 7.63 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
72
73
74
75
76
    """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"""

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
89
90
91
92
        log_dir=log_dir, histogram_freq=1, profile_batch=2,
    )

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

93
94
95
96
97
98
99
100
101
102
103
104
105
    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
106
107
108


def tune_search(
109
    data: List[np.array],
110
111
    hypertun_trials: int,
    hpt_type: str,
112
113
    hypermodel: str,
    k: int,
114
    kl_warmup_epochs: int,
115
    loss: str,
116
    mmd_warmup_epochs: int,
117
    overlap_loss: float,
118
    pheno_class: float,
119
120
    predictor: float,
    project_name: str,
121
    callbacks: List,
122
    n_epochs: int = 30,
123
    n_replicas: int = 1,
124
) -> Union[bool, Tuple[Any, Any]]:
125
126
127
128
129
    """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
130
131
            - hypertun_trials (int): number of Bayesian optimization iterations to run
            - hpt_type (str): specify one of Bayesian Optimization (bayopt) and Hyperband (hyperband)
132
133
            - hypermodel (str): hypermodel to load. Must be one of S2SAE (plain autoencoder)
            or S2SGMVAE (Gaussian Mixture Variational autoencoder).
134
135
136
137
            - 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
138
139
            - 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
140
141
142
143
            - 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
144
145
146
            - 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
147
148
149
150
151
152
153

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

    """

154
155
    X_train, y_train, X_val, y_val = data

156
157
158
159
    assert hpt_type in ["bayopt", "hyperband"], (
        "Invalid hyperparameter tuning framework. " "Select one of bayopt and hyperband"
    )

lucas_miranda's avatar
lucas_miranda committed
160
    if hypermodel == "S2SAE":  # pragma: no cover
161
162
163
        assert (
            predictor == 0.0 and pheno_class == 0.0
        ), "Prediction branches are only available for variational models. See documentation for more details"
164
        hypermodel = deepof.hypermodels.SEQ_2_SEQ_AE(input_shape=X_train.shape)
165
166
167

    elif hypermodel == "S2SGMVAE":
        hypermodel = deepof.hypermodels.SEQ_2_SEQ_GMVAE(
168
            input_shape=X_train.shape,
169
            kl_warmup_epochs=kl_warmup_epochs,
170
            loss=loss,
171
            mmd_warmup_epochs=mmd_warmup_epochs,
172
            number_of_components=k,
173
            overlap_loss=overlap_loss,
174
            phenotype_predictor=pheno_class,
175
            predictor=predictor,
176
        )
lucas_miranda's avatar
lucas_miranda committed
177

178
179
180
    else:
        return False

181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
    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,
            **hpt_params
        )
    else:
        tuner = BayesianOptimization(
            directory="BayOpt_{}_{}".format(loss, str(date.today())),
            max_trials=hypertun_trials,
            **hpt_params
        )
203
204
205

    print(tuner.search_space_summary())

206
207
208
209
210
211
212
213
214
215
216
    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]

217
    tuner.search(
218
219
        Xs,
        ys,
220
        epochs=n_epochs,
221
        validation_data=(Xvals, yvals),
222
223
        verbose=1,
        batch_size=256,
lucas_miranda's avatar
lucas_miranda committed
224
        callbacks=callbacks,
225
226
227
228
229
    )

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

lucas_miranda's avatar
lucas_miranda committed
230
231
    print(tuner.results_summary())

232
233
234
235
236
237
238
239
    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.