Поиск по сетке Hyperas с сетью с несколькими входами

В настоящее время у меня проблемы с использованием оптимизатора Hyperas в моей сети с несколькими входами..

Вот как я это реализовал:

def data():
    X_train, Y_train = next(train_generator())
    X_test, Y_test = next(test_generator())

    datagen = ImageDataGenerator()
    train_list = []
    for input in X_train:
        train_list.append(datagen.fit(input))

    return datagen, train_list, Y_train, X_test, Y_test

Я использую data_generator, так как все данные не могут содержаться в оперативной памяти.

Основываясь на примере данных, которые они сделали, я сделал это:

def fws(datagen, X_train, Y_train, X_test, Y_test):
    # Input shape: (batch_size,40,45,3)
    # Output shape: (1,15,50)
    # Number of units in conv_feature_map = splitd
    filter_size = 8
    pooling_size = 28
    stride_step = 2
    pool_splits = ((splits - pooling_size)+1)/2
    temp_list = []
    sun_temp_list = []
    conv_featur_map = []
    pool_feature_map = []
    print "Printing shapes"

    list_of_input = [Input(shape = (window_height,total_frames_with_deltas,3)) for i in range(splits)]

    # Convolution
    shared_conv = Conv2D(filters = 150, kernel_size = (filter_size,45), activation='relu')
    for i in range(splits):
        conv_featur_map.append(shared_conv(list_of_input[i]))

    # Pooling
    input = Concatenate()(conv_featur_map)
    input = Reshape((splits,-1))(input)
    pooled = MaxPooling1D(pool_size = pooling_size, strides = stride_step)(input)

    # fc
    dense1 = Dense(units = 1000, activation = 'relu',    name = "dense_1")(pooled)
    dense2 = Dense(units = 1000, activation = 'relu',    name = "dense_2")(dense1)
    dense3 = Dense(units = 50 , activation = 'softmax', name = "dense_3")(dense2)

    model = Model(inputs = list_of_input , outputs = dense3)
    sgd = keras.optimizers.SGD(lr = {{uniform(0, 1)}}, decay = {{uniform(0, 1)}}, momentum = {{uniform(0, 1)}}, nesterov = True)
    model.compile(loss="categorical_crossentropy", optimizer=sgd , metrics = [metrics.categorical_accuracy])

    hist_current = model.fit_generator(datagen.flow(X_train, Y_train),
                        steps_per_epoch=32,
                        epochs = 1000,
                        verbose = 1,
                        validation_data = (X_test, Y_test),
                        validation_steps=32,
                        pickle_safe = True,
                        workers = 4)

    score, acc = model.evaluate(X_test, Y_test, verbose=0)

    return {'loss': -acc, 'status': STATUS_OK, 'model': model}

Особенностью этой сети является то, что она принимает несколько входов. Я мог бы сделать так, чтобы он брал только один вход и использовал лямбда-слой для его разделения, но так как разделение довольно утомительно, я решил сохранить его разделенным и подать его в разделенном виде, создав, таким образом, 33 входа. В остальном сеть довольно стандартная.

(Визуализация сети)

Enter image description here

if __name__ == '__main__':

    datagen, X_train, Y_train, X_test, Y_test = data()

    best_run, best_model = optim.minimize(model=fws,
                                          data=data,
                                          algo=tpe.suggest,
                                          max_evals=5,
                                          trials=Trials())

    print("Evalutation of best performing model:")
    print(best_model.evaluate(X_test, Y_test))

Это где я начинаю оптимизацию, а также где я получаю сообщение об ошибке:

Traceback (most recent call last):
  File "keras_cnn_phoneme_original_fit_generator_hyperas.py", line 211, in <module>
    trials=Trials())
  File "/usr/local/lib/python2.7/dist-packages/hyperas/optim.py", line 43, in minimize
    notebook_name=notebook_name, verbose=verbose)
  File "/usr/local/lib/python2.7/dist-packages/hyperas/optim.py", line 63, in base_minimizer
    model_str = get_hyperopt_model_string(model, data,functions,notebook_name, verbose, stack)
  File "/usr/local/lib/python2.7/dist-packages/hyperas/optim.py", line 130, in get_hyperopt_model_string
    imports = extract_imports(cleaned_source, verbose)
  File "/usr/local/lib/python2.7/dist-packages/hyperas/utils.py", line 44, in extract_imports
    import_parser.visit(tree)
  File "/usr/lib/python2.7/ast.py", line 241, in visit
    return visitor(node)
  File "/usr/lib/python2.7/ast.py", line 249, in generic_visit
    self.visit(item)
  File "/usr/lib/python2.7/ast.py", line 241, in visit
    return visitor(node)
  File "/usr/local/lib/python2.7/dist-packages/hyperas/utils.py", line 14, in visit_Import
    if (self._import_asnames(node.names)!=''):
  File "/usr/local/lib/python2.7/dist-packages/hyperas/utils.py", line 36, in _import_asnames
    return ''.join(asname)
TypeError: sequence item 0: expected string, NoneType found

Я не уверен, как следует интерпретировать эту ошибку. Это ошибка реализации или ошибка в библиотеке? Я не знаю...

Минимальный рабочий пример:

import numpy as np
import re
from keras.utils import np_utils
from keras import metrics
import keras
from keras.models import Sequential
from keras.optimizers import SGD
import scipy
from keras.layers.core import Dense, Activation, Lambda, Reshape,Flatten
from keras.layers import Conv1D,Conv2D,MaxPooling2D, MaxPooling1D, Reshape
#from keras.utils.visualize_util import plot
from keras.utils import np_utils
from keras.models import Model
from keras.layers import Input, Dense
from keras.layers import Dropout
from keras import backend as K
from keras.layers.merge import Concatenate
from keras.models import load_model
from keras.utils import plot_model
from keras.preprocessing.image import ImageDataGenerator
import math
import random
from keras.callbacks import ModelCheckpoint
import tensorflow as tf
from hyperopt import Trials, STATUS_OK, tpe
from hyperas import optim
from hyperas.distributions import uniform

def train_generator():
    while True:
        train_input = np.random.randint(100,size=(1,33,8,45,3))
        train_input_list = np.split(train_input,33,axis=1)

        for i in range(len(train_input_list)):
            train_input_list[i] = train_input_list[i].reshape(1,8,45,3)

        train_output = np.random.randint(100,size=(1,3,50))
        yield (train_input_list, train_output)

def test_generator():
    while True:
        test_input = np.random.randint(100,size=(1,33,8,45,3))
        test_input_list = np.split(test_input,33,axis=1)

        for i in range(len(test_input_list)):
            test_input_list[i] = test_input_list[i].reshape(1,8,45,3)

        test_output = np.random.randint(100,size=(1,3,50))

        yield (test_input_list, test_output)

def data():
    X_train, Y_train = next(train_generator())
    X_test, Y_test = next(test_generator())

    datagen = ImageDataGenerator()
    train_list = []
    for input in X_train:
        train_list.append(datagen.fit(input))

    return datagen, train_list, Y_train, X_test, Y_test

def fws(datagen, X_train, Y_train, X_test, Y_test):
    # Input shape: (batch_size,40,45,3)
    # Output shape: (1,15,50)
    # Number of units in conv_feature_map = splitd
    filter_size = 8
    pooling_size = 28
    stride_step = 2
    pool_splits = ((splits - pooling_size)+1)/2
    temp_list = []
    sun_temp_list = []
    conv_featur_map = []
    pool_feature_map = []
    print "Printing shapes"

    list_of_input = [Input(shape = (8,45,3)) for i in range(33)]

    # Convolution
    shared_conv = Conv2D(filters = 150, kernel_size = (filter_size,45), activation='relu')
    for i in range(splits):
        conv_featur_map.append(shared_conv(list_of_input[i]))

    # Pooling
    input = Concatenate()(conv_featur_map)
    input = Reshape((splits,-1))(input)
    pooled = MaxPooling1D(pool_size = pooling_size, strides = stride_step)(input)

    #reshape = Reshape((3,-1))(pooled)

    #fc
    dense1 = Dense(units = 1000, activation = 'relu',    name = "dense_1")(pooled)
    dense2 = Dense(units = 1000, activation = 'relu',    name = "dense_2")(dense1)
    dense3 = Dense(units = 50 , activation = 'softmax', name = "dense_3")(dense2)


    model = Model(inputs = list_of_input , outputs = dense3)
    sgd = keras.optimizers.SGD(lr = {{uniform(0, 1)}}, decay = {{uniform(0, 1)}}, momentum = {{uniform(0, 1)}}, nesterov = True)
    model.compile(loss="categorical_crossentropy", optimizer=sgd , metrics = [metrics.categorical_accuracy])

    hist_current = model.fit_generator(datagen.flow(X_train, Y_train),
                        steps_per_epoch=32,
                        epochs = 1000,
                        verbose = 1,
                        validation_data = (X_test, Y_test),
                        validation_steps=32,
                        pickle_safe = True,
                        workers = 4)

    score, acc = model.evaluate(X_test, Y_test, verbose=0)

    return {'loss': -acc, 'status': STATUS_OK, 'model': model}

if __name__ == '__main__':

    datagen, X_train, Y_train, X_test, Y_test = data()

    best_run, best_model = optim.minimize(model=fws,
                                          data=data,
                                          algo=tpe.suggest,
                                          max_evals=5,
                                          trials=Trials())

    print("Evalutation of best performing model:")
    print(best_model.evaluate(X_test, Y_test))

Ответ 1

Я думаю, что ваша проблема связана с функцией data.

Вот:

datagen, X_train, Y_train, X_test, Y_test = data()

X_train соответствует train_list, который генерируется:

datagen = ImageDataGenerator()
train_list = []
for input in X_train:
    train_list.append(datagen.fit(input))

Так что train_list - это не массив. Это просто список того, что возвращает datagen.fit, а это None.