hyperas z sieci z wieloma wejściami

Question

Obecnie problemy z używaniem hyperas optymalizator w mojej sieci z wieloma wejściami ..

To jest jak I zostały wdrożone go:

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 

używam data_generator, ponieważ wszystkie dane nie mogą być zawarte w pamięci RAM. Na podstawie wykonanych data example zrobiłem to.

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 unit 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} 

Specjalna dla tej sieci jest to, że wymaga wielu wejść. Mógłbym to zrobić tylko za pomocą jednego wejścia i użyć warstwy lambda do podziału, ale ponieważ dzielenie jest dość uciążliwe, zdecydowałem się przechowywać je podzielone, i podać je w splitowaniu, tworząc 33 wejścia. W przeciwnym razie sieć jest dość standardowa. (visulization sieci)

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)) 

To gdzie i rozpocząć optymalizację, a także wtedy, gdy otrzymuję mi komunikat o błędzie:

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 

nie jestem pewien, w jaki sposób należy interpretować ten błąd, to jest błąd implementacji lub błąd w bibliotece Nie wiem ...

Minimalny przykład roboczy:

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 unit 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)) 

Answer 1

Myślę, że Twój problem jest związany z funkcją data.

tutaj:

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

X_train odpowiada train_list, który jest generowany przez:

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

Więc train_list nie jest tablicą, to tylko lista pełna co datagen.fit zwrotów, które jest None.