hyperas Rastersuche mit Netzwerk mit mehreren Eingängen

Question

ich derzeit Probleme bei der Verwendung hyperas optimiser in meinem Netzwerk mit mehreren Eingängen ..

Dies ist, wie ich es implementiert habe:

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 

ich bin mit data_generator, da nicht alle Daten im RAM enthalten sein können. Basierend auf der data example haben sie gemacht, ich habe dies gemacht.

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} 

Speziell für dieses Netzwerk ist, dass es mehrere Eingänge einnimmt. Ich hätte es nur in einer Eingabe machen und eine Lambda-Ebene verwenden können, um sie zu teilen, aber da das Teilen ziemlich langweilig ist, entschied ich mich dafür, es gespaltet zu speichern und es gespalten zu geben, um 33 Eingaben zu erzeugen. Ansonsten ist das Netzwerk ziemlich Standard. (Visualisierung schneller von Netzwerk)

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)) 

Dies, wo ich die Optimierung beginnen, und wo auch ich erhalte mir Fehlermeldung:

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 

Ich bin nicht sicher, wie dieser Fehler interpretieren soll, dann ist dies ein Implementierungsfehler oder ein Fehler in der Bibliothek, die ich nicht kenne ...

Ein minimales Arbeitsbeispiel:

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

Ich denke, dass Ihr Problem mit der data Funktion zusammenhängt.

hier:

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

X_train entspricht train_list, die erzeugt wird durch: So

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

train_list kein Array, es ist nur eine Liste voller datagen.fit zurückkehrt, was, das ist None.