问在Keras中为fit_generate创建自定义data_generator ()

EN

train_batches = ImageDataGenerator().flow_from_directory(train_path, target_size=(224, 224),
                                                         classes=['Bark', 'Bitting', 'Engage', 'Hidden', 'Jump',
                                                                  'Stand', 'Walk'], batch_size=18156, shuffle=False)
valid_batches = ImageDataGenerator().flow_from_directory(valid_path, target_size=(224, 224),
                                                         classes=['Bark', 'Bitting', 'Engage', 'Hidden', 'Jump',
                                                                  'Stand', 'Walk'], batch_size=6, shuffle=False)
test_batches = ImageDataGenerator().flow_from_directory(test_path, target_size=(224, 224),
                                                        classes=['Bark', 'Bitting', 'Engage', 'Hidden', 'Jump',
                                                                 'Stand','Walk'], batch_size=6, shuffle=False)

def train_gen():

    n_frames=6    
    n_samples=6 #to decide
    H=W=224
    C = 3

    imgs, labels = next(train_batches)

    y = np.empty((n_samples, 7))
    j = 0
    for i in range(n_samples):       
        y[i] = labels[j]        
        j +=6
    frame_sequence = imgs.reshape(n_samples,n_frames, H,W,C)

    return frame_sequence,y



def valid_gen():

    v_frames=6
    v_samples=1
    H=W=224
    C = 3

    vimgs,vlabels = next(valid_batches)
    y2 = np.empty((v_samples, 7))

    k = 0
    for l in range(v_samples):       
        y2[l] = vlabels[k]        
        k +=6
    valid_sequence = vimgs.reshape(v_samples,v_frames, H,W,C)

    return valid_sequence,y2

def main():

    cnn = VGG16(weights='imagenet',
                include_top='False', pooling='avg')

    cnn.layers.pop()
    print(cnn.summary())
    cnn.trainable = False

    video_input= Input(shape=(None,224,224,3), name='video_input')   
    print(video_input.shape)

    encoded_frame_sequence = TimeDistributed(cnn)(video_input) # the output will be a sequence of vectors
    encoded_video = LSTM(256)(encoded_frame_sequence)  # the output will be a vector
    output = Dense(7, activation='relu')(encoded_video)
    video_model = Model(inputs=[video_input], outputs=output)

    tr_data = train_gen()
    vd_data= valid_gen()
    print(video_model.summary())

    imgs, labels = next(train_batches)    
    vimgs,vlabels = next(valid_batches)

    print("Training ...")
    video_model.compile(Adam(lr=.001), loss='categorical_crossentropy', metrics=['accuracy'])
    video_model.fit_generator(tr_data, 
                              steps_per_epoch=1513, 
                             validation_data=vd_data, 
                              validation_steps=431, 
                              epochs=1, 
                              verbose=2)