Keras非顺序的，尺寸麻烦，重塑

Question

我试图做类似的架构的一个在这个例子：
https://github.com/fchollet/keras/blob/master/examples/image_ocr.py#L480
但是我的数据我一直有尺寸的问题，我还没有找到一个很好的网站这解释了用您自己的数据而不是MNIST或默认数据来控制尺寸。

上下文：即时尝试前文提到的图像与文字让我说我第一次尝试与2000.对于标签，我决定做one_hot编码，这是数据特征：
图像固定形状： （2000,208,352,1）#B & W
one_hot标签大小：（2000,346,1）＃2000个样本和346个类，最后一个值是具有三维数组，因为它对于softmax显然是需要的

现在的代码：

nb_classes = 346 
max_lin, max_col = (208, 352) 
input_shape = (max_lin, max_col, 1) 
conv_filters = 16 
kernel_size = (3, 3) 
pool_size = 2 
time_dense_size = 32 
rnn_size = 512 
act = 'relu' 

input_data = Input(name='the_input', shape=input_shape) 
inner = Conv2D(conv_filters, kernel_size, padding='same', 
      activation=act, name='CONV2D_1')(input_data) 
inner = MaxPooling2D(pool_size=(pool_size, pool_size), 
      name='MXPOOL2D_1')(inner) 
inner = Conv2D(conv_filters, kernel_size, padding='same', 
      activation=act, name='CONV2D_1')(input_data) 
inner = MaxPooling2D(pool_size=(pool_size, pool_size), 
      name='MXPOOL2D_1')(inner) 

#This is my problem, I dont really know how to reshape it with my data, 
#I chose (104,2816) because other stuff didnt worked and I found it was 
#the Layer Before (104,176,16) = (104, 176*16) = (104,2816); others values 
#gives me ValueError: total size of new array must be unchanged 

conv_to_rnn_dims = (104,2816) 
inner = Reshape(target_shape=conv_to_rnn_dims, name='reshape')(inner) 

inner = Dense(time_dense_size, activation=act, name='dense1')(inner) 
gru_1 = GRU(rnn_size, return_sequences=True, kernel_initializer='he_normal', name='gru1')(inner) 
gru_1b = GRU(rnn_size, return_sequences=True, go_backwards=True, kernel_initializer='he_normal', name='gru1_b')(inner) 
gru1_merged = add([gru_1, gru_1b]) 
gru_2 = GRU(rnn_size, return_sequences=True, kernel_initializer='he_normal', name='gru2')(gru1_merged) 
gru_2b = GRU(rnn_size, return_sequences=True, go_backwards=True, kernel_initializer='he_normal', name='gru2_b')(gru1_merged) 
gru_conc = concatenate([gru_2, gru_2b]) 
print("GruCOnc: ",gru_conc.shape) 
inner = Dense(nb_classes, kernel_initializer='he_normal', 
      name='DENSE_2')(gru_conc) 
print("2ndDense: ",inner.shape) 
y_pred = Activation('softmax',name='softmax')(inner) 
print(y_pred.shape) 
model = Model(inputs=input_data, outputs=y_pred) 
print(model.summary()) 

sgd = SGD(lr=0.02, decay=1e-6, momentum=0.9, nesterov=True, clipnorm=5) 
model.compile(loss='categorical_crossentropy',optimizer=sgd) 
model.fit(train_data, train_label, batch_size=10, epochs=2, verbose=1) 
score = model.evaluate(x_test, y_test, verbose=1) 

print(score) 

和运行代码后，我得到：

ValueError: Error when checking target: expected softmax to have shape (None, 104, 346) but got array with shape (2000, 346, 1) 

所以这里的大问题是，什么是104？因为346显然是班级的数量，但另一个值让我完全失去了。

感谢大家阅读我的问题。

Answer 1

1. conv_to_rnn_dims = (104,2816)这是虚构的。据我所知，你正尝试将你的CNN输出提供给Dense图层。但CNN的最后一层是MaxPooling，它产生2D输出。您应该使用Flatten来执行此连接。让我们检查一下这个例子。

   model=Sequential()    
   model.add(Conv2D(16,3,3,border_mode="same",input_shape=(208,352,1)) 
   #Produces 2000 x 208 x 352 x 16 
   model.add(Conv2D(32,3,3,activation="tanh",border_mode="valid")) 
   #Produces 2000 x 208 x 352 x 32 
   model.add(Flatten()) 
   #Produces 2000 x 2342912 
   model.add(Dense(100,activation="sigmoid")) 
   #Produces 2000 x 100 
   

这意味着你不需要重塑层这里。

这Dense后，你应该使用Reshape，使输出准备GRU。现在你有100 时间步数阅读。所以你应该重塑为model.add(Reshape((100,1))所以网络的结果现在是2000 x 100 x 1。你可以用一个热载体安全适合给你的GRU层

最后，对于分类问题和Dense层在输出你的目标形状应该是2000×346因此，最终Dense层应该有346个节点。