Question

我目前正在尝试使用Keras构建CRNN。当我尝试调整输入大小时，在为LSTM找到正确的尺寸时遇到了一些麻烦。经过一些调试后，我在我的 model 对象中找到了一个名为 output_shape 的字段，其值为（3,1,244），并尝试将其作为带有（3,224）的2D数组传递。一切正常，但我做对了吗？这背后的数学原理是什么？我下次如何做才能发现这种大小而无需调试？

def CRNN(blockSize, blockCount, inputShape, trainGen, testGen, epochs):

model = Sequential()

# Conv Layer
channels = 32
for i in range(blockCount):
    for j in range(blockSize):
        if (i, j) == (0, 0):
            conv = Conv2D(channels, kernel_size=(5, 5),
                          input_shape=inputShape, padding='same')
        else:
            conv = Conv2D(channels, kernel_size=(5, 5), padding='same')
        model.add(conv)
        model.add(BatchNormalization())
        model.add(Activation('relu'))
        model.add(Dropout(0.15))
        if j == blockSize - 2:
            channels += 32
    model.add(MaxPooling2D(pool_size=(2, 2), padding='same'))
    model.add(Dropout(0.15))

# Feature aggregation across time
model.add(Reshape((3, 224)))

# LSTM layer
model.add(Bidirectional(LSTM(200), merge_mode='ave'))
model.add(Dropout(0.5))

# Linear classifier
model.add(Dense(4, activation='softmax'))


model.compile(loss=keras.losses.categorical_crossentropy,
              optimizer=keras.optimizers.Adam(),
              metrics=['accuracy']) # F1?


model.fit_generator(trainGen,
                    validation_data=testGen, steps_per_epoch = trainGen.x.size // 20,
                    validation_steps = testGen.x.size // 20,
                    epochs=epochs, verbose=1)
return model

# Function call
model = CRNN(4, 6, (140, 33, 1), trainGen, testGen, 1)

正确管理Reshape以从以前的CNN构建RNN

0 个答案: