Keras:InputLayer和Input的区别 [英] Keras: difference of InputLayer and Input

问题描述

我使用带有Tensorflow的Keras制作了模型.我在这些代码行中使用Inputlayer:

I made a model using Keras with Tensorflow. I use Inputlayer with these lines of code:

img1 = tf.placeholder(tf.float32, shape=(None, img_width, img_heigh, img_ch))
first_input = InputLayer(input_tensor=img1, input_shape=(img_width, img_heigh, img_ch)) 
first_dense = Conv2D(16, 3, 3, activation='relu', border_mode='same', name='1st_conv1')(first_input)

但是我得到这个错误:

ValueError: Layer 1st_conv1 was called with an input that isn't a symbolic tensor. Received type: <class 'keras.engine.topology.InputLayer'>. Full input: [<keras.engine.topology.InputLayer object at 0x00000000112170F0>]. All inputs to the layer should be tensors.

当我这样使用Input时，效果很好:

When I use Input like this, it works fine:

first_input = Input(tensor=img1, shape=(224, 224, 3), name='1st_input')
first_dense = Conv2D(16, 3, 3, activation='relu', border_mode='same', name='1st_conv1')(first_input)

Inputlayer和Input有什么区别?

推荐答案

• InputLayer是一层.
• Input是张量.
• InputLayer is a layer.
• Input is a tensor.

您只能调用将张量传递给它们的图层.

You can only call layers passing tensors to them.

想法是:

outputTensor = SomeLayer(inputTensor)

因此，只有Input可以通过，因为它是张量.

So, only Input can be passed because it's a tensor.

老实说，我不知道InputLayer存在的原因.也许应该在内部使用.我从没使用过，而且似乎永远也不需要.

Honestly, I have no idea about the reason for the existence of InputLayer. Maybe it's supposed to be used internally. I never used it, and it seems I'll never need it.

这篇关于Keras:InputLayer和Input的区别的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！