带Tensorflow后端的Keras的K.function方法是否可以与网络层一起使用? [英] Does K.function method of Keras with Tensorflow backend work with network layers?

问题描述

我最近开始使用Keras构建神经网络.我建立了一个简单的CNN对MNIST数据集进行分类.在学习模型之前，我使用了K.set_image_dim_ordering('th')来绘制卷积层权重.现在，我正在尝试使用K.function方法可视化卷积层输出，但是我一直遇到错误.

I recently have started using Keras to build neural networks. I built a simple CNN to classify MNIST dataset. Before learning the model I used K.set_image_dim_ordering('th') in order to plot a convolutional layer weights. Right now I am trying to visualize convolutional layer output with K.function method, but I keep getting error.

这是我现在想要做的:

input_image = X_train[2:3,:,:,:]

output_layer = model.layers[1].output
input_layer = model.layers[0].input

output_fn = K.function(input_layer, output_layer)

output_image = output_fn.predict(input_image)
print(output_image.shape)

output_image = np.rollaxis(np.rollaxis(output_image, 3, 1), 3, 1)
print(output_image.shape)

fig = plt.figure()
for i in range(32):
    ax = fig.add_subplot(4,8,i+1)
    im = ax.imshow(output_image[0,:,:,i], cmap="Greys")
    plt.xticks(np.array([]))
    plt.yticks(np.array([]))
fig.subplots_adjust(right=0.8)
cbar_ax = fig.add_axes([1, 0.1, 0.05 ,0.8])
fig.colorbar(im, cax = cbar_ax)
plt.tight_layout()

plt.show()

这就是我得到的:

  File "/home/kinshiryuu/anaconda3/lib/python3.5/site-packages/keras/backend/tensorflow_backend.py", line 1621, in function
return Function(inputs, outputs, updates=updates)

  File "/home/kinshiryuu/anaconda3/lib/python3.5/site-packages/keras/backend/tensorflow_backend.py", line 1569, in __init__
raise TypeError('`inputs` to a TensorFlow backend function '

TypeError: `inputs` to a TensorFlow backend function should be a list or tuple.

推荐答案

您应进行以下更改:

output_fn = K.function([input_layer], [output_layer])
output_image = output_fn([input_image])

K.function将输入和输出张量作为列表，以便您可以创建从多个输入到多个输出的函数.在您的情况下，从一个输入到一个输出..但是您仍然需要将它们作为列表传递.

K.function takes the input and output tensors as list so that you can create a function from many input to many output. In your case one input to one output.. but you need to pass them as a list none the less.

下一步K.function返回张量函数，而不是可在其中使用predict()的模型对象.正确的使用方法只是作为函数调用

Next K.function returns a tensor function and not a model object where you can use predict(). The correct way of using is just to call as a function

这篇关于带Tensorflow后端的Keras的K.function方法是否可以与网络层一起使用?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！