使用我自己的数据时出现Tensorflow错误

Question

I've been playing with the Tensorflow library doing the tutorials. Now I wanted to play with my own data, but I fail horribly. This is perhaps a noob question but I can't figure it out.

I'm using this example: https://github.com/aymericdamien/TensorFlow-Examples/blob/master/examples/3%20-%20Neural%20Networks/convolutional_network.py

I want to use my own images, for converting my images to use with tensorflow i'm using this: https://github.com/HamedMP/ImageFlow/blob/master/ImageFlow.py

Now I change the parameters in the example from this:

 n_input = 784
 n_classes = 10

to this:

 n_input = 9216
 n_classes = 2

I did that because my images are 96 * 96 and there are only 2 classes of my images

I also change the weights and biases to the numbers I need.

I read the data like this:

batch_xs = imgReader.read_images(pathname);

imgReader being the ImageFlow file

but when I try to run it I gives me an error:

 ValueError: Cannot feed value of shape (104, 96, 96, 1) for Tensor
 u'Placeholder:0', which has shape (Dimension(None), Dimension(9216))

I feel like i'm overlooking something small but I don't see it.

Answer 1

This error arises because the shape of the data that you're trying to feed (104 x 96 x 96 x 1) does not match the shape of the input placeholder ( batch_size x 9216, where batch_size may be variable).

To make it work, add the following line before running a training step:

batch_xs = np.reshape(batch_xs, (-1, 9216))

This uses numpy to reshape the images read in, which are 4-D arrays of batch_size xhxwx channels, into a batch_size x 9216 element matrix as expected by the placeholder.

Answer 2

我通过pip升级tensorflow解决了这个问题。