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
n_input = 9216
n_classes = 2
batch_xs = imgReader.read_images(pathname);
ValueError: Cannot feed value of shape (104, 96, 96, 1) for Tensor
u'Placeholder:0', which has shape (Dimension(None), Dimension(9216))
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 x h x w x channels, into a
batch_size x 9216 element matrix as expected by the placeholder.