Joel Akeret

We can't help you if you don't provide any kind of information

you could use tensorboard to visualize the graph of the network. The input placeholder is defined [here](https://github.com/jakeret/tf_unet/blob/master/tf_unet/unet.py#L194) and the output [here](https://github.com/jakeret/tf_unet/blob/master/tf_unet/unet.py#L209)

Depending on the loss you are using this actually [valid](https://github.com/jakeret/tf_unet/blob/master/tf_unet/unet.py#L235)

I see, that's every odd. Haven't seen that before

You're right, this incorrect. Luckily, this has no effect on the network. The 'variables' are only used to compute the normalized gradients in order to visuize the overall training process....

Based on the information I have to guess a bit. Are you sure that the data and the mask image have the same dimension? What is the error you are...

No this line is actually important. Thats where I load the dataset used for the verification. I just checked in an update where I replaced the magic-number with a constant...

Thats the data you want to run the prediction/test on.

Hard to tell from this. Can you provide the code and the data so that it can be reproduced? Apart from that, this line `prediction = net.predict(path, data_provider)` is not...

Seems like that there is a bug in the `util.crop_to_shape` function when the image size contains an odd number. One way around this in the meantime it to resize your...