Daniel Penalva

this may be related to the issue #229 i posted earlier, seems to be something related with the preprocessings of the input but i still cant say exactly what it...

iam also using all libs in (seeminly) right versions, however the assertion error persists, the image_T_only produces Nans

yes i tried to hack the whole thing out, even securing the dependency version of numpy and tensoflow it does not works. Its get nans as outputs. I think a...

Which code are you trying to execute ? Are you able to go though the tutorial, but outside Colab env ? On Fri, Feb 21, 2020 at 1:07 PM Cristina...

I think this is the case for the other notebooks too. Basic tutorial goes the same thing (and it is the basics ! its not as hard as 3D textures),...

I would start with the following strategy, try to execute in eager mode or try to get rid of every tensorflow function that preprocess image, since you have to start...

try to put it before all the code you are executing tf.enable_eager_execution() tf.enable_resource_variables() them go on hacking and seeing the variable values ... On Fri, Feb 21, 2020 at 1:35...

or you can simply create a session with the graph in the context (the supposition is it is alreaded builded by model keras instance), generate an init_op and run it,...

You can use something like this to try to debug the code while the devs are busy to not attend this bug. ```python def debug_info(tensor, mode="value"): import matplotlib.pyplot as plt    ...

The thing iam wondering can be causing bug is not the pre-processing, since it showed numerical matrices, but objective.as_objective can be breaking the path of the layer or the tensor,...