Gábor Vecsei

I think the problem is with the `VotePooling`. Instead of `pooled = tf.expand_dims(pooled, 0)` the right output is `pooled = tf.reshape(pooled, (self.batch_size, self.num_rois, self.channel_num))` as your comment says that the...

Hi @parap1uie-s Thank you for your response! I am looking forward to hear your thoughts on this issue. I hope we can find a solution. Btw, Thank you very much...

I had a little time and I tried to find out what went wrong: - Where I generate the boxes I need to clip the values between 0 and the...

@nkta3m, yes, this could be easily achieved with improving the plotting a bit. If you create a PR I will check it out as soon as I can. 🙂

Thank you very much for the help! It has been successful. ❤️

What is the version of Tensorflow and Keras?

Then I would advice to change to the newest version of Tensorflow and try out with that. It is defined in the requirements: https://github.com/gaborvecsei/Ridurre-Network-Filter-Pruning-Keras/blob/master/requirements.txt#L1 With this version it can happen...

Hi @Leci37 , Thank you very much I am flattered! Your project sounds interesting, and I think the open-source community would love such a project. If you can create a...

@caihengyu520 I do not have a problem with this, I just do not want my package to depend on it. To be fair, I have not touched this package in...

@Dronakurl thank you very much for the PR! I'll try to review it in the following week - but this is a huge one so it'll take a bit of...