Chenglong Zou

batch normalization layer for data_format == 'channels_last'

1

### New Issue Checklist - [ ] I have read the [Contribution Guidelines](https://github.com/tensorlayer/tensorlayer/blob/master/CONTRIBUTING.md) - [ ] I searched for [existing GitHub issues](https://github.com/tensorlayer/tensorlayer/issues) ### Issue Description according to batch normalization implement...

tensor.sign? no backward?

4

See https://github.com/itayhubara/BinaryNet.pytorch/blob/master/models/binarized_modules.py  I want to know what is the backward process of this function. Only use tensor.sign()? What is the backward values of it？

about seq5 in synthetic dataset

3

In you paper, the seq5 example in Figure 4 is rotated with a random degree between 0 and 360 degrees. but it can't be distinguished between clockwise or counterclockwise. Because...

The file "normalize_nn_data.m" and "normalize_cnn_data.m" have the code such as : for l = 1 : numel(nn.size)-1 % Find the max and rescale weight_max = max(max(max(0, nn.W{l}))); activation_max = max(max(max(0,...

https://github.com/zcaicaros/L2D/blob/7b2efbb1ffc960260b16952f2bed68e500765bf0/permissibleLS.py#L13

How to test bigger instance and irregular instance

5

Why your models trained on small instances can be tested on bigger instances, how to solve the difference of size. Why each operation of your instance need different machines, no...

请问如何将训练好的模型在更大或者更小的instance上进行测试，调试的时候一直报错。