GitLab

Fix the old flatten method which use the size(0) to caculate the batch size, the old method will intruduce Gather opertion in the onnx output, which will faild parsed by tensorRT 5.0 (#1134)

* Add memory_efficient args to densenet docs

This PR adds the arg `memory_efficient` to densenet docs and also mentions the relevant publication.

* linting

* GPU efficient Densenets

* removed `import math`

* Changed 'efficient' to 'memory_efficient'

* Add tests

* Bugfix in test

* Fix lint

* Remove unecessary formatting

* added progress flag to model getters

* flake8

* bug fix

* backward commpability

* remove duplicate code from densenet

* correct indentation

* Changing to AdaptiveAvgPool2d

* add whitespace

* Update densenet.py

* Update densenet.py

* fix for PyTorch v0.4 (remove .data and add _ for the initializations in nn.init)

* fix m.**.**() style to nn.init.**(**) style

* remove .idea

* fix lines and indents

* fix lines and indents

* change to use `kaming_normal_`

* add `.data` for safety

* add nonlinearity='relu' for sure

* fix indents

* Update densenet.py

added missing weight init for densenet

* Update densenet.py

following official implementation [here](https://github.com/liuzhuang13/DenseNet/blob/master/models/densenet.lua#L160)

* Update densenet.py

changed to nn.init & fixed lint

I have made some performance improvements to the model, and testing them now.  If results turn out good, I will submit a separate PR.

Using python2 style '/' will convert int type to float in python3 which will cause the following error when creating FloatTensor:

TypeError: torch.FloatTensor constructor received an invalid combination of arguments - got (float, int, int, int), but expected one of:
 * no arguments
 * (int ...)
      didn't match because some of the arguments have invalid types: (float, int, int, int)