efficient_densenet_pytorch

efficient_densenet_pytorch copied to clipboard

AttributeError: module 'fire' has no attribute 'Fire'

8

AttributeError: module 'fire' has no attribute 'Fire'

MRLQ-Q

How can I apply this to my own model?

1

Thank you for your nice work. My model use the densenet connections like: tensorFeat = torch.cat([self.moduleOne(tensorFeat), tensorFeat], 1) tensorFeat = torch.cat([self.moduleTwo(tensorFeat), tensorFeat], 1) tensorFeat = torch.cat([self.moduleThr(tensorFeat), tensorFeat], 1) tensorFeat =...

CXMANDTXW

Is this really memory efficient?

1

I see the memory consumption chart in the readme, but after looking at the code, I have doubts that this implementation is fully memory efficient. I see the call to...

leonardishere

pretrained densenet169 weights

8

Hi, thanks for your great work! I'm working on densenet169 these days, do you know where I can find the ImageNet pretrained weights for this efficient implementation? Or do you...

Kexiii

Hi, thanks for your work. I have a question here on dropout. In densenet.py, the block function is defined as follow: ```python def forward(self, *prev_features): bn_function = _bn_function_factory(self.norm1, self.relu1, self.conv1)...

lizhenstat

What is the minimum GPU memory required? Still breaks for me in a single GPU

1

**Amazon p3.2xlarge: 1 GPUs - Tesla V100 -- GPU Memory: 16GB -- Batch Size = 64** If efficient = False: Error: RuntimeError: CUDA out of memory. Tried to allocate 1024.00...

PabloRR100

does this code support pytorch1.0 and the jit feature for c++ online deployment?

3

mmxuan18

MultiGPU efficient densenets are slow

14

I just want to benchmark the new implementation of efficient densenet with the code [here](https://gist.github.com/wandering007/d7f3db11285f382fefa39a9cda99ad0d). However, it seems that the used checkpointed modules are not broadcast to multiple GPUs as...

wandering007

Segmentation fault (core dumped) error for multiple GPUs

6

Environment: - Python: 3.6 - PyTorch: 0.4.0 - OS: Ubuntu 18.04.1 LTS - CUDA: V9.1.85 - GPU: Tesla K80 Problem: I was running a model that does not need BatchNorm,...

theonegis

Broken link - MxNet implementation

2

Hi. The link for the MxNet implementation provided in README is broken.

desertnaut