linnan wang comments

Results 43 comments of


                                            linnan wang

[GPUNet/PyTorch] Model padding is incorrect, layer naming goes against norms.

Hello @rwightman , Thank you so much for submitting this bug report; we're working on fixing the license issue and sincerely apologize for not doing it right in the first...

[GPUNet/PyTorch] Model padding is incorrect, layer naming goes against norms.

> @linnanwang thanks for updating the copyright/license info > > The issue with padding is that the 3x3 convs in the EdgeResidual (FusedMBConv) layers have 0 padding, for typical PyTorch...

[GPUNet/PyTorch] Model padding is incorrect, layer naming goes against norms.

@rwightman Also I really appreciate your advices in the naming convention. Yes, our stem and head is opposite to the conventions in timm and the community and we will revise...

[GPUNet/PyTorch] Model padding is incorrect, layer naming goes against norms.

@rwightman Thanks Ross. It will be great to see GPUNet into Timm's library. I'm talking to the team to see our bandwidth and make a properly plan ahead. But I'm...

[GPUNet/PyTorch] Model padding is incorrect, layer naming goes against norms.

Hello @rwightman, we have changed the naming and padding of GPUNet and the following is the **new** network structure from get_configs(batch=1, latency="0.65ms", gpuType="GV100") on our side. Could you please kindly...

[GPUNet/PyTorch] Model padding is incorrect, layer naming goes against norms.

Thank you @rwightman. The activation in stem/head are all RELU now. Another thing I want to confirm with you is our customized InvertedResidual. We search for its internal structure and...

[GPUNet/PyTorch] Model padding is incorrect, layer naming goes against norms.

Thank you @rwightman. I'm pasting all the model definitions here for you to double check with Timm's compatibility. Please note re-train these models are very expensive, so let's try to...

[GPUNet/PyTorch] Model padding is incorrect, layer naming goes against norms.

get_configs(batch=1, latency="1.75ms", gpuType="GV100") ``` GPUNet( (network): Sequential( (stem: 2): Prologue( (net): Sequential( (0): Conv2d(3, 32, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False) (1): BatchNorm2d(32, eps=0.001, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace=True)...

[GPUNet/PyTorch] Model padding is incorrect, layer naming goes against norms.

get_configs(batch=1, latency="0.5ms-D", gpuType="GV100") ``` GPUNet( (network): Sequential( (stem: 2): Prologue( (net): Sequential( (0): Conv2d(3, 32, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False) (1): BatchNorm2d(32, eps=0.001, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace=True)...

[GPUNet/PyTorch] Model padding is incorrect, layer naming goes against norms.

get_configs(batch=1, latency="0.8ms-D", gpuType="GV100") ``` GPUNet( (network): Sequential( (stem: 2): Prologue( (net): Sequential( (0): Conv2d(3, 32, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False) (1): BatchNorm2d(32, eps=0.001, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace=True)...