pytorch-cpn

pytorch-cpn copied to clipboard

https://github.com/elixir-lsp/vscode-elixir-ls/blob/b645862891c3d8c92b0a286848be8a999f29072b/src/test/suite/index.ts

ghost

Hello, I want to ask the use of parameter "symmetry" in the config file.

tendernesswty

Can pre-trained model be loaded during training? I don't see the pretrained model loading code in the train.py

ing-NT

Unable to extract pretrained model archive

1

Hi, I'm trying to use the pretrained model but none of the tar files seem to be in working order. I get the following error: An error occurred while extracting...

solitarysandman

half of the output predictions are wrong

2

I am running custom images through this model. All the images have been pre-proceed and cropped as to just include the human, and I've removed all annotation files and hardcoded...

Michaelszeng

Image test demo

5

How to use the pre-training network model to visualize the image test results? Is there a demo?

Cronusf

in this paper, I see that CPN used the image cropped in raw image with the bounding box of FPN as input. Where is the FPN in your reimplement ?

zhwzhao

about the train.py file line:119

7

for global_output, label in zip(global_outputs, targets): num_points = global_output.size()[1] global_label = label * (valid > 1.1).type(torch.FloatTensor).view(-1, num_points, 1, 1) global_loss = criterion1(global_output, torch.autograd.Variable(global_label.cuda(async=True))) / 2.0 loss += global_loss global_loss_record +=...

gag1223

There are 4 vars: target15 target11 target9 target7 what's the means of them?

hgzry2015

target.cuda(async=True),在async=True处出现SyntaxError: invalid syntax

1

相关资料不是很直观，想问下我直接把 ``` refine_target_var = torch.autograd.Variable(target7.cuda(async=True)) valid_var = torch.autograd.Variable(valid.cuda(async=True)) ``` 改成如下可以吗？ ``` refine_target_var = torch.autograd.Variable(target7.cuda()) valid_var = torch.autograd.Variable(valid.cuda()) ```

my-hello-world