-
Where is DenseCL code?
The DenseCL code link is 'https://git.io/AdelaiDet' in your paper, but I not found DenseCL code.
-
Where is the code of DenseCL? The link in your paper is this repo, but I don't see that.
-
The output size of the standard ResNet (after average pooling and without fc layer) is torch.Size([batchsize, 512, 1, 1]), but we need torch.Size([batchsize, 512, image_H, image_W]) as our pixel-lev…
-
RuntimeError: Default process group has not been initialized, please make sure to call init_process_group.
/usr/local/lib/python3.7/dist-packages/torch/nn/functional.py:718: UserWarning: Named tensor…
-
Replacing contrastive learning from image level to pixel level，it's going to be a lot less efficient, especially when calculating comparative loss. So how do you solve the thorny efficiency issues?
-
### Branch
main branch (mmpretrain version)
### Describe the bug
i try to run the training of a model of densecl on my custom dataset
i run this command on 1 gpu system
`python tools/train.py…
-
[DenseCL ResNet50 weights](https://cloudstor.aarnet.edu.au/plus/s/hdAg5RYm8NNM2QP/download)
URL is not woking
-
### Branch
1.x branch (1.x version, such as `v1.0.0rc2`, or `dev-1.x` branch)
### Prerequisite
- [X] I have searched [Issues](https://github.com/open-mmlab/mmselfsup/issues) and [Discussions](https…
-
Hi, Thanx for your great work,.
when run "$ bash inference_freemask.sh", error existed as :no such file. Pls tell me where can i get this json file?
-
### Describe the feature
I did the training on densecl model on my custom dataset .
i make the max_epoch first to be 300 as my dataset is very small ( only 170 images for training) , the increase t…