Ligeng Zhu
Ligeng Zhu
Hi author Thanks for sharing your code. I notice in README you said "Multi-gpu help wanted". If you are indicating data parallelism, then it can be implemented in several lines...
Thanks a lot for sharing pretrained models. Now I am trying to modify the network structure, e.g. change num_filters, add kernel size. With `symbol.json` it is hard to operate, could...
After `docker build .`, the image was successfully built. However, when I typed next instructions, following error occurred. ```fish 02:58 Albireo (master) ✗ docker run --rm -it -v "latest:/albireo" -p...
Hi there, It seems that the `manywheel/build_docker.sh` failed to execute currently. On Github Action, the build shows error https://github.com/pytorch/builder/actions/workflows/build-pytorch-wheels.yml and on my local workstation, the build shows ``` => CACHED...
Hi there, I appreciate the pretrained model shared on links. However, I want to try adjustments on these models, so surgery on `symbol.json` does not seem like the proper way....
Hi author Thanks for sharing the code. I am pretty interested in this work. When I am testing the compression LeNet, it raises "dimension not match" error. Could you share...
When I load using `model = gcv.models.resnet50(pretrained=True)` and test forwarding, error `RuntimeError: size mismatch, m1: [1 x 991232], m2: [2048 x 1000]` raises. I think there should be something wrong...
Hi author, I notice that in your experiment on imagenet, instead of having same repeated layers in each block, you set different layers for each block. Do you design it...
Hi author, Thanks for designing such a flexible and efficient dataloader. WIDS used to work fine in my training pipelines, however, I recently notice a werid error when loading [SAM...