yanghu819 issues

Results 19 issues of


                                            yanghu819

the result of resnet18 with imagenet is Test Acc: 0.09(I loaded your pretrained model)

Wonderful work, we want to reproduce your results on imagenet, could you provide us your bash with detailed setting?

not cool to name a variable self.nonlocal maybe change to non_local(for nonlocal is not ok for python3)

Cmake error，other 2 compile methods succeeded

Checking whether the CUDA compiler is NVIDIA using "" did not match "nvcc: NVIDIA \(R\) Cuda compiler driver": Checking whether the CUDA compiler is Clang using "" did not match...

Reproduction of Repopt on yolo-nano with batchsize 256 on 8 gpus ?

The reproduction results are far lower than the reported ## hs python -m torch.distributed.launch --nproc_per_node 8 tools/train.py --batch 256 --conf configs/repopt/yolov6n_hs.py --data data/coco_run.yaml --device 0,1,2,3,4,5,6,7 \ --name repopt_n_hs --workers 16...

Configs and pretrained weights about nano&tiny repopt?

404

part1 is no where

No pretrained model to be logistic regression will also achieve 83+ on cifar-10

before pre-train I save the checkpoint which should be very weak in representation ![image](https://user-images.githubusercontent.com/44990984/219338971-0ebd38f8-695b-4fcc-b016-8a493331084e.png) and perform logistic regression as: python3 logistic_regression.py --model_path=./model-no-train.pt and the result is Epoch [296/300]: Loss/train: 0.4051439380645752...

yanghu819