mega.pytorch
mega.pytorch copied to clipboard
Scalsol
Memory Enhanced Global-Local Aggregation for Video Object Detection, CVPR2020
输入命令行 python -m torch.distributed.launch --nproc_per_node 8 tools/train_net.py --config-file configs/DFF/vid_R_50_C4_DFF_1x.yaml OUTPUT_DIR ./training_dir/vid_R_50_C4_DFF_1x 训练后测试AP50的结果是0
(mega) PS D:\learning\mega-master> python demo/demo.py base configs/vid_R_101_C4_1x.yaml R_101.pth --visualize-path D:/learning/mega-master/test.png --output-folder visualization Traceback (most recent call last): File "demo/demo.py", line 6, in from predictor import VIDDemo File "D:\learning\mega-master\demo\predictor.py", line 11,...
Does anybody know, where to find the imagenet VID dataset? All links I found were dead
Hello, I failed to follow the mega.pytorch.INSTALL.md due to the CUDA version being incompatible with the Pytorch version. I exactly followed the INSTALL.md step by step, and I did install...
I try to run the training code for vid_R_50_C4_MEGA_1x.yaml. When i set SOLVER.TEST_PERIOD to a number > 0, then the error occurs :
 按照教程制作了自己的数据集 进行训练出现loss为nan的问题，更改学习率等操作没有效果，请各位大佬帮帮我。
Hello, My GPU supports only cuda 11.0 or higher. In that case, how can I run this model? When I tried, the error comes out like "lib10_cuda.so doesn't exist "....
