-
-
I use 3 GPUs to train it. But the error occurs. Do you have any solution?
RuntimeError: cuda runtime error (10) : invalid device ordinal at /pytorch/torch/csrc/cuda/Module.cpp:33
THCudaCheck FAIL …
-
I found the best performance in Cityscapes leaderboard(83.7). How can I reproduce this result?
-
I had train the pascal voc 2012 dataset,but The result of training is 67.23, the training loss is decreaseing, but the valing loss unchange,Can you tell me your result?thank you.
-
Thanks for sharing your work!
Can you tell me in detail how you did this landmark loss, which is to present the langmark in the form of a heatmap of [h,w,1], and then calculate the l2loss for the inp…
-
i try to train htc
`python /mmdetection/tools/train.py 'htc_hrnetv2p_w18_20e_coco.py'`
and this is the config file
```
dataset_type = 'CocoDataset'
data_root = 'data/coco/'
img_norm_cfg = …
-
Showing module not found error in nms.py file, 'nms.cpu_nms' is not found.
Error found while executing :
python tools/test.py \ --cfg experiments/mpii/hrnet/w32_256x256_adam_lr1e-3.yaml \ TEST.MOD…
-
Hi:
Need `HRNetV2p-W48` backbone to run the related config model, like `Cascade R-CNN with HRNetV2p-W48`. Now there are `msra/hrnetv2_w18', 'msra/hrnetv2_w32', 'msra/hrnetv2_w40.`
-
Why do I use your HRNetW18, the forward time is 2.5 times as long as resnet50
-
Hello!
Did you use syncBN during training this HRNet?
I find that the mmdetection had not achieved the function of syncBN in the version you are using.