Closed ykk648 closed 2 years ago
Hi @ykk648 , thank you very much for your feedback.
- MPII official dataset missing
train.h5
, see #135 We are looking into this, will update here if we have any progress.- MPI-INF-3DHP & Human3.6m needs extract frame first, I add
extract_img=True
inconvert_datasets.py
, it costs about 16 & 6 hours with low cpu consumation on one hard disk, no one had told me that :(- According human36m-mosh, the file structure is
/datasets/h36m_mosh
, but the h36m_spin convertor acturally needs/datasets/h36m_extras/mosh_data
- Why remove
frame_
in MPI-INF-3DHP image path ref here? It raiseFileNotFoundError: [Errno 2] No such file or directory: 'data/datasets/mpi_inf_3dhp/S5/Seq2/imageFrames/video_7/frame_000368.jpg'
when you start your first SPIN training.
These problems will be fixed in #143 .
To download H36M, you need to make an account at the official website first and wait for approval. For H36M mosh, the original license does not allow us to redistribute it, but it is indeed available online.
thx, issue close
I have no human3d training exp before , most are datasets preprocess problems.
train.h5
, see #135extract_img=True
inconvert_datasets.py
, it costs about 16 & 6 hours with low cpu consumation on one hard disk, no one had told me that :(/datasets/h36m_mosh
, but the h36m_spin convertor acturally needs/datasets/h36m_extras/mosh_data
frame_
in MPI-INF-3DHP image path ref here? It raiseFileNotFoundError: [Errno 2] No such file or directory: 'data/datasets/mpi_inf_3dhp/S5/Seq2/imageFrames/video_7/frame_000368.jpg'
when you start your first SPIN training.Finally, in case #53 occur, run
python
-m torch.distributed.launch --nproc_per_node=4 --master_port=29500 tools/train.py ./configs/spin/resnet50_spin_pw3d.py --no-validate --work-dir ./work_dir --gpus 4 --launcher pytorch`2022-03-30 07:17:02,817 - mmhuman3d - INFO - Epoch [1][50/782] lr_backbone: 3.000e-05 lr_head: 3.000e-05, eta: 5:46:10, time: 2.673, data_time: 0.355, memory: 3296, keypoints3d_loss: 0.9700, keypoints2d_loss: 0.1061, vertex_loss: 0.1511, smpl_pose_loss: 0.0978, smpl_betas_loss: 0.0287, camera_loss: 0.0000, loss: 1.3538
The world is bright again.