OpenMMLab's Next Generation Video Understanding Toolbox and Benchmark
4.21k
stars
1.23k
forks
source link
[Bug] skeleton-based action recognition posec3d config with keypoints extracted from hrnet can not train from resume mode. #2654
Open
Newj596 opened 1 year ago
Branch
main branch (1.x version, such as
v1.0.0
, ordev-1.x
branch)Prerequisite
Environment
sys.platform: linux Python: 3.8.16 (default, Mar 2 2023, 03:21:46) [GCC 11.2.0] CUDA available: True numpy_random_seed: 2147483648 GPU 0,1,2,3: NVIDIA GeForce RTX 3090 CUDA_HOME: /usr/local/cuda NVCC: Cuda compilation tools, release 11.2, V11.2.67 GCC: gcc (Ubuntu 7.5.0-6ubuntu2) 7.5.0 PyTorch: 1.9.1+cu111 PyTorch compiling details: PyTorch built with:
TorchVision: 0.10.1+cu111 OpenCV: 4.8.0 MMEngine: 0.7.3 MMAction2: 1.1.0+ MMCV: 2.0.0 MMDetection: 3.0.0 MMPose: 1.0.0
Describe the bug
when I try to train from resume for posec3d, it doesn't work. tools/train.py
Reproduces the problem - code sample
No response
Reproduces the problem - command or script
No response
Reproduces the problem - error message
No response
Additional information
No response