When webcam_demo.py and long_video_demo.py perform motion recognition on the same video, their results are much different.

[Air847735]

Branch

main branch (1.x version, such as v1.0.0, or dev-1.x branch)

Prerequisite

• I have searched Issues and Discussions but cannot get the expected help.
• I have read the documentation but cannot get the expected help.
• The bug has not been fixed in the latest version.

Environment

sys.platform: win32
Python: 3.8.19 (default, Mar 20 2024, 19:55:45) [MSC v.1916 64 bit (AMD64)]
CUDA available: True
MUSA available: False
numpy_random_seed: 2147483648
GPU 0: NVIDIA GeForce RTX 4080
CUDA_HOME: C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.2
NVCC: Cuda compilation tools, release 11.2, V11.2.67
GCC: n/a
PyTorch: 1.13.1
PyTorch compiling details: PyTorch built with:

• C++ Version: 199711
• MSVC 192829337
• Intel(R) Math Kernel Library Version 2020.0.2 Product Build 20200624 for Intel(R) 64 architecture applications
• Intel(R) MKL-DNN v2.6.0 (Git Hash 52b5f107dd9cf10910aaa19cb47f3abf9b349815)
• OpenMP 2019
• LAPACK is enabled (usually provided by MKL)
• CPU capability usage: AVX2
• CUDA Runtime 11.7
• NVCC architecture flags: -gencode;arch=compute_37,code=sm_37;-gencode;arch=compute_50,code=sm_50;-gencode;arch=compute_60,code=sm_60;-gencode;arch=compute_61,code=sm_61;-gencode;arch=compute_70,code=sm_70;-gencode;arch=compute_75,code=sm_75;-gencode;arch=compute_80,code=sm_80;-gencode;arch=compute_86,code=sm_86;-gencode;arch=compute_37,code=compute_37
• CuDNN 8.5
• Magma 2.5.4
• Build settings: BLAS_INFO=mkl, BUILD_TYPE=Release, CUDA_VERSION=11.7, CUDNN_VERSION=8.5.0, CXX_COMPILER=C:/cb/pytorch_1000000000000/work/tmp_bin/sccache-cl.exe, CXX_FLAGS=/DWIN32 /D_WINDOWS /GR /EHsc /w /bigobj -DUSE_PTHREADPOOL
  -openmp:experimental -IC:/cb/pytorch_1000000000000/work/mkl/include -DNDEBUG -DUSE_KINETO -DLIBKINETO_NOCUPTI -DUSE_FBGEMM -DUSE_XNNPACK -DSYMBOLICATE_MOBILE_DEBUG_HANDLE -DEDGE_PROFILER_USE_KINETO, LAPACK_INFO=mkl, PERF_WITH_AVX=1
  , PERF_WITH_AVX2=1, PERF_WITH_AVX512=1, TORCH_VERSION=1.13.1, USE_CUDA=ON, USE_CUDNN=ON, USE_EXCEPTION_PTR=1, USE_GFLAGS=OFF, USE_GLOG=OFF, USE_MKL=ON, USE_MKLDNN=ON, USE_MPI=OFF, USE_NCCL=OFF, USE_NNPACK=OFF, USE_OPENMP=ON, USE_ROCM=OFF,

TorchVision: 0.14.1
OpenCV: 4.10.0
MMEngine: 0.10.4
MMAction2: 1.2.0+4d6c934
MMCV: 2.1.0
MMDetection: 3.2.0
MMPose: 1.3.2

Describe the bug

I fine-tuned tsn using my own dataset during experiments. The results I got are working fine in webcam_demo. But I wanted to be able to identify each picture of the video, so I tried long_video_demo.py, but I found that the same video was shot on the screen through the webcam and the video was directly identified, the results were very different. , but the results of Webcam are closer to correct, while long_video_demo cannot get good results, and even recognizes errors. My config and label_map both use the same one. Does anyone know what could cause this to happen?

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