Get different result for the same input in inference

Branch

0.x branch (0.x version, such as v0.24.1)

Prerequisite

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

Environment

sys.platform: linux
Python: 3.8.16 (default, Oct 16 2023, 14:40:53) [GCC 11.4.0]
CUDA available: True
GPU 0,1: NVIDIA GeForce RTX 4090
CUDA_HOME: None
GCC: gcc (Ubuntu 11.4.0-1ubuntu1~22.04) 11.4.0
PyTorch: 1.9.0+cu111
PyTorch compiling details: PyTorch built with:

GCC 7.3
C++ Version: 201402
Intel(R) Math Kernel Library Version 2020.0.0 Product Build 20191122 for Intel(R) 64 architecture applications
Intel(R) MKL-DNN v2.1.2 (Git Hash 98be7e8afa711dc9b66c8ff3504129cb82013cdb)
OpenMP 201511 (a.k.a. OpenMP 4.5)
NNPACK is enabled
CPU capability usage: AVX2
CUDA Runtime 11.1
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_70,code=sm_70;-gencode;arch=compute_75,code=sm_75;-g encode;arch=compute_80,code=sm_80;-gencode;arch=compute_86,code=sm_86
CuDNN 8.0.5
Magma 2.5.2
Build settings: BLAS_INFO=mkl, BUILD_TYPE=Release, CUDA_VERSION=11.1, CUDNN_VERSION=8.0.5, CXX_COMPILER=/opt/rh/devtoolset-7/root/usr/bin/c++, CXX_FLAGS= -Wno-deprecated -fvisibility-inlines-hidden -DUSE_PT$ READPOOL -fopenmp -DNDEBUG -DUSE_KINETO -DUSE_FBGEMM -DUSE_QNNPACK -DUSE_PYTORCH_QNNPACK -DUSE_XNNPACK -DSYMBOLICATE_MOBILE_DEBUG_HANDLE -O2 -fPIC -Wno-narrowing -Wall -Wextra -Werror=return-type -Wno-missing-fi eld-initializers -Wno-type-limits -Wno-array-bounds -Wno-unknown-pragmas -Wno-sign-compare -Wno-unused-parameter -Wno-unused-variable -Wno-unused-function -Wno-unused-result -Wno-unused-local-typedefs -Wno-stric t-overflow -Wno-strict-aliasing -Wno-error=deprecated-declarations -Wno-stringop-overflow -Wno-psabi -Wno-error=pedantic -Wno-error=redundant-decls -Wno-error=old-style-cast -fdiagnostics-color=always -faligned- new -Wno-unused-but-set-variable -Wno-maybe-uninitialized -fno-math-errno -fno-trapping-math -Werror=format -Wno-stringop-overflow, LAPACK_INFO=mkl, PERF_WITH_AVX=1, PERF_WITH_AVX2=1, PERF_WITH_AVX512=1, TORCH_V ERSION=1.9.0, 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=ON, USE_NNPACK=ON, USE_OPENMP=ON,

TorchVision: 0.10.0+cu111
OpenCV: 4.8.0
MMCV: 1.7.1 MMCV Compiler: GCC 7.3
MMCV CUDA Compiler: 11.1
MMAction2: 0.24.1+27c674a

Describe the bug

When I do inference using the "inference_recognizer" function in mmaction/apis/inference.py I get different results! I have tried to see if there is any thing that causes randomness in the pipeline but not found! Anyone know the solution?

Reproduces the problem - code sample

Just that:

results, returned_features = inference_recognizer(model,
                                     video,
                                     nb_class_predicted=9,
                                     score_threshold=0)

Reproduces the problem - command or script

No response

Reproduces the problem - error message

No response

Additional information

No response

open-mmlab / mmaction2