You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
According to DeiT's official GitHub results, DeiT-Tiny's accuracy (acc@1) is 72.2%. However, in MMPretrain, the acc@1 is reported as 74.50%. I would like to ask the cause of this difference.
Branch
main branch (mmpretrain version)
Describe the bug
According to DeiT's official GitHub results, DeiT-Tiny's accuracy (acc@1) is 72.2%. However, in MMPretrain, the acc@1 is reported as 74.50%. I would like to ask the cause of this difference.
MMPretrain
DeiT Official Code
Environment
{"env_info": "sys.platform: linux\nPython: 3.9.7 (default, Sep 16 2021, 13:09:58) [GCC 7.5.0]\nCUDA available: True\nGPU 0,1,2,3: Tesla PG503-216\nCUDA_HOME: /mnt/cache/share/cuda-11.1\nNVCC: Build cuda_11.1.TC455_06.29069683_0\nGCC: gcc (GCC) 7.3.0\nPyTorch: 1.9.1\nPyTorch compiling details: PyTorch built with:\n - GCC 7.3\n - C++ Version: 201402\n - Intel(R) oneAPI Math Kernel Library Version 2021.3-Product Build 20210617 for Intel(R) 64 architecture applications\n - Intel(R) MKL-DNN v2.1.2 (Git Hash 98be7e8afa711dc9b66c8ff3504129cb82013cdb)\n - OpenMP 201511 (a.k.a. OpenMP 4.5)\n - NNPACK is enabled\n - CPU capability usage: AVX2\n - CUDA Runtime 11.1\n - 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\n - CuDNN 8.0.5\n - Magma 2.5.2\n - 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_PTHREADPOOL -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-field-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-strict-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_VERSION=1.9.1, 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=ON, USE_NNPACK=ON, USE_OPENMP=ON, \n\nTorchVision: 0.10.1\nOpenCV: 4.5.3\nMMCV: 1.4.1\nMMCV Compiler: GCC 7.3\nMMCV CUDA Compiler: 11.1\nMMClassification: 0.19.0+61c1259", "seed": 666, "hook_msgs": {}}
Other information
No response
The text was updated successfully, but these errors were encountered: