I train eqlv2 using 8 gpus, howerer, the AP is only 0.192
CRuJia opened this issue · 2 comments
CRuJia commented
Describe the issue
I used your training command, but it doesn't works. But i use your pretrained model to test, i can get a expected result.
Tkanks.
Reproduction
- What command or script did you run?
./tools/dist_test.sh configs/end2end/eqlv2_r50_8x2_1x.py data/pretrain_models/eqlv2_1x.pth 8 --out results.pkl --eval bbox segm
- What config dir you run?
configs/end2end/eqlv2_r50_8x2_1x.py
-
Did you make any modifications on the code or config? Did you understand what you have modified?
No. -
What dataset did you use?
LVIS
Environment
- Please run
python mmdet/utils/collect_env.pyto collect necessary environment information and paste it here.
Python: 3.7.0 (default, Oct 9 2018, 10:31:47) [GCC 7.3.0]
CUDA available: True
CUDA_HOME: None
GPU 0,1,2,3,4,5,6,7: TITAN Xp
GCC: gcc (Ubuntu 7.4.0-1ubuntu1~18.04.1) 7.4.0
PyTorch: 1.5.0
PyTorch compiling details: PyTorch built with:
- GCC 7.3
- C++ Version: 201402
- Intel(R) Math Kernel Library Version 2020.0.2 Product Build 20200624 for Intel(R) 64 architecture applications
- Intel(R) MKL-DNN v0.21.1 (Git Hash 7d2fd500bc78936d1d648ca713b901012f470dbc)
- OpenMP 201511 (a.k.a. OpenMP 4.5)
- NNPACK is enabled
- CPU capability usage: AVX2
- CUDA Runtime 10.2
- 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_37,code=compute_37
- CuDNN 7.6.5
- Magma 2.5.2
- Build settings: BLAS=MKL, BUILD_TYPE=Release, CXX_FLAGS= -Wno-deprecated -fvisibility-inlines-hidden -fopenmp -DNDEBUG -DUSE_FBGEMM -DUSE_QNNPACK -DUSE_PYTORCH_QNNPACK -DUSE_XNNPACK -DUSE_INTERNAL_THREADPOOL_IMPL -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-strict-overflow -Wno-strict-aliasing
-Wno-error=deprecated-declarations -Wno-stringop-overflow -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, PERF_WITH_AVX=1, PERF_WITH_AVX2=1, PERF_WITH_AVX512=1, USE_CUDA=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, USE_STATIC_DISPATCH=OFF,
TorchVision: 0.6.0a0+82fd1c8
OpenCV: 4.5.1
MMCV: 1.0.5
MMDetection: ('2.3.0',)
MMDetection Compiler: GCC 7.3
MMDetection CUDA Compiler: 10.2
Results
i wish get your result in readme file, howerer, the really result is this.
Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=300 catIds=all] = 0.192
Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=300 catIds=all] = 0.310
Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=300 catIds=all] = 0.206
Average Precision (AP) @[ IoU=0.50:0.95 | area= s | maxDets=300 catIds=all] = 0.153
Average Precision (AP) @[ IoU=0.50:0.95 | area= m | maxDets=300 catIds=all] = 0.259
Average Precision (AP) @[ IoU=0.50:0.95 | area= l | maxDets=300 catIds=all] = 0.318
Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=300 catIds= r] = 0.021
Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=300 catIds= c] = 0.169
Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=300 catIds= f] = 0.293
Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=300 catIds=all] = 0.268
Average Recall (AR) @[ IoU=0.50:0.95 | area= s | maxDets=300 catIds=all] = 0.196
Average Recall (AR) @[ IoU=0.50:0.95 | area= m | maxDets=300 catIds=all] = 0.354
Average Recall (AR) @[ IoU=0.50:0.95 | area= l | maxDets=300 catIds=all] = 0.449
2021-04-13 23:22:31,913 - mmdet - INFO - Evaluating segm...
Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=300 catIds=all] = 0.184
Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=300 catIds=all] = 0.288
Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=300 catIds=all] = 0.194
Average Precision (AP) @[ IoU=0.50:0.95 | area= s | maxDets=300 catIds=all] = 0.140
Average Precision (AP) @[ IoU=0.50:0.95 | area= m | maxDets=300 catIds=all] = 0.254
Average Precision (AP) @[ IoU=0.50:0.95 | area= l | maxDets=300 catIds=all] = 0.317
Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=300 catIds= r] = 0.018
Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=300 catIds= c] = 0.169
Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=300 catIds= f] = 0.274
Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=300 catIds=all] = 0.257
Average Recall (AR) @[ IoU=0.50:0.95 | area= s | maxDets=300 catIds=all] = 0.180
Average Recall (AR) @[ IoU=0.50:0.95 | area= m | maxDets=300 catIds=all] = 0.345
Average Recall (AR) @[ IoU=0.50:0.95 | area= l | maxDets=300 catIds=all] = 0.442
2021-04-13 23:38:18,184 - mmdet - INFO - Epoch [12][6213/6213] lr: 2.000e-04, bbox_AP: 0.1920, bbox_AP50: 0.3100, bbox_AP75: 0.2060, bbox_APs: 0.1530, bbox_APm: 0.2590,
bbox_APl: 0.3180, bbox_APr: 0.0210, bbox_APc: 0.1690, bbox_APf: 0.2930, bbox_mAP_copypaste: AP:0.192 AP50:0.310 AP75:0.206 APs:0.153 APm:0.259 APl:0.318 APr:0.021 APc:0
.169 APf:0.293, segm_AP: 0.1840, segm_AP50: 0.2880, segm_AP75: 0.1940, segm_APs: 0.1400, segm_APm: 0.2540, segm_APl: 0.3170, segm_APr: 0.0180, segm_APc: 0.1690, segm_APf
: 0.2740, segm_mAP_copypaste: AP:0.184 AP50:0.288 AP75:0.194 APs:0.140 APm:0.254 APl:0.317 APr:0.018 APc:0.169 APf:0.274
Issue fix
If you have already identified the reason, you can provide the information here. If you are willing to create a PR to fix it, please also leave a comment here and that would be much appreciated!
CRuJia commented
i'm sorry, i train model with eqlv1