JDAI-CV / fast-reid

SOTA Re-identification Methods and Toolbox

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

PartialReid 无法复现

lovehuanhuan opened this issue · comments

Dataset Rank-1 Rank-5 Rank-10 mAP mINP
PartialREID 59.67 74.00 81.00 46.26 23.76
[05/06 02:17:44 fastreid.engine.defaults]: Prepare testing set
build_test_loader
OccludedREID
[05/06 02:17:44 fastreid.data.datasets.bases]: => Loaded OccludedREID in csv format:
subset # ids # images # cameras
:--------- :-------- :----------- :------------
query 319 1119 6
gallery 319 1119 6
size is
2238
[05/06 02:17:44 fastreid.evaluation.evaluator]: Start inference on 2238 images
[W pthreadpool-cpp.cc:90] Warning: Leaking Caffe2 thread-pool after fork. (function pthreadpool)
[W pthreadpool-cpp.cc:90] Warning: Leaking Caffe2 thread-pool after fork. (function pthreadpool)
[W pthreadpool-cpp.cc:90] Warning: Leaking Caffe2 thread-pool after fork. (function pthreadpool)
[W pthreadpool-cpp.cc:90] Warning: Leaking Caffe2 thread-pool after fork. (function pthreadpool)
[05/06 02:17:48 fastreid.evaluation.evaluator]: Inference done 11/18. 0.1116 s / batch. ETA=0:00:01
[05/06 02:17:49 fastreid.evaluation.evaluator]: Total inference time: 0:00:02.479559 (0.190735 s / batch per device, on 1 devices)
[05/06 02:17:49 fastreid.evaluation.evaluator]: Total inference pure compute time: 0:00:01 (0.105859 s / batch per device, on 1 devices)
<class 'list'>
<class 'torch.Tensor'>
<class 'list'>
<class 'int'>
[05/06 02:17:50 fastreid.partialreid.dsr_evaluation]: Testing with DSR setting
[05/06 02:20:31 fastreid.engine.defaults]: Evaluation results for OccludedREID in csv format:
[05/06 02:20:31 fastreid.evaluation.testing]: Evaluation results in csv format:
Dataset Rank-1 Rank-5 Rank-10 mAP mINP
:------------- :--------- :--------- :---------- :------ :-------
OccludedREID 57.40 74.50 81.90 53.07 39.81
[05/06 02:20:31 fastreid.utils.checkpoint]: Saving checkpoint to projects/PartialReID/logs/test_partial/model_final.pth
[05/06 02:20:36 fastreid.utils.events]: eta: 0:00:00 epoch/iter: 119/7679 total_loss: 2.353 loss_cls: 1.177 loss_triplet: 0 loss_fore_cls: 1.177 loss_fore_triplet: 0 time: 0.5482 data_time: 0.0028 lr: 8.73e-07 max_mem: 20270M
[05/06 02:20:36 fastreid.engine.hooks]: Overall training speed: 7678 iterations in 1:10:09 (0.5483 s / it)
[05/06 02:20:36 fastreid.engine.hooks]: Total training time: 1:52:43 (0:42:33 on hooks)

This issue is stale because it has been open for 30 days with no activity.

This issue was closed because it has been inactive for 14 days since being marked as stale.