fast-reid

fast-reid copied to clipboard

训练过程中，内存一直增长，到后期会把整个服务器的内存都占完

14

``` ys.platform linux Python 3.9.7 (default, Sep 16 2021, 13:09:58) [GCC 7.5.0] numpy 1.22.4 fastreid 1.3 @/ssd8/exec/jiaruoran/python/fast-reid-master/./fastreid FASTREID_ENV_MODULE PyTorch 1.7.1+cu101 @/ssd7/exec/jiaruoran/anaconda3/lib/python3.9/site-packages/torch PyTorch debug build False GPU available True GPU 0,1,2,3...

rrjia

训练过程中，内存一直增长，到后期会把整个服务器的内存都占完，初步分析将上述两个增强关闭后，内存使用会正常，具体是因为哪个方法，因为哪个实现有问题，暂时还没有时间分析

rrjia

rrjia

请问一下MODEL ZOO里提供的MSMT17数据集的训练权重是基于V1训练的还是V2训练的？

lanyufei

add RGPR data augmentation for person reid

2

Add RGPR data augmentation for person reid(An Effective Data Augmentation for person re-identification(https://arxiv.org/abs/2101.08533)) mgn_repvgg_wo_RGPR(epoch 60): rank1: 90.44, mAP: 81.56 mgn_repvgg_w_RGPR(epoch 60): rank1: 90.66, mAP: 82.16 mgn_repvgg_w_RGPR(epoch 120): rank1: 91.07, mAP:...

AlphaPlusTT

optimize jaccard distance computation and the ranking

1

- I run a line_profiler on the ranking function and discovered that the line I modified takes 91.4 of the run time of the rank function. By modifying we can...

MarahGamdou

Add the code for GPU-Reranking

1

Hi, Xingyu! I integrate the re-ranking into fast-reid. As suggested, the modified code can make users use the GPU-reranking by changing config. I have tested the code in Market1501 with...

Xuanmeng-Zhang

Update visualize_result.py

1

update for error: `TypeError: can't convert cuda:0 device type tensor to numpy. Use Tensor.cpu() to copy the tensor to host memory first.`

xugaoxiang

This is the result if `--actmap` is added when run `python3 demo/visualize_result.py` 

TelBotDev

The value will be treated as `str` if there is no type. Then there will be error ``` Traceback (most recent call last):   File "demo/visualize_result.py", line 144, in     query_indices =...

TelBotDev