-
The link you offered for MSMT17 downloading is invalid, could you please upload it again, thanks a lot.
-
很棒的工作！但是我在近期复现此工作时，在msmt17上，有关map只有28%，无法达到论文所给的33%，相关实验设置，按照按照默认，如下，数据集为本项目所给链接下载，请问是什么原因呢：
CUDA_VISIBLE_DEVICES=0,1,2,3 python examples/cluster_contrast_train_usl.py -b 256 -a resnet50 -d msmt17 --…
-
Thanks for your code. I managed to reproduce the results for Market, Duke and CUHK03. However, I tried to add CUHK-SYSU and MSMT17 into argument --test_dataset, which could not give results mentioned…
-
Hello, I have a question, the performance of SpCL+ or MMT+ on DukeMTMC-reID -> MSMT17 and Market-1501 -> MSMT17, have you made these experimental settings?
Look forward to your reply. Thank you ve…
-
Hi! I want to train the resnet50 on MSMT17 data set but i am unable to understand the preparation process. In your read me file, it says "for MSMT17, there are more than 10 cameras. You need to modif…
-
Could you shared with the generated 3D data of the duke and msmt17 datasets? Thank you.
-
你好，作者，不知道代码里面加载数据集的list_train.txt这些TXＴ文件可以发布一下吗？按照您的执行预训练的步骤，我不理解ln -s [PATH TO MSMT17_V1] ./data/MSMT17_V1这个命令，数据集需要自己下载？？
-
当我使用以下代码导出时报错：
`import torchreid
from torch.autograd import Variable
import torch
import onnx
input_name = ['input']
output_name = ['output']
model = torch.load('osnet_x1_0_msmt17_256x128_ams…
-
使用http://idstcv.oss-cn-zhangjiakou.aliyuncs.com/Ada-NETS/MSMT17/msmt17_feature_label.zip给出的数据集跑不出论文中的结果
top改为40的时候bcubed: ave_pre: 0.8325, ave_rec: 0.6552, fscore: 0.7333, cluster_num: 15176
top改为80…
-
直接改了tt参数每次评估都报错
ValueError: Input contains NaN, infinity or a value too large for dtype('float32').