-
Hi,I want to replace the resnet50 with other networks,but every time I switch to the source code for another network, the program runs up a lot of memory after it shows" create dataloader for Training…
-
UserWarning: The pretrained weights "./log/old_MOT/hacnn_ibn_b_global+local_mot_person_softmax/model.pth.tar-150" cannot be loaded, please check the key names manually (** ignored and continue **)
…
-
Hi,
I am trying to run the project with Duke dataset, However when dataloader for test starts and it begins to load the dataset , the memory usage increases rapidly and it runs out of memory.
…
-
Hi, sorry for bothering you. I have two minor questions for the re-id part.
1. in the /src/train/mot/py, line 64,
if opt.id_weight > 0:
id_head = _tranp…
-
The current lable returned are not available on softmax training, and I wonder if you can provide some tips or code that are related to classify using CrossEntrophyLoss() and softmax. Also, the paper …
-
您好，在这个项目底下似乎没有找到论文《Spatial and Temporal Mutual Promotion for Video-based Person Re-identification》所对RRU和STIM所对应的代码，另一个项目https://github.com/yolomax/rru-reid 也是不完整的，请问有没有整合进来相关的代码，谢谢~
-
prid2011 can be supported?
-
Do you have any suggestions to run the strongerbasline? Currently I am using the default params in configs/Market1501/sbs_R50.yml for training and the loss is extremely large. The test accuracy is als…
-
On running the command python baseline.py -b 64 -j 4 -d market1501 -a resnet50 --combine-trainval --lr 0.01 --epochs 100 --step-size 40 --eval-step 5
I am getting the above said error. I am pasting…
-
Would you share the OSNet config file without ImageNet pretrained to me? Thanks!