-
Thanks for this code. Where is the RGBNT201 dataset? In the home page of https://aihuazheng.github.io/publications/. The following link of the CODE is linked to this website. However, this link is for…
-
请问可否分享除ViT-B之外其他模块的预训练权重
-
Thank you for your great work.
I have a question, what is the difference between RGBNT201 and RGBNT201-C in your dataset?
Thank you~
-
Traceback (most recent call last):
File "/home/tiancun/EDITOR/modeling/backbones/vit_pytorch.py", line 666, in load_param
self.state_dict()[k].copy_(v)
KeyError: 'state_dict_ema'
During ha…
-
，作者你好，这个loss值为什么会变成nan呀，然后后续就没法训练了
2023-12-20 20:47:31,494 TOPReID.train INFO: Epoch[5] Iteration[220/467] Loss: 12.059, Acc: 0.090, Base Lr: 4.54e-03
2023-12-20 20:47:34,031 TOPReID.train INFO: Epo…
-
Hi @924973292 thanks for the repo and codes. Is it possible to upload the checkpoints of the best performing models for downoad, please?
-
-
Hi, thansk for your excellent works for nighttime ReID.
Would you please release codes for evaluation on datasets Knight / Night600 / RGBNT201_rgb / Syn_Dark, and your methods IDF (TMM2023) and CEN…
-
Nice work!
I wonder the performance of UniCat with the stride of [16,16] and w/o the additional "RandomGrayscalePatchReplacement"(compared to TransReID), could you release the result?
Thanks a lot!
-
I'm just new training different losses and try with --sphere. But it turn like this.
Before try --sphere, other losses worked! (circle, contrast, triplet)
`!python /content/vision/Person_reID_bas…
culxe updated
4 months ago