kitware / coat Goto Github PK

I can find the OIM loss, but not the ID loss. This question is caused by the Section 3.3 and the Equation 4 in your paper.

here I only find how to change the gallery_size, but I
don't know how to use the Occlusion and Resolution on CUHK dataset, Have you done research in this area, or can you give me some advice? Thank you very much for your help!

your code:
box_head = TransformerHead(
cfg=cfg,
trans_names=cfg.MODEL.TRANSFORMER.NAMES_1ST,
kernel_size=cfg.MODEL.TRANSFORMER.KERNEL_SIZE_1ST,
use_feature_mask=cfg.MODEL.TRANSFORMER.USE_MASK_1ST,
)
box_head_2nd = TransformerHead(
cfg=cfg,
trans_names=cfg.MODEL.TRANSFORMER.NAMES_2ND,
kernel_size=cfg.MODEL.TRANSFORMER.KERNEL_SIZE_2ND,
use_feature_mask=cfg.MODEL.TRANSFORMER.USE_MASK_2ND,
)
box_head_3rd = TransformerHead(
cfg=cfg,
trans_names=cfg.MODEL.TRANSFORMER.NAMES_3RD,
kernel_size=cfg.MODEL.TRANSFORMER.KERNEL_SIZE_3RD,
use_feature_mask=cfg.MODEL.TRANSFORMER.USE_MASK_3RD,
)
definition: box_head box_head_2nd box_head_3rd
then:
box_features = self.roi_heads.box_roi_pool(features, boxes, images.image_sizes) #MultiScaleRoIAlign
box_features_2nd = self.roi_heads.box_head_2nd(box_features)
embeddings_2nd, _ = self.roi_heads.embedding_head_2nd(box_features_2nd) #NormAwareEmbedding
box_features_3rd = self.roi_heads.box_head_3rd(box_features) #box_features
embeddings_3rd, _ = self.roi_heads.embedding_head_3rd(box_features_3rd)

I wonder why this place doesn't have the first TransformerHead?But what is drawn in Figure 2 is to go through the first TransformerHead.

Could you supply the numbers used to generate the CUHK-SYSU Gallery Size plot (Figure 6 in the paper)?

Dear Author,

I found your work very interesting. I find minor typo mistakes in your code in transformer.py. Please cross-check from lines 173 to 193.
Here are changes that may be required:
1)-change feature_aug_type to self.feature_aug_type
2)-indent error from line 187 to 193.

I tried to draw the style of display as shown in Figure 4, but I failed, which bothered me for several days. I hope to get your help, thank you very much！

hello:
python train.py --cfg ./logs/prw_coat/config.yaml --eval --ckpt ./logs/prw_coat/prw_COAT.pth

When I entered this line of command during the test phase, this error was displayed, that is, in the file trnasform.py, the size of the convolution kernel is not defined? But I see that it has been defined in the code, and I don’t know what the problem is. looking forward to your reply.

(coat) zqx_tesla@tesla-v100:~/home/zqx_tesla/PersonReID/PersonReID2/COAT-main$ python train.py --cfg ./logs/prw_coat/config.yaml --eval --ckpt ./logs/prw_coat/prw_COAT.pth
Creating model...
Traceback (most recent call last):
File "train.py", line 186, in
main(args)
File "train.py", line 35, in main
model = COAT(cfg)
File "/home/zqx_tesla/home/zqx_tesla/PersonReID/PersonReID2/COAT-main/models/coat.py", line 53, in init
box_head = TransformerHead(
File "/home/zqx_tesla/home/zqx_tesla/PersonReID/PersonReID2/COAT-main/models/transformer.py", line 40, in init
self.transformer_encoder = Transformers(
File "/home/zqx_tesla/home/zqx_tesla/PersonReID/PersonReID2/COAT-main/models/transformer.py", line 102, in init
raise ValueError('Undefined kernel size.')
ValueError: Undefined kernel size.

论文中 这个地方应该是 在等式1中
d=1

Dear Author:
I wanna reproduce the performance of COAT on the multi-view gallery of PRW in Table 4 of your paper. However, I have no idea about how to do. Could you give me some advices? Thx a lot.

Dear authors,
I found your paper very interesting.
I was trying to reproduce your results over CUHK-SYSU dataset but failed. However, I can successfully reproduce results over PRW dataset. I request you to please help me in this regard.
On CYHK-SYSU dataset, I got mAP = 93.34%
top- 1 = 94.00%.

Thank you.