wusize CLIPSelf issues - Githubissues

wusize / CLIPSelf

[ICLR2024 Spotlight] Code Release of CLIPSelf: Vision Transformer Distills Itself for Open-Vocabulary Dense Prediction

https://arxiv.org/abs/2310.01403

Other

170 stars 9 forks source link

issues

Newest

Newest Most commented Recently updated Oldest Least commented Least recently updated

Train F-ViT on LVIS v1 Dataset.

#33 zhangyupeng123 closed 1 month ago
9
Google Drive Link

#32 nobeldang opened 1 month ago
1
The implementation of extract_roi_features_v1 in timm_model.py different from paper

#31 vietluong2110 opened 2 months ago
0
Inquiry Regarding Resolution Choice in OV-COCO ViT-B16 Experiment

#30 xiaomoguhz opened 2 months ago
0
Google Drive links have expired

#29 xiaomoguhz closed 2 months ago
4
Unable to Reproduce Results from Table 2

#28 lyhisme opened 3 months ago
0
OV-LVIS Training Log

#27 JiamingLv opened 3 months ago
0
Could you advise me on your ODISE inference settings?

#26 juanyeo opened 3 months ago
0
Would you share openai ViT-L weights trained by CLIPSelf?

#25 jw00oo1 opened 4 months ago
2
The model and loaded state dict do not match exactly

#24 WangZz777 closed 5 months ago
0
why class_weight is uneven between categories in F-ViT？

#23 Bilibilee closed 5 months ago
1
How to train on custom dataset with ground truth masks?

#22 Irennnne opened 6 months ago
0
inference time

#21 eternaldolphin opened 6 months ago
1
Problem happend when perform "test_eva_vitb16_macc_boxes_masks.sh "

#20 JuanJia closed 7 months ago
2
How to get CLIPSelf Checkpoints?

#19 meilijunxi closed 7 months ago
0
Could you provide the K-Means Visualization code?

#18 SuleBai closed 7 months ago
2
ValueError: assignment destination is read-only

#17 SuleBai opened 7 months ago
3
RuntimeError: Pretrained weights (checkpoints) not found for model EVA02-CLIP-B-16.Available pretrained tags (['eva', 'eva02', 'eva_clip', 'eva02_clip'].

#16 cpy0029 opened 8 months ago
1
Is it intentional or a mistake that coco_proposals.json and coco_pseudo_4764.json are completely identical.

#15 Bilibilee opened 8 months ago
7
question about the results in the paper

#14 jayaylee2 closed 8 months ago
2
Config files for F-ViT from OpenAI-CLIP

#13 yhosoya66 opened 8 months ago
2
Visualization of image segmentation

#12 cjm178 closed 8 months ago
0
performance of Zero-shot Classification and Zero-shot Cross-Modal Retrieval

#11 hamigualisingl opened 8 months ago
9
Environmental problem

#10 zhangyupeng123 opened 9 months ago
12
Providing Scripts and Checkpoints for training on CC3M

#9 ORippler opened 9 months ago
1
Generating text embedding files

#8 yhosoya66 closed 9 months ago
2
Request for Window Attention Weights and Code as Referenced in Table 7

#7 cilinyan closed 9 months ago
3
Error about the dataset-type: invalid choice: 'grid_distill'

#6 wxqlab opened 9 months ago
1
Can the Lvis_v1 dataset be evaluated？

#5 Xianqiao-Cai closed 9 months ago
0
CAT-Seg's training setting

#4 BuRr-Lee opened 1 year ago
3
What are the compute resources required for this?

#3 yxchng opened 1 year ago
4
Can you provide the VIT/B 16 weights trained by CLIPself on the COCO dataset using Open AI clip?

#2 winnerwu6 closed 1 year ago
2
the Mean Accuracy in table1 means evaluation of ovcoco(65) or coco(80)?

#1 eternaldolphin opened 1 year ago
2