openai CLIP issues - Githubissues

openai / CLIP

CLIP (Contrastive Language-Image Pretraining), Predict the most relevant text snippet given an image

MIT License

26.19k stars 3.35k forks source link

issues

Newest

Newest Most commented Recently updated Oldest Least commented Least recently updated

Question / Confirmation on arange in encode_text

#371 AwePhD closed 1 year ago
2
download weights manually

#370 lucasjinreal opened 1 year ago
0
5. Data Overlap Analysis

#369 constanceferragu opened 1 year ago
0
Remove unused variables 'text_features' and 'image_features'

#368 developer0hye closed 1 year ago
1
openai/clip-vit-large-patch14 cannot be traced with torch_tensorrt.compile

#367 kct22aws opened 1 year ago
1
Using clip.load("ViT-L/14", device=device) Failed to load

#366 Blessing92 opened 1 year ago
5
CLIP backbone make my laptop strange noises，what the hell are you doing?

#365 jcyhcs closed 1 year ago
0
Is there any way to use the Clip model in the Java technology stack?

#364 zhangjh closed 1 year ago
2
Question: How to produce a correct embedding for a dataset?

#363 GaetanoDibenedetto opened 1 year ago
1
CLIP - No progression in Training

#362 TEnsorTHiru opened 1 year ago
3
YFCC100M Embeddings Location

#360 iamsabhoho opened 1 year ago
0
A new Idea

#359 PozitronikTech opened 1 year ago
0
ImportError: .../python3.10/site-packages/torch/lib/libtorch_cuda.so: undefined symbol: cudaGraphDebugDotPrint, version libcudart.so.11.0

#358 Bailey-24 opened 1 year ago
1
执行p = ( pipe.input('path') .map('path', 'img', ops.image_decode.cv2('rgb')) .map('img', 'vec', ops.image_text_embedding.clip(model_name='clip_vit_base_patch16', modality='image')) .map('vec', 'vec', lambda x: x / np.linalg.norm(x)) .output('img', 'vec') ) DataCollection(p('./teddy.png')).show() 报以下错误，请问是什么原因，该如何解决

#357 JN0925 opened 1 year ago
1
Laion embeddings and clip output for the same image do not match exactly

#356 stevebottos opened 1 year ago
4
Pytorch versions

#355 Crestina2001 closed 1 year ago
0
Problems encountered when calling `clip_model.train()`

#354 JWargrave opened 1 year ago
0
Linear probe pre or post-projection?

#353 DianeBouchacourt opened 1 year ago
0
Improve the Speed in Batch Processing

#352 ahmadmustafaanis opened 1 year ago
3
does it has c++ version for tokenizer?

#351 susht3 opened 1 year ago
0
how to load checkpoint trained using openclip codebase

#350 lezhang7 opened 1 year ago
1
pip install git+https://github.com/openai/CLIP.git

#349 Zianye opened 1 year ago
0
where is the files located?

#348 jwolf25 opened 1 year ago
0
RuntimeError: The size of tensor a (768) must match the size of tensor b (7) at non-singleton dimension 2.

#347 sankyde opened 1 year ago
1
Reproducing results in table 11

#346 AnhLee081198 opened 1 year ago
1
Reproducing Zeroshot results in Table 11.

#345 AnhLee081198 opened 1 year ago
0
Input Negative Examples

#344 cucumberguagua opened 1 year ago
7
Possible inconsistencies arising from the pattern matching of CLIP tokenizer

#343 Mypathissional opened 1 year ago
0
ResourceWarning: unclosed file

#342 ibuda opened 1 year ago
0
RN50x16, RN50x4, ViT-B/32 output nan

#340 tojiboyevf opened 1 year ago
0
How could I only use image encoder to do classification task after fine tuning the entire CLIP.

#339 lr19960813 opened 1 year ago
1
Model has been downloaded but the SHA256 checksum does not not match

#338 trltzy opened 1 year ago
4
Added mps

#337 CGCooke opened 1 year ago
3
Any Google Colab Notebook for calculating image similarity of given 2 images?

#336 FurkanGozukara opened 1 year ago
0
preprocess _transfrom function

#335 sherlock666 opened 1 year ago
1
Using CLIP in transfer learning for multilabel classification

#334 EachOneChew closed 11 months ago
8
Pytorch 1.7 contains vulnerability that is fixed in upgraded version

#333 cprocak3 opened 1 year ago
1
How to add the scheduler to the Model CLIP?

#332 APiaoG closed 1 year ago
3
Causal mask

#331 kimihailv opened 1 year ago
0
How can I reduce dimension of image feature by encode_image?

#330 sdalinluo opened 1 year ago
6
'clip' has no attribute 'load'

#329 nitrocon opened 1 year ago
4
visual feature translation question

#328 wuyou111 opened 1 year ago
0
Release a new pypi build with looser dependency locking

#327 bswami50 closed 1 year ago
2
Update README.md

#326 jongwook closed 1 year ago
0
Number of dims don't match in permute

#325 shantanu778 opened 1 year ago
3
Not able to install following instructions on main page.

#324 teslashark opened 1 year ago
1
Getting overfitted CLIP model while fine-tuning with a large training dataset

#323 antu-saha opened 1 year ago
4
Question about simple_tokenizer.

#322 Mypathissional opened 1 year ago
0
CLIP model training using custom dataset.

#321 imostafizur closed 1 year ago
1
what format were the images used for training?

#320 jn2clark opened 1 year ago
0

Previous Next