WZMIAOMIAO/CLIPJupyter Notebook
CLIP (Contrastive Language-Image Pretraining), Predict the most relevant text snippet given an image
(3 stars) (1 fork) (0 件の索引済み issue) (0 件のオープンな good first issue)
リポジトリ
CLIP (Contrastive Language-Image Pretraining), Predict the most relevant text snippet given an image
Awesome multilingual OCR toolkits based on PaddlePaddle (practical ultra lightweight OCR system, support 80+ languages recognition, provide data annotation and synthesis tools, support training and deployment among server, mobile, embedded and IoT devices)
deep learning for image processing including classification and object-detection etc.
A latent text-to-image diffusion model
Datasets, Transforms and Models specific to Computer Vision