bes-dev/pytorch_clip_bbox
Pytorch based library to rank predicted bounding boxes using text/image user's prompts.
This library helps refine object detection results to find very specific items. You provide an image with detected objects and a text description (like "red cup" instead of just "cup") or an example image. It then helps you pinpoint the exact object you're looking for, making your detection more precise. This is for machine learning engineers and computer vision scientists who build and deploy object detection systems.
No commits in the last 6 months.
Use this if you need to find highly specific objects within an image using natural language descriptions or example images, going beyond the general categories your object detector was originally trained on.
Not ideal if your existing object detection model already provides sufficient specificity for your needs without further refinement.
Stars
52
Forks
4
Language
Python
License
Apache-2.0
Category
Last pushed
Dec 25, 2021
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/bes-dev/pytorch_clip_bbox"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
mlfoundations/open_clip
An open source implementation of CLIP.
noxdafox/clipspy
Python CFFI bindings for the 'C' Language Integrated Production System CLIPS
openai/CLIP
CLIP (Contrastive Language-Image Pretraining), Predict the most relevant text snippet given an image
moein-shariatnia/OpenAI-CLIP
Simple implementation of OpenAI CLIP model in PyTorch.
BioMedIA-MBZUAI/FetalCLIP
Official repository of FetalCLIP: A Visual-Language Foundation Model for Fetal Ultrasound Image Analysis