GitHub - debryu/Visual-Grounding: Given a prompt, recognize and locate the object described in the prompt. The model uses CLIP as backbone and then a custom convolutional module for refinement.

debryu / Visual-Grounding Public

Notifications You must be signed in to change notification settings
Fork 0
Star 0

Given a prompt, recognize and locate the object described in the prompt. The model uses CLIP as backbone and then a custom convolutional module for refinement.

0 stars 0 forks Branches Tags Activity

Star

Notifications

Branches Tags

Name		Name	Last commit message	Last commit date
Latest commit History 24 Commits
Graph		Graph
Project		Project
.DS_Store		.DS_Store
ClipPreproc.py		ClipPreproc.py
Model.py		Model.py
dataprep.py		dataprep.py
heatmap.py		heatmap.py

About

Given a prompt, recognize and locate the object described in the prompt. The model uses CLIP as backbone and then a custom convolutional module for refinement.

cv pytorch resnet deeplearning computervision

Activity

0 stars

1 watching

0 forks

Report repository