AT38875

NA

Pinned Repositories

Count-Anything
This method uses Segment Anything and CLIP to ground and count any object that matches a custom text prompt, without requiring any point or box annotation.
Language:Python00
SAM-finetune
Finetune SegmentAnything for Road Segmentation
Language:Python00
Segment-Any-Anomaly
Official implementation of "Segment Any Anomaly without Training via Hybrid Prompt Regularization (SAA+)".
Language:Jupyter Notebook711 10 3275
MobileSAM
This is the official code for MobileSAM project that makes SAM lightweight for mobile applications and beyond!
Language:Jupyter Notebook4.7k 44 123481
LearningToCountEverything
Language:Python358 13 4572
face-emotion-recognition
Efficient face emotion recognition in photos and videos
Language:Jupyter Notebook483 9 44109
ultralytics
NEW - YOLOv8 🚀 in PyTorch > ONNX > OpenVINO > CoreML > TFLite
Language:Python28.4k 157 8.7k5.6k
Count-Anything
This method uses Segment Anything and CLIP to ground and count any object that matches a custom text prompt, without requiring any point or box annotation.
Language:Python127 3 516

AT38875's Repositories

AT38875/Count-Anything
This method uses Segment Anything and CLIP to ground and count any object that matches a custom text prompt, without requiring any point or box annotation.
Language:Python00
AT38875/SAM-finetune
Finetune SegmentAnything for Road Segmentation
Language:Python00