meakbiyik / torchcache
Cache PyTorch module outputs on-the-fly
☆35Updated 3 weeks ago
Related projects: ⓘ
- Timm model explorer☆36Updated 5 months ago
- [CVPR 2023 Highlight] Beyond mAP: Towards better evaluation of instance segmentation☆26Updated last year
- [NeurIPS 2023] HASSOD: Hierarchical Adaptive Self-Supervised Object Detection☆47Updated 7 months ago
- ☆29Updated 2 weeks ago
- Simplify Your Visual Data Ops. Find and visualize issues with your computer vision datasets such as duplicates, anomalies, data leakage, …☆65Updated 11 months ago
- Repo for event-based binary image reconstruction.☆30Updated 6 months ago
- Repository for the paper: "TiC-CLIP: Continual Training of CLIP Models".☆90Updated 3 months ago
- ☆55Updated 3 months ago
- Efficient parallelizable algorithms for multidimensional arrays to speed up your data pipelines☆21Updated last month
- ☆131Updated last year
- Tracking through Containers and Occluders in the Wild (CVPR 2023) - Official Implementation☆39Updated 3 months ago
- The official repository of the RePoGen paper☆44Updated 2 months ago
- Muggled SAM: Segmentation without the magic☆31Updated last week
- Implementation of MaMMUT, a simple vision-encoder text-decoder architecture for multimodal tasks from Google, in Pytorch☆97Updated 11 months ago
- [CVPR 2022] WALT: Watch And Learn 2D amodal representation from Time-lapse imagery☆57Updated 2 years ago
- Occlusion Copy & Paste augmentation for Occluded Instance Segmentation☆19Updated last year
- Implementing DropPath/StochasticDepth in PyTorch☆16Updated 2 years ago
- Object Recognition as Next Token Prediction (CVPR 2024)☆153Updated 2 months ago
- Dataset and Code for the paper "AutoSoccerPose: Automated 3D posture Analysis of Soccer Shot Movements"☆29Updated 3 months ago
- Implementation of VisionLLaMA from the paper: "VisionLLaMA: A Unified LLaMA Interface for Vision Tasks" in PyTorch and Zeta☆15Updated last week
- Use Segment Anything 2, grounded with Florence-2, to auto-label data for use in training vision models.☆80Updated last month
- Official implementation of "Active Image Indexing"☆58Updated last year
- EdgeSAM model for use with Autodistill.☆24Updated 3 months ago
- ☆175Updated 11 months ago
- SAM-CLIP module for use with Autodistill.☆12Updated 10 months ago
- SAM Annotaton Tool☆27Updated 2 months ago
- Conversions between kornia and other computer vision libraries formats☆33Updated 11 months ago
- Just some miscellaneous utility functions / decorators / modules related to Pytorch and Accelerate to help speed up implementation of new…☆115Updated last month
- A Platform for Visual Learning from Human Feedback☆77Updated 5 months ago
- Pixel Parsing. A reproduction of OCR-free end-to-end document understanding models with open data☆12Updated last month