Computer Vision
Detection, segmentation, OCR, and vision pipelines — production CV open source.
508 projects
See methodology for ranking rules; order uses public GitHub metrics within this scenario.
| Rank | Project | Stars | Forks | Updated | License |
|---|---|---|---|---|---|
| 461 |
CoreML-in-ARKit
Simple project to detect objects and display 3D labels above them in AR. This serves as a basic Template for an ARKit project to use CoreML. |
1.7K | 221 | 08/23/21 | MIT |
| 462 |
aster.pytorch
ASTER in Pytorch |
682 | 171 | 12/09/21 | MIT |
| 463 |
easy12306
Use machine learning algorithms to automatically recognize 12306 captchas. |
2.9K | 724 | 03/04/21 | Other |
| 464 |
self-attention-cv
Implementation of various self-attention mechanisms focused on computer vision. Ongoing repository. |
1.2K | 152 | 09/14/21 | MIT |
| 465 |
natural-language-youtube-search
Search inside YouTube videos using natural language |
935 | 70 | 10/15/21 | MIT |
| 466 |
vehicle_counting_tensorflow
:oncoming_automobile: "MORE THAN VEHICLE COUNTING!" This project provides prediction for speed, color and size of the vehicles with TensorFlow Object Counting API. |
928 | 362 | 09/11/21 | MIT |
| 467 |
fast-autoaugment
Official Implementation of 'Fast AutoAugment' in PyTorch. |
1.6K | 197 | 06/16/21 | MIT |
| 468 |
gandissect
Pytorch-based tools for visualizing and understanding the neurons of a GAN. https://gandissect.csail.mit.edu/ |
1.8K | 276 | 05/23/21 | MIT |
| 469 |
Realtime_Multi-Person_Pose_Estimation
Code repo for realtime multi-person pose estimation in CVPR'17 (Oral) |
5.1K | 1.4K | 03/21/20 | Other |
| 470 |
SRN-Deblur
Repository for Scale-recurrent Network for Deep Image Deblurring |
762 | 189 | 09/05/21 | MIT |
| 471 |
TimeSformer-pytorch
Implementation of TimeSformer from Facebook AI, a pure attention-based solution for video classification |
729 | 89 | 08/25/21 | MIT |
| 472 |
VisTR
[CVPR2021 Oral] End-to-End Video Instance Segmentation with Transformers |
758 | 97 | 07/15/21 | Apache-2.0 |
| 473 |
MobileNet-Yolo
MobileNetV2-YoloV3-Nano: 0.5BFlops 3MB HUAWEI P40: 6ms/img, YoloFace-500k:0.1Bflops 420KB:fire::fire::fire: |
1.7K | 278 | 02/06/21 | Other |
| 474 |
inat_comp
iNaturalist competition details |
810 | 113 | 05/26/21 | MIT |
| 475 |
GCNet
GCNet: Non-local Networks Meet Squeeze-Excitation Networks and Beyond |
1.2K | 165 | 02/16/21 | Apache-2.0 |
| 476 |
swin-transformer-pytorch
Implementation of the Swin Transformer in PyTorch. |
861 | 129 | 03/29/21 | MIT |
| 477 |
lemniscate.pytorch
Unsupervised Feature Learning via Non-parametric Instance Discrimination |
758 | 130 | 03/25/21 | Other |
| 478 |
lambda-networks
Implementation of LambdaNetworks, a new approach to image recognition that reaches SOTA with less compute |
1.5K | 155 | 11/18/20 | MIT |
| 479 |
mean-teacher
A state-of-the-art semi-supervised method for image recognition |
1.7K | 342 | 10/08/20 | Other |
| 480 |
quiver
Interactive convnet features visualization for Keras |
1.8K | 224 | 09/04/20 | MIT |