DETReg
yolov5
Our great sponsors
| DETReg | yolov5 | |
|---|---|---|
| 1 | 65 | |
| 235 | 26,386 | |
| - | 8.9% | |
| 6.3 | 9.8 | |
| 25 days ago | 5 days ago | |
| Python | Python | |
| Apache License 2.0 | GNU General Public License v3.0 only |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
DETReg
-
Researchers From Tel Aviv University, UC Berkeley and NVIDIA Introduce ‘DETReg’, A Novel Unsupervised AI For Object Detection
Codes: https://github.com/amirbar/DETReg
yolov5
-
How to run detect.py of yolov5 without cmd?
See https://github.com/ultralytics/yolov5/issues/36
-
Yolo and overfitting, which graph is leading ?
The following issue at GitHub asks which graph to use for inspecting overfitting. https://github.com/ultralytics/yolov5/issues/5061 . Indeed, in this example one can see that for val/box_loss there is still room to improve, however val/obj_loss reached a plateau and the minimum loss is at around 40 epochs. Unfortunately, reading this GitHub issue the answer is not straightforward and so I was wondering if there are any rules.
- How to train yolov5 model with german traffic sign recognition dataset?
-
Detecting HAZMAT Placards on Trucks - Running On SPOT Robot
Install YOLOv5 from https://github.com/ultralytics/yolov5 and follow the excellent notes and documentation to point it at those images/labels.
-
How to do meaningful work as an independent researcher? [Discussion]
4 years ago I'd never done any AI. Now I've written YOLOv5.
- PyTorch: Understanding detach and the effect of in-place operations
-
bike classification advice sought for used bike aggregator
yolov5 GitHub
-
Object detection and batch size
The only reference I found is https://github.com/ultralytics/yolov5/issues/2377 where no real difference is found as a result of batch_size [16, 20, 32, 40, 64, 80, 96, 128].
-
Classify a person image is full body or not
I 'm using ultralytics 's yolov5 to detect and track people in video. To feed the next model, I want to pass the cropped images with full body. But there are some detected people consist of upper body. Can anyone give me some idea to discard non full body images?
-
Yolo annotated dataset to custom Dataloader
https://github.com/ultralytics/yolov5/blob/master/utils/datasets.py line 555
What are some alternatives?
darknet - YOLOv4 / Scaled-YOLOv4 / YOLO - Neural Networks for Object Detection (Windows and Linux version of Darknet )
yolor - implementation of paper - You Only Learn One Representation: Unified Network for Multiple Tasks (https://arxiv.org/abs/2105.04206)
detectron2 - Detectron2 is a platform for object detection, segmentation and other visual recognition tasks.
Deep-SORT-YOLOv4 - People detection and optional tracking with Tensorflow backend.
mmdetection - OpenMMLab Detection Toolbox and Benchmark
edge-tpu-tiny-yolo - Run Tiny YOLO-v3 on Google's Edge TPU USB Accelerator.
Mask-Detection-YOLOv3 - Mask Detection with YOLOv3.
yolo-tensorrt - TensorRT8.Support Yolov5n,s,m,l,x .darknet -> tensorrt. Yolov4 Yolov3 use raw darknet *.weights and *.cfg fils. If the wrapper is useful to you,please Star it.
OpenCV - Open Source Computer Vision Library
yolov3 - YOLOv3 in PyTorch > ONNX > CoreML > TFLite
gocv - Go package for computer vision using OpenCV 4 and beyond.
CenterNet - Object detection, 3D detection, and pose estimation using center point detection: