sahi
darknet
Our great sponsors
sahi | darknet | |
---|---|---|
11 | 62 | |
3,580 | 21,449 | |
4.7% | - | |
7.4 | 6.5 | |
2 days ago | about 1 month ago | |
Python | C | |
MIT License | GNU General Public License v3.0 or later |
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.
sahi
-
How to Detect Small Objects
An alternative to this is to leverage existing object detection, apply the model to patches or slices of fixed size in our image, and then stitch the results together. This is the idea behind Slicing-Aided Hyper Inference!
-
Small-Object Detection using YOLOv8
Hi All, I am trying to detect defects in the images using YOLOv8where some of the classes (defectType1, defectType2) have very small bounding boxes and some of them have large bounding boxes associated with the, (defectType3, defectType4). Also, real-time operation is desired (at least 5Hz on Jetson Xavier) What I have done till now: I am primarily trying to use the SAHI technique (Slicing Aided Hyper Inference)
-
Changing labels of default YOLOv5 model
I am using the default YOLOv5m6 model here with sahi/yolov5 library for my object detection project. I want to change just some of labels - for example when YOLO detects a human, I want it to label the human as "threat", not "person". Is there any way I can do it just changing some code, or I should train the model from scratch by just changing labels?
-
Which Azure service to host this ML model
I need to execute this model https://github.com/obss/sahi upon an HTTP request. I will need between 32GB and 128GB of RAM (depending on the request). Also, I will only receive this request once or twice a week (they are not predefined dates). Each process may take a few hours.
-
Library for chopping image in pieces for training
https://github.com/obss/sahi should do the job
-
Semantic Segmentation with 2048x1024 images
I think you have multiple options: why run inference on this large resolution? Why not run on 1024x512 or smaller. Use a smaller model which uses less memory, eg enet, erfnet, bisenet etc. Otherwise, patchbased inference is the way to go, there is a nice library, but also easy to implement yourself: https://github.com/obss/sahi
-
How to convert big TIF image to smaller jpgs
i have the EXACT thing ! the libs github!
-
Roboflow 100: A New Object Detection Benchmark
Good idea. I haven’t looked too closely yet at the “hard” datasets.
We originally considered “fixing” the labels on these datasets by hand, but ultimately decided that label error is one of the challenges “real world” datasets have that models should work to become more robust against. There is some selection bias in that we did make sure that the datasets we chose passed the eye test (in other words, it looked like the user spent a considerable amount of time annotating & a sample of the images looked like they labeled some object of interest).
For aerial images in particular my guess would be that these models suffer from the “small object problem”[1] where the subjects are tiny compared to the size of the image. Trying a sliding window based approach like SAHI[2] on them would probably produce much better results (at the expense of much lower inference speed).
[1] https://blog.roboflow.com/detect-small-objects/
[2] https://github.com/obss/sahi
-
Diffusion model for synthetc data generation
I am not very experienced, but do I understand that the problem is the size of the image? If so, have you heard of sahi
-
Which model is best for detecting small objects? Yolov3? MaskRCNN, Faster-RCNN?
Try slicing and yolov4. https://github.com/obss/sahi
darknet
-
Anybody building ML models in C++?
YoloV3/4 is C based if that counts: https://github.com/AlexeyAB/darknet
-
[D] Fixing the angle of Skewed Paintings, see comments
This is all well-known information, see any (and all!) previous discussions when YOLOv5 comes up. For details: https://github.com/AlexeyAB/darknet/issues/5920
- Viseron 2.0.0 - Self-hosted, local only NVR and AI Computer Vision software.
-
How do I train YOLO5 to detect small objects (arial imagery). something like 20-20 pixels or maybe little more? How do I increase resolution and apply augmentation and tiling? Or maybe the YOLO5 is not he best choice for that?
2) YOLOv5 is both slower and less precise than YOLOv4. Why use YOLOv5? Source: https://github.com/AlexeyAB/darknet/issues/5920
- Machine learning Library in C?
-
I just realized yolov5 is GPL-3
So my recommendation is you stuck with Darknet/YOLO and use v4 of YOLO. The Darknet framework license is definitely suitable for commercial use: https://github.com/AlexeyAB/darknet/blob/master/LICENSE
-
GPL vs MIT.
Still to long. Here's my favourite license: https://github.com/AlexeyAB/darknet/blob/master/LICENSE
-
I was excited about YOLOv7, so I built a sharable object detection application with VDP and Streamlit.
When YOLOv7 was out, I built a web app to test it against the classic YOLOv4 and shared it with my team, then deployed it online to share with the community.
-
Does reducing the number of classes on YOLOv5 make it faster at inference?
If you're worried about performance, you shouldn't be using YOLOv5 since it is slower (and less accurate!) than YOLOv4. Source: https://github.com/AlexeyAB/darknet/issues/5920
-
[D] DarkNet YOLOv4 with CUDA 11.7 in Windows?
I looked around online but I only found this post discussing a related issue, leading me to think there seems to be some sort of compatibility issue going on here. And I think this is the most recent version of the file I am trying to compile located on the exact same folder where my copy is and when I opened it it shows CUDA 11.1 in line 307.
What are some alternatives?
mmdetection - OpenMMLab Detection Toolbox and Benchmark
yolov5 - YOLOv5 🚀 in PyTorch > ONNX > CoreML > TFLite
PixelLib - Visit PixelLib's official documentation https://pixellib.readthedocs.io/en/latest/
tensorflow-yolov4-tflite - YOLOv4, YOLOv4-tiny, YOLOv3, YOLOv3-tiny Implemented in Tensorflow 2.0, Android. Convert YOLO v4 .weights tensorflow, tensorrt and tflite
mask-rcnn - Mask-RCNN training and prediction in MATLAB for Instance Segmentation
tensorflow-yolo-v3 - Implementation of YOLO v3 object detector in Tensorflow (TF-Slim)
awesome-tiny-object-detection - 🕶 A curated list of Tiny Object Detection papers and related resources.
efficientdet-pytorch - A PyTorch impl of EfficientDet faithful to the original Google impl w/ ported weights
fastdup - fastdup is a powerful free tool designed to rapidly extract valuable insights from your image & video datasets. Assisting you to increase your dataset images & labels quality and reduce your data operations costs at an unparalleled scale.
yolor - implementation of paper - You Only Learn One Representation: Unified Network for Multiple Tasks (https://arxiv.org/abs/2105.04206)
datumaro - Dataset Management Framework, a Python library and a CLI tool to build, analyze and manage Computer Vision datasets.
darknet_ros - YOLO ROS: Real-Time Object Detection for ROS