DeepLabCut
CenterNet
| DeepLabCut | CenterNet | |
|---|---|---|
| 12 | 6 | |
| 4,294 | 7,101 | |
| 1.5% | - | |
| 8.6 | 0.0 | |
| 5 days ago | about 1 year ago | |
| Python | Python | |
| GNU Lesser General Public License v3.0 only | MIT License |
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.
DeepLabCut
-
Landmark tracking / Pose estimation model training in TensorFlow :
Use DeepLabCut, I also strongly suggest that you should fund their work: https://github.com/DeepLabCut/DeepLabCut
-
DeepLabCut alternatives - leap, DeepPoseKit, APT, sleap, and anipose
6 projects | 15 Jul 2022
-
Help: Using CV to recognize angles and lines from a picture
DeepLabCut is also worth mentioning here
-
Backyard AI dog poop detector walkthrough
1 - Detecting the dog's body parts was the most difficult portion of this, and thankfully I stumbled upon DeepLabCut (https://github.com/DeepLabCut/DeepLabCut) which enables training a model to track a specific animal(s) posture. In the video, this is basically the dots that are overlayed on top of the dog, and follower her around. DeepLabCut is basically just saying that this is where it thinks it recognizes "spine" and "tail".
-
Built a dog poop detector for my backyard
I used https://github.com/DeepLabCut/DeepLabCut for the core dog tracking capability, then I wrote the code that analyzes the posture (output by the model, trained via DeepLabCut) of the dog.
I built a dog poop detector for my backyard using DeepLabCut (https://github.com/DeepLabCut/DeepLabCut) and some janky poop detection heuristics I wrote that processed on the detected posture of my dog, if it's in the frame of my security camera. If it detects my dog pooping, it will record the location in a CSV and draw all the locations on an up to date image of my backyard.
-
[P] Built a dog poop detector for my backyard
Also, check out DeepLabCut. My project wouldn't have been possible without it, and it's really cool: https://github.com/DeepLabCut/DeepLabCut
-
I want to create a pill counter using points instead of bounding boxes. What model should I train from?
Well you could try DeepLabCut - https://github.com/DeepLabCut/DeepLabCut
- DeepLabCut: Deep-learning based markerless pose estimation for all animals
- Can AI make 3d model using my 2d photos ?
CenterNet
-
Seeking AI Model to Predict the Center of an Object in Images
CenterNet comes to mind
-
[D] Cross Shape Artifact in Heatmap
Found relevant code at https://github.com/xingyizhou/CenterNet + all code implementations here
-
CUDA errors while trying to run CenterNet
I am trying the implement this paper https://github.com/xingyizhou/CenterNet
-
I want to create a pill counter using points instead of bounding boxes. What model should I train from?
Take a look at this centernet architecture.
-
Using PyTorch and NumPy? You're making a mistake
Yeah, I'd run into this 2 years ago and ended up also reporting an issue on the Centernet repo [1]
The solution I have in that repo adapts from the very helpful discussions in the original Pytorch issue [2]
I will admit that this is *very* easy to mess up as evidenced by the fact that examples in the official tutorials for Pytorch and other well known code-bases suffer from it. In the Pytorch training framework I've developed at work, we've implemented a custom `worker_init_fn` as outlined in [1] that is the default for all "trainer" instances who are responsible for instantiating DataLoaders in 99% of our training runs.
[1] https://github.com/xingyizhou/CenterNet/issues/233
[2] https://github.com/pytorch/pytorch/issues/5059
- [P] Using PyTorch + NumPy? A bug that plagues thousands of open-source ML projects.
What are some alternatives?
DeepPoseKit - a toolkit for pose estimation using deep learning
yolov5 - YOLOv5 🚀 in PyTorch > ONNX > CoreML > TFLite
mmdetection - OpenMMLab Detection Toolbox and Benchmark
lightweight-human-pose-estimation.pytorch - Fast and accurate human pose estimation in PyTorch. Contains implementation of "Real-time 2D Multi-Person Pose Estimation on CPU: Lightweight OpenPose" paper.
Pytorch - Tensors and Dynamic neural networks in Python with strong GPU acceleration
sleap - A deep learning framework for multi-animal pose tracking.
Kornia - Geometric Computer Vision Library for Spatial AI
OpenCV - Open Source Computer Vision Library
pose-tensorflow - Human Pose estimation with TensorFlow framework
Hekate-Toolbox - A toolbox for Hekate
tensorflow - An Open Source Machine Learning Framework for Everyone