zpy
detectron2
zpy | detectron2 | |
---|---|---|
9 | 49 | |
288 | 28,856 | |
0.0% | 1.6% | |
0.0 | 7.6 | |
over 2 years ago | 7 days ago | |
Python | Python | |
GNU General Public License v3.0 only | Apache License 2.0 |
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.
zpy
-
Help finding a model that can identify small cubes
This is actually a great problem for synthetic data. You can make a synthetic dataset of colored cubes on different backgrounds using something like Unity or zpy (shameless plug). The synthetic data will be much larger and more varied than one you create & label by hand.
-
Why isn't this technology used more for AI projects?
I'm sort of in the same boat. I just discovered this very interesting package called zpy that's meant to help automate turning synthetic conditions into training data. I have some experience with Python and am fairly new to Blender, but I could probably get as far as making a good segmented dataset.
-
Why Blender Is the Best Software for the 3D Workflow
Thanks for getting this far! If you’re interested in 3D and what it can do for synthetic data, check out our open-source data development toolkit zpy. Everything you need to generate and iterate synthetic data for computer vision is available for free. Your feedback, commits, and feature requests are invaluable as we continue to build a more robust set of tools for generating synthetic data. In the meantime, if you need our support with a particularly tricky problem, please reach out.
-
Discussion on Medium
I work at Zumo Labs, where we create synthetic data for computer vision using zpy (github.com/ZumoLabs/zpy).
-
How to 3D Scan an Object for Synthetic Data
The easiest way to get started with zpy (available on GitHub) is to follow the steps outlined in this short video tutorial series.
-
Use Python and Blender to Make More Dynamic Training Data
Tools that make synthetic data generation easy are fundamentally changing the way machine learning work is done. Iterating and improving the dataset over the course of a project is more important to project success than iterating the model architecture. That's why we are releasing zpy, an open source synthetic data toolkit. All developers should have the option of working with dynamic data rather than static data.
-
[P] Synthetic Data for CV with Python and Blender
https://github.com/ZumoLabs/zpy We just released our open source synthetic data toolkit built on top of Blender. Our package makes it easy to design and generate synthetic data for computer vision projects. Let us know what you think and what features you want us to focus on next!
https://github.com/ZumoLabs/zpy We just released our open source synthetic data toolkit built on top of Blender. Our package makes it easy to design and generate synthetic data for computer vision projects. Let us know what you think and what features you want us to focus on next!
- Using Blender for Computer Vision
detectron2
-
Ask HN: How to train an image recognition AI
I don’t do AI professionally but as a hobby, so this may not be the best way. But the way you described, it seems the user maybe taking the picture a bit further away and there may be other objects in the frame. So you may want to look into some sort of segmentation or have bounding box. This could help the user make sure they are looking at documents for the correct machine.
I think something like detectron2 [1] could help. It is Apache2 license, so commercial friendly. That said the pre-trained weights may not be used for commercial purposes, so you’ll want to check on that.
[1] https://github.com/facebookresearch/detectron2
-
Instance segmentation of small objects in grainy drone imagery
And not enough true positives either. Add more augmentations in the config. Also make sure the config is set correctly, so that Detectron2 isn't skipping background images: https://github.com/facebookresearch/detectron2/issues/80
- Openpose alternatives (humanSD & Densepose)
-
Probelms with importing tensormask from detectron2.projects
I followed the setup of https://github.com/facebookresearch/detectron2/tree/main/projects/TensorMask. But still I can not import it. As I can with from detectron2.projects import point_rend easily from PointRend projects
-
Problems with Lazy Config detectron2 (MViTv2)
I have to use this config file with the dataloader which is in https://github.com/facebookresearch/detectron2/blob/main/projects/MViTv2/configs/common/coco_loader.py. I figured that i can use cfg.dataloader.train.dataset.names = "my_dataset_train" for this.
-
"[D]" Problems with Lazy Config detectron2 (MViTv2)
I want to use this config file https://github.com/facebookresearch/detectron2/blob/main/projects/MViTv2/configs/mask_rcnn_mvitv2_t_3x.py like the beneath typical way I use a yaml config file. But giving so many errors one after another that, I even failed to count at this point.
-
AI Real Time (lgd for cn)
Which is built on https://github.com/facebookresearch/detectron2
-
List of AI-Models
Click to Learn more...
-
good computer vision or deep learning projects in github
Detectron2 (GitHub: https://github.com/facebookresearch/detectron2) is a Facebook AI Research library with state-of-the-art object detection and segmentation algorithms in PyTorch.
- Object Detection using PyTorch: Would you recommend a Framework (Detectron2, MMDetection, ...) or a project from scratch ?
What are some alternatives?
BlenderProc - A procedural Blender pipeline for photorealistic training image generation
mmdetection - OpenMMLab Detection Toolbox and Benchmark
bpycv - Computer vision utils for Blender (generate instance annoatation, depth and 6D pose by one line code)
yolov5 - YOLOv5 🚀 in PyTorch > ONNX > CoreML > TFLite
retopoflow - A suite of retopology tools for Blender
openpose - OpenPose: Real-time multi-person keypoint detection library for body, face, hands, and foot estimation
Meshroom - 3D Reconstruction Software
U-2-Net - The code for our newly accepted paper in Pattern Recognition 2020: "U^2-Net: Going Deeper with Nested U-Structure for Salient Object Detection."
metaflow - :rocket: Build and manage real-life ML, AI, and data science projects with ease!
pytorch-lightning - Build high-performance AI models with PyTorch Lightning (organized PyTorch). Deploy models with Lightning Apps (organized Python to build end-to-end ML systems). [Moved to: https://github.com/Lightning-AI/lightning]
TextRecognitionDataGenerator - A synthetic data generator for text recognition
rembg - Rembg is a tool to remove images background