detectron2
transformers
Our great sponsors
detectron2 | transformers | |
---|---|---|
49 | 173 | |
28,585 | 124,557 | |
1.6% | 2.4% | |
7.5 | 10.0 | |
6 days ago | about 5 hours ago | |
Python | Python | |
Apache License 2.0 | 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.
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.
-
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 ?
transformers
-
AI enthusiasm #6 - Finetune any LLM you want💡
Most of this tutorial is based on Hugging Face course about Transformers and on Niels Rogge's Transformers tutorials: make sure to check their work and give them a star on GitHub, if you please ❤️
-
Schedule-Free Learning – A New Way to Train
* Superconvergence + LR range finder + Fast AI's Ranger21 optimizer was the goto optimizer for CNNs, and worked fabulously well, but on transformers, the learning rate range finder sadi 1e-3 was the best, whilst 1e-5 was better. However, the 1 cycle learning rate stuck. https://github.com/huggingface/transformers/issues/16013
-
Gemma doesn't suck anymore – 8 bug fixes
Thanks! :) I'm pushing them into transformers, pytorch-gemma and collabing with the Gemma team to resolve all the issues :)
The RoPE fix should already be in transformers 4.38.2: https://github.com/huggingface/transformers/pull/29285
My main PR for transformers which fixes most of the issues (some still left): https://github.com/huggingface/transformers/pull/29402
- HuggingFace Transformers: Qwen2
- HuggingFace Transformers Release v4.36: Mixtral, Llava/BakLlava, SeamlessM4T v2
- HuggingFace: Support for the Mixtral Moe
-
Paris-Based Startup and OpenAI Competitor Mistral AI Valued at $2B
If you want to tinker with the architecture Hugging Face has a FOSS implementation in transformers: https://github.com/huggingface/transformers/blob/main/src/tr...
If you want to reproduce the training pipeline, you couldn't do that even if you wanted to because you don't have access to thousands of A100s.
-
Fail to reproduce the same evaluation metrics score during inference.
I am aware that using mixed precision reduces the stability of weight and there will be little consistency but don't expect it to be this much. I have attached the graph of evaluation metrics. If someone can give me some insight into this issue, that would be great.
-
[D] What is a good way to maintain code readability and code quality while scaling up complexity in libraries like Hugging Face?
In transformers, they tried really hard to have a single function or method to deal with both self and cross attention mechanisms, masking, positional and relative encodings, interpolation etc. While it allows a user to use the same function/method for any model, it has led to severe parameter bloat. Just compare the original implementation of llama by FAIR with the implementation by HF to get an idea.
-
Mixtral-7b-8expert working in Oobabooga (unquantized multi-gpu)
pip install git+https://github.com/huggingface/transformers.git@main
What are some alternatives?
mmdetection - OpenMMLab Detection Toolbox and Benchmark
fairseq - Facebook AI Research Sequence-to-Sequence Toolkit written in Python.
yolov5 - YOLOv5 🚀 in PyTorch > ONNX > CoreML > TFLite
sentence-transformers - Multilingual Sentence & Image Embeddings with BERT
openpose - OpenPose: Real-time multi-person keypoint detection library for body, face, hands, and foot estimation
llama - Inference code for Llama models
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."
transformer-pytorch - Transformer: PyTorch Implementation of "Attention Is All You Need"
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]
text-generation-webui - A Gradio web UI for Large Language Models. Supports transformers, GPTQ, AWQ, EXL2, llama.cpp (GGUF), Llama models.
rembg - Rembg is a tool to remove images background
huggingface_hub - The official Python client for the Huggingface Hub.