Transformers-Tutorials
pytorch-image-models
Our great sponsors
Transformers-Tutorials | pytorch-image-models | |
---|---|---|
7 | 35 | |
7,510 | 29,751 | |
- | 2.9% | |
8.4 | 9.4 | |
16 days ago | 6 days ago | |
Jupyter Notebook | Python | |
MIT License | 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.
Transformers-Tutorials
-
AI enthusiasm #6 - Finetune any LLM you want๐ก
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 โค๏ธ
- FLaNK Stack Weekly for 07August2023
- How to annotate compound words to build NER models?
-
[discussion] Anybody Working with VITMAE?
I'm pretraining on 850K grayscale spectrograms of birdsongs. I'm on epoch 400 out of 800 and the loss has declined from about 1.2 to 0.7. I don't really have a sense of what is "good enough" and I guess the only way I can judge is by looking at the reconstruction. I'm doing that using this notebook as a guide and right now it's doing quite badly.
-
[D] NLP has HuggingFace, what does Computer Vision have?
More tutorials can be found at https://github.com/NielsRogge/Transformers-Tutorials.
-
[Discussion] Information Extraction with LayoutLMv2
Ive been looking for an off the shelf encoder-decoder document understanding model for key information extraction. I found a great Huggingface implementation with concise notebook examples. However, the token classification model outputs a list of token labels corresponding bounding boxes for the token, but, not the text contained within the labeled bounding boxes themselves. Am I missing something? LayoutLMv2 describes itself as being capable of information extraction but without extracting the text I feel like it's fallen short of that ambition.
-
[Project] Deepmind's Perceiver IO available through Hugging Face
Example Notebooks
pytorch-image-models
- FLaNK AI Weekly 18 March 2024
-
[D] Hugging face and Timm
I am a PyTorch user I work in CV, I usually use the PyTorch models. However, I see people use timm in research papers to train their models I don't understand what it is timm is it a new framework like PyTorch? Further, when I click https://pypi.org/project/timm/ homepage it takes me to hugging face GitHub https://github.com/huggingface/pytorch-image-models is there any connection between timm and hugging face many of my friends use hugging face but I also don't know about hugging face I use simple PyTorch and torchvision.models.
-
FLaNK Stack Weekly for 07August2023
https://github.com/huggingface/pytorch-image-models https://huggingface.co/docs/timm/index
-
[R] Nvidia RTX 4090 ML benchmarks. Under QEMU/KVM. Image + Transformers. FP16/FP32.
pytorch-image-models
-
Inference on resent, cant work out the problem?
additionally, you might find the timm library handy for this sort of work.
-
Swin Transformer: Hierarchical Vision Transformer Using Shifted Windows
This is still being pursued. Ross Wightmann's timm[0,1] package (now on Hugging Face) has done a lot of this. There's also a V2 of ConvNext[2]. Ross does write about this a lot on Twitter fwiw. I should also mention that there are still many transformer based networks that still beat convs. So there probably won't be a resurgence in convs until someone can show that there's a really strong reason for them. They have some advantages but they also might not be flexible enough for the long range tasks in segmentation and detection. But maybe they are.
FAIR definitely did great work with ConvNext, and I do hope to see more. There always needs to be people pushing unpopular paradigms.
[0] https://github.com/huggingface/pytorch-image-models
[1] https://arxiv.org/abs/2110.00476
[2] https://arxiv.org/abs/2301.00808
-
Problems with Learning Rate Finder in Pytorch Lightning
I am doing Binary classification with a pre-trained EfficientNet tf_efficientnet_l2. I froze all weights during training and replaced the classifier with a custom trainable one that looks like:
-
PyTorch at the Edge: Deploying Over 964 TIMM Models on Android with TorchScript and Flutter
In this post, Iโm going to show you how you can pick from over 900+ SOTA models on TIMM, train them using best practices with Fastai, and deploy them on Android using Flutter.
-
ImageNet Advise
The other thing is, try to find tricks to speed up your experiments (if not having done so already). The most obvious are mixed precision training, have your model train on a lower resolution input first and then increase the resolution later in the training, stochastic depth, and a bunch more stuffs. Look for implementations in https://github.com/rwightman/pytorch-image-models .
- Doubt about transformers
What are some alternatives?
nn - ๐งโ๐ซ 60 Implementations/tutorials of deep learning papers with side-by-side notes ๐; including transformers (original, xl, switch, feedback, vit, ...), optimizers (adam, adabelief, sophia, ...), gans(cyclegan, stylegan2, ...), ๐ฎ reinforcement learning (ppo, dqn), capsnet, distillation, ... ๐ง
yolov5 - YOLOv5 ๐ in PyTorch > ONNX > CoreML > TFLite
gorilla-cli - LLMs for your CLI
mmdetection - OpenMMLab Detection Toolbox and Benchmark
notebooks - Notebooks using the Hugging Face libraries ๐ค
detectron2 - Detectron2 is a platform for object detection, segmentation and other visual recognition tasks.
adaptnlp - An easy to use Natural Language Processing library and framework for predicting, training, fine-tuning, and serving up state-of-the-art NLP models.
mmcv - OpenMMLab Computer Vision Foundation
OpenBuddy - Open Multilingual Chatbot for Everyone
segmentation_models.pytorch - Segmentation models with pretrained backbones. PyTorch.
ToolBench - [ICLR'24 spotlight] An open platform for training, serving, and evaluating large language model for tool learning.
yolact - A simple, fully convolutional model for real-time instance segmentation.