Swin-Transformer
stable-diffusion
Swin-Transformer | stable-diffusion | |
---|---|---|
23 | 383 | |
13,002 | 65,504 | |
1.7% | 1.1% | |
2.8 | 0.0 | |
24 days ago | 22 days ago | |
Python | Jupyter Notebook | |
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.
Swin-Transformer
-
Samsung expected to report 80% profit plunge as losses mount at chip business
> there is really nothing that "normal" AI requires that is bound to CUDA. pyTorch and Tensorflow are backend agnostic (ideally...).
There are a lot of optimizations that CUDA has that are nowhere near supported in other software or even hardware. Custom cuda kernels also aren't as rare as one might think, they will often just be hidden unless you're looking at libraries. Our more well known example is going to be StyleGAN[0] but it isn't uncommon to see elsewhere, even in research code. Swin even has a cuda kernel[1]. Or find torch here[1] (which github reports that 4% of the code is cuda (and 42% C++ and 2% C)). These things are everywhere. I don't think pytorch and tensorflow could ever be agnostic, there will always be a difference just because you have to spend resources differently (developing kernels is time resource). We can draw evidence by looking at Intel MKL, which is still better than open source libraries and has been so for a long time.
I really do want AMD to compete in this space. I'd even love a third player like Intel. We really do need competition here, but it would be naive to think that there's going to be a quick catchup here. AMD has a lot of work to do and posting a few bounties and starting a company (idk, called "micro grad"?) isn't going to solve the problem anytime soon.
And fwiw, I'm willing to bet that most AI companies would rather run in house servers than from cloud service providers. The truth is that right now just publishing is extremely correlated to compute infrastructure (doesn't need to be but with all the noise we've just said "fuck the poor" because rejecting is easy) and anyone building products has costly infrastructure.
[0] https://github.com/NVlabs/stylegan2-ada-pytorch/blob/d72cc7d...
[1] https://github.com/microsoft/Swin-Transformer/blob/2cb103f2d...
[2] https://github.com/pytorch/pytorch/tree/main/aten/src
- Swin Transformer: Hierarchical Vision Transformer using Shifted Windows
- Swin Transformer: Hierarchical Vision Transformer Using Shifted Windows
-
[D] Influential papers round-up 2022. What are your favorites?
ConvNeXt. The A ConvNet for the 2020s paper is a highlight for me because the authors were able to design a purely convolutional architecture that outperformed popular vision transformers such as Swin Transformer (and all convolutional neural networks that came before it, of course).
-
[R] LiBai: a large-scale open-source model training toolbox
Found relevant code at https://github.com/microsoft/Swin-Transformer + all code implementations here
-
Using VIT as a feature extractor
Figures aside, you can reform the image from the tokens if you want. This is what's done in SWIN transformers (https://arxiv.org/abs/2103.14030) patches are tokenized, transformed, and then re-assembled into an image-like tensor. The patchification is shifted at every other transformer stage so that there is more information that propagates from one patch to the next.
-
Pathways Autoregressive Text-to-Image Model (Parti)
Give it a few days and lucidrains will have the code up[0].
But in honesty, it is probably how people react. We saw this with Pulse, GPT, and many others. The authors are clear about the limitations but people talk it up too much and others shit on it. There's also a reproducibility crisis in ML (many famous networks, like Swin[1][2][3], can't be reproduced (even worse when reviewers concentrate on benchmarks)). It isn't like many can train a model like this anyways. It gives them benefit of the doubt and maintains good publicity rather than controversial.
Of course, this is extremely bad from an academic perspective and personally I believe you should have your paper revoked if it isn't reproducible. You'd be surprised how many don't track the random seed or measure variance. We have GitHub. You should be able to write training options that get approximately the same results as the paper. Otherwise I don't trust your results.
[0] https://github.com/lucidrains/parti-pytorch
[1] https://github.com/microsoft/Swin-Transformer/issues/183
[2] https://github.com/microsoft/Swin-Transformer/issues/180
[3] https://github.com/microsoft/Swin-Transformer/issues/148
-
[D] What do you value in a paper replication?
That's about it. I should be able to go to your code and hit run, and reproduce your results (or within the reported variance). If you don't meet any of these criteria them I'm going to be pretty upset and lose a lot of respect for your work. I think we should also put pressure on these papers if they don't meet these conditions, especially if they are pushing the benchmarks (I'm looking at you Swin). If you win on benchmarks due to silicon lottery, then we shouldn't be trusting you.
stable-diffusion
-
Top 7 Text-to-Image Generative AI Models
Stable Diffusion: It is based on a kind of diffusion model called a latent diffusion model, which is trained to remove noise from images in an iterative process. It is one of the first text-to-image models that can run on consumer hardware and has its code and model weights publicly available.
-
Go is bigger than crab!
Which is a 1-click install of Stable Diffusion with an alternative web interface. You can choose a different approach but this one is pretty simple and I am new to this stuff.
-
Why & How to check Invisible Watermark
an invisible watermarking of the outputs, to help viewers identify the images as machine-generated.
-
How to create an Image generating AI?
It sounds like you just want to set up Stable Diffusion to run locally. I don't think your computer's specs will be able to do it. You need a graphics card with a decent amount of VRAM. Stable diffusion is in Python as is almost every AI open source project I've seen. If you can get your hands on a system with an Nvidia RTX card with as much VRAM as possible, you're in business. I have an RTX 3060 with 12 gigs of VRAM and I can run stable diffusion and a whole variety of open source LLMs as well as other projects like face swap, Roop, tortoise TTS, sadtalker, etc...
-
Two video cards...one dedicated to Stable Diffusion...the other for everything else on my PC?
Use specific GPU on multi GPU systems · Issue #87 · CompVis/stable-diffusion · GitHub
- Automatic1111 - Multiple GPUs
- Ist Google inzwischen einfach unbrauchbar?
-
Why are people so against compensation for artists?
I dealt with this in one of my posts. At least SD 1.1 till 1.5 are all trained on a batch size of 2048. The version pretty much everyone uses (1.5) is first pretrained at a resolution of 256x256 for 237K steps on laion2B-en, at the end of those training steps it will have seen roughly 500M images in laion2B-en. After that it is pre-trained for 194K steps on laion-high-resolution at a resolution of 512x512, which is a subset of 170M images from laion5B. Finally it is trained for 1.110K steps on LAION aesthetic v2 5+. This is easily verified by taking a glance at the model card of SD 1.5. Though that one doesn't specify for part of the training exactly which aesthetic set was used for part of the training, for that you have to look at the CompVis github repo. Thus at the end of it all both the most recent images and the majority of images will have come from LAION aesthetic v2 5+ (seeing every image approx 4 times). Realistically a lot of the weights obtained from pretraining on 2B will have been lost, and only provided a good starting point for the weights.
-
Is SDXL really open-source?
stable diffusion · CompVis/stable-diffusion@2ff270f · GitHub
- I want to ask the AI to draw me as a Pokemon anime character then draw six of Pokemon of my choice next to me. What are my best free, 15$ or under and 30$ or under choices?
What are some alternatives?
Swin-Transformer-Tensorflow - Unofficial implementation of "Swin Transformer: Hierarchical Vision Transformer using Shifted Windows" (https://arxiv.org/abs/2103.14030)
GFPGAN - GFPGAN aims at developing Practical Algorithms for Real-world Face Restoration.
parti-pytorch - Implementation of Parti, Google's pure attention-based text-to-image neural network, in Pytorch
Real-ESRGAN - Real-ESRGAN aims at developing Practical Algorithms for General Image/Video Restoration.
Video-Swin-Transformer - This is an official implementation for "Video Swin Transformers".
diffusers-uncensored - Uncensored fork of diffusers
pytorch-image-models - PyTorch image models, scripts, pretrained weights -- ResNet, ResNeXT, EfficientNet, NFNet, Vision Transformer (ViT), MobileNet-V3/V2, RegNet, DPN, CSPNet, Swin Transformer, MaxViT, CoAtNet, ConvNeXt, and more
diffusers - 🤗 Diffusers: State-of-the-art diffusion models for image and audio generation in PyTorch and FLAX.
ConvNeXt - Code release for ConvNeXt model
VQGAN-CLIP - Just playing with getting VQGAN+CLIP running locally, rather than having to use colab.
semantic-segmentation-pytorch - Pytorch implementation for Semantic Segmentation/Scene Parsing on MIT ADE20K dataset
onnx - Open standard for machine learning interoperability