fastbook VS CLIP

This chapter focuses on defining the DataLoader classes and a Bing Image Search downloader that is provided with the fastai library. We're not going to implement a Bing downloader. That is too much work for something that could be a crate on its own. Please feel free to write such a crate, though, the world could use one.

The book is available online here The course is accessible here

Fastai Lesson 2 notebook

I recently read the FastAI book from O'Reilly, which is also published as a series of notebooks on GitHub here. I personally liked it because it shows how to obtain a working model trained with modern techniques without delving too much in the low-level details.

I recommend fastai-fastbook. I just started myself though it’s a coupled with tools and a way of working that may help you including being and to create and publish python packages from a jupyter notebook using nbdev

The fastai book actually makes a nice comparison between the systems described in PDP and modern deep learning.

> In fact, the approach laid out in PDP is very similar to the approach used in today's neural networks.

From: https://github.com/fastai/fastbook/blob/master/01_intro.ipyn...

I’m a fan of fast book by fastai.

We will also need two more libraries: OpenAI’s CLIP GitHub repo, enabling us to generate image features with the CLIP model, and the umap-learn library, which will let us apply a dimensionality reduction technique called Uniform Manifold Approximation and Projection (UMAP) to those features to visualize them in 2D:

Biggest missing feature for all these self hosted photo hosting is the lack of a real search. Being able to search for things like "beach at night" is a time saver instead of browsing through hundreds or thousands of photos. There are trained neural networks out there like https://github.com/openai/CLIP which are quite good.

In computer vision, this is known as zero-shot learning, or zero-shot prediction, because the goal is to generate predictions without explicitly being given any example predictions to learn from. With the advent of high quality multimodal models like CLIP and foundation models like Segment Anything, it is now possible to generate remarkably good zero-shot predictions for a variety of computer vision tasks, including:

(Github Repo | Most Popular Model | Paper | Project Page)

the first thing that comes to mind is CLIP: https://github.com/openai/CLIP

Whenever I’m working on semantic search applications that connect images and text, I start with a family of models known as contrastive language image pre-training (CLIP). These models are trained on image-text pairs to generate similar vector representations or embeddings for images and their captions, and dissimilar vectors when images are paired with other text strings. There are multiple CLIP-style models, including OpenCLIP and MetaCLIP, but for simplicity we’ll focus on the original CLIP model from OpenAI. No model is perfect, and at a fundamental level there is no right way to compare images and text, but CLIP certainly provides a good starting point.

in the modal card it says: pretrained text encoders (OpenCLIP-ViT/G and CLIP-ViT/L).

Command: "C:\StabilityMatrix\Packages\stable-diffusion-webui\venv\Scripts\python.exe" -m pip install https://github.com/openai/CLIP/archive/d50d76daa670286dd6cacf3bcd80b5e4823fc8e1.zip --prefer-binary

CLIP might work for your needs.

pip install deepfloyd_if==1.0.2rc0 pip install xformers==0.0.16 pip install git+https://github.com/openai/CLIP.git --no-deps pip install huggingface_hub --upgrade