Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/discus0434/evaluate-images-to-feed-diffusion
Small notebook to preprocess and evaluate images.
https://github.com/discus0434/evaluate-images-to-feed-diffusion
Last synced: 7 days ago
JSON representation
Small notebook to preprocess and evaluate images.
- Host: GitHub
- URL: https://github.com/discus0434/evaluate-images-to-feed-diffusion
- Owner: discus0434
- Created: 2022-11-10T15:18:11.000Z (almost 2 years ago)
- Default Branch: master
- Last Pushed: 2022-11-11T12:23:49.000Z (almost 2 years ago)
- Last Synced: 2023-03-10T06:11:10.454Z (over 1 year ago)
- Language: Python
- Homepage:
- Size: 32.2 KB
- Stars: 12
- Watchers: 1
- Forks: 2
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# Evaluate Images to Feed Diffusion
## Simple Description
A small notebook to:
- Preprocess images
- Evaluate how difficult the model grasp the features of your images
- evaluated mainly by perceptual and GAN's discriminator loss.## Installation
### Docker
1. Just build `Dockerfile`.
```bash
docker build . -t eval_images
```2. Then, run.
```bash
docker run -it --runtime=nvidia --gpus all -d --restart=always eval_images:latest bash
```### Conda
1. Create virtual environment from `environment.yaml`.
```bash
conda env create -f=environment.yaml
conda activate sd
```2. Run `setup.sh`.
```bash
chmod +x ./setup.sh
./setup.sh
```