Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/cattoface/deeplearningfinalproject
Final project in deep learning course
https://github.com/cattoface/deeplearningfinalproject
Last synced: 26 days ago
JSON representation
Final project in deep learning course
- Host: GitHub
- URL: https://github.com/cattoface/deeplearningfinalproject
- Owner: CattoFace
- Created: 2024-03-25T16:00:53.000Z (10 months ago)
- Default Branch: main
- Last Pushed: 2024-04-07T14:04:54.000Z (9 months ago)
- Last Synced: 2024-04-08T14:37:58.133Z (9 months ago)
- Language: Python
- Size: 75.7 MB
- Stars: 0
- Watchers: 2
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# Usage:
For both training and evaluation:
Install all the required packages using `pip install -r requirements.txt`
Place all the dataset images in a folder called dataset(we used https://www.robots.ox.ac.uk/~vgg/data/flowers/102/).
## Training:
Change any desired value in preprocess_dataset.py or preprocess_dataset_rgb.py(namely the YCbCr/HSV boolean in the former and the resize dimension).
Run preprocess_dataset.py/preprocess_dataset_rgb.py
Change any desired model/training parameter in train_gan.py.
Run train_gan.py.## Evaluation Only:
Run preprocess_dataset_rgb.py.
Run eval_gan.py.
Numerical results will be printed and the colored samples will be saved to the current directory as samples.png