Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/eriklindernoren/Fast-Neural-Style-Transfer
Fast Neural Style Transfer in Pytorch
https://github.com/eriklindernoren/Fast-Neural-Style-Transfer
Last synced: 7 days ago
JSON representation
Fast Neural Style Transfer in Pytorch
- Host: GitHub
- URL: https://github.com/eriklindernoren/Fast-Neural-Style-Transfer
- Owner: eriklindernoren
- License: mit
- Created: 2019-04-11T19:02:48.000Z (over 5 years ago)
- Default Branch: master
- Last Pushed: 2020-05-13T17:23:03.000Z (over 4 years ago)
- Last Synced: 2024-08-01T16:41:34.168Z (3 months ago)
- Language: Python
- Size: 20.7 MB
- Stars: 343
- Watchers: 8
- Forks: 86
- Open Issues: 10
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# Fast Neural Style Transfer in PyTorch
PyTorch implementation of [Fast Neural Style Transfer](https://cs.stanford.edu/people/jcjohns/eccv16/) ([official Lua implementation](https://github.com/jcjohnson/fast-neural-style)).
I have made some trained models available [here](https://drive.google.com/drive/folders/1aRD6zakhcDImN2Y54qAT6f4801iLcCLB?usp=sharing).
## Train
```
python3 train.py --dataset_path \
--style_image \
--epochs 1 \
--batch_size 4 \
--image_size 256
```
Figure: Training progress over the first 10,000 batches.## Test on Video
```
python3 test_on_video.py --video_path \
--checkpoint_model \
```
## Test on Image
```
python3 test_on_image.py --image_path \
--checkpoint_model \
```