Giter Club home page Giter Club logo

fast-neural-style-transfer's Introduction

Fast Neural Style Transfer in PyTorch

PyTorch implementation of Fast Neural Style Transfer (official Lua implementation).

I have made some trained models available here.

Train

python3 train.py  --dataset_path <path-to-dataset> \
                  --style_image <path-to-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 <path-to-video> \
                          --checkpoint_model <path-to-checkpoint> \

Test on Image

python3 test_on_image.py  --image_path <path-to-image> \
                          --checkpoint_model <path-to-checkpoint> \

fast-neural-style-transfer's People

Contributors

eriklindernoren avatar panispani avatar

Stargazers

 avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar

Watchers

 avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar

fast-neural-style-transfer's Issues

The model generate nothing after retrained on coco2014

Hi, you are handsome and your work are awesome! Thank you for your work.
I got a problem when I try to train a smaller 'TransformerNet' model, all input images are resize to 256x256 while training.
The 'Content' and the 'Style' reports high loss value:
image
And while train the model after some epoches, the model will never generate a picture:
image
I'm looking forward to your guidance.

train.py

hello , thanks for your codes, can you tell me the checkpoint_model
parser.add_argument("--checkpoint_model", type=str, help="Optional path to checkpoint model")
thank you

Time process

Can u give some detail of time process on 1 image?

the Video is SO BIG

i hava a video about 15 seconds, and after processing i got a nearly 1G gif. Is there anyone can tell me why it is so big ?

Training producing no result

Hi,
I am training your style transfer network with my own dataset and the style image as starry nights, just like yours. But even after training it for 6000 batches, I get black images as below:
6000
Please suggest why this is happening
My dataset has the following structure:
/RGB/data/001/image_0.jpg
/RGB/data/001/image_2.jpg
...
/RGB/data/001/image_100.jpg
...
/RGB/data/084/image_8800.jpg
/RGB/data/084/image_8801.jpg

Dataset for training

Could you tell which dataset I should ues? And what format the dataset should be ?After reading README.md,I cannot understand how to train the network clearly.Thanks!

tanh function in TransformerNet

I am confused why there isn't a tanh function in the output of TransformerNet network. Can you please tell me your approach in the conversion of the output images?

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    ๐Ÿ–– Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. ๐Ÿ“Š๐Ÿ“ˆ๐ŸŽ‰

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google โค๏ธ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.