fullfanta / Multimodal_transfer
tensorflow implementation of 'Multimodal Transfer: A Hierarchical Deep Convolutional Neural Network for Fast Artistic Style Transfer'
Stars: ✭ 31
Programming Languages
python
139335 projects - #7 most used programming language
Labels
Projects that are alternatives of or similar to Multimodal transfer
Deep Motion Editing
An end-to-end library for editing and rendering motion of 3D characters with deep learning [SIGGRAPH 2020]
Stars: ✭ 620 (+1900%)
Mutual labels: style-transfer
Arbitrary Image Stylization Tfjs
Arbitrary style transfer using TensorFlow.js
Stars: ✭ 822 (+2551.61%)
Mutual labels: style-transfer
Neural Style Audio Tf
TensorFlow implementation for audio neural style.
Stars: ✭ 413 (+1232.26%)
Mutual labels: style-transfer
Pytorch Adain
Unofficial pytorch implementation of 'Arbitrary Style Transfer in Real-time with Adaptive Instance Normalization' [Huang+, ICCV2017]
Stars: ✭ 550 (+1674.19%)
Mutual labels: style-transfer
Stylized Neural Painting
Official Pytorch implementation of the preprint paper "Stylized Neural Painting", in CVPR 2021.
Stars: ✭ 663 (+2038.71%)
Mutual labels: style-transfer
Shapematchinggan
[ICCV 2019, Oral] Controllable Artistic Text Style Transfer via Shape-Matching GAN
Stars: ✭ 315 (+916.13%)
Mutual labels: style-transfer
Transferlearning
Transfer learning / domain adaptation / domain generalization / multi-task learning etc. Papers, codes, datasets, applications, tutorials.-迁移学习
Stars: ✭ 8,481 (+27258.06%)
Mutual labels: style-transfer
Ebsynth
Fast Example-based Image Synthesis and Style Transfer
Stars: ✭ 554 (+1687.1%)
Mutual labels: style-transfer
Data Augmentation Review
List of useful data augmentation resources. You will find here some not common techniques, libraries, links to github repos, papers and others.
Stars: ✭ 785 (+2432.26%)
Mutual labels: style-transfer
Deep Learning V2 Pytorch
Projects and exercises for the latest Deep Learning ND program https://www.udacity.com/course/deep-learning-nanodegree--nd101
Stars: ✭ 4,457 (+14277.42%)
Mutual labels: style-transfer
Hidt
Official repository for the paper "High-Resolution Daytime Translation Without Domain Labels" (CVPR2020, Oral)
Stars: ✭ 513 (+1554.84%)
Mutual labels: style-transfer
Pytorch Multi Style Transfer
Neural Style and MSG-Net
Stars: ✭ 687 (+2116.13%)
Mutual labels: style-transfer
Stylized Imagenet
Code to create Stylized-ImageNet, a stylized version of standard ImageNet (ICLR 2019 Oral)
Stars: ✭ 353 (+1038.71%)
Mutual labels: style-transfer
Py Style Transfer
🎨 Artistic neural style transfer with tweaks (pytorch).
Stars: ✭ 23 (-25.81%)
Mutual labels: style-transfer
Few Shot Patch Based Training
The official implementation of our SIGGRAPH 2020 paper Interactive Video Stylization Using Few-Shot Patch-Based Training
Stars: ✭ 313 (+909.68%)
Mutual labels: style-transfer
Tensorflow 101
TensorFlow 101: Introduction to Deep Learning for Python Within TensorFlow
Stars: ✭ 642 (+1970.97%)
Mutual labels: style-transfer
Deep preset
[WACV'21] Deep Preset: Blending and Retouching Photos with Color Style Transfer
Stars: ✭ 29 (-6.45%)
Mutual labels: style-transfer
Style Transfer
Style Transfer - Alia Bhatt (Google Colab)
Stars: ✭ 26 (-16.13%)
Mutual labels: style-transfer
Landmark Detection
Four landmark detection algorithms, implemented in PyTorch.
Stars: ✭ 747 (+2309.68%)
Mutual labels: style-transfer
Style transfer
This is tensorflow implementation of 'Multimodal Transfer: A Hierarchical Deep Convolutional Neural Network for Fast Artistic Style Transfer' which generates stylized image in high resulution such as 1024 pixels.
Download program
$ git clone https://github.com/fullfanta/multimodal_style_transfer.git
Train
To train network, I use MS coco dataset.
$ cd multimodal_style_transfer
$ bash get_coco.sh
- downloaded image is in 'data/train2014'.
For stylization, pretrained VGG16 is necessary.
$ bash get_vgg16.sh
Then training is SIMPLE.
$ python train.py
- If you have multiple GPU cards, use CUDA_VISIBLE_DEVICES to specify GPU card.
- Trained model is in summary.
During training, you can see generated images through tensorboard.
$ tensorboard --logdir=summary
Freeze model
$ sh freeze.sh 10000
- parameter is iteration number among saved check point files.
- It generates pb file which contains weights as contant.
Test
$ python stylize.py --model=models/starry_night.pb --input_image=test_images/jolie.jpg
- It generates hierarchical stylized images and save them to 'test_images/jolie_output_1.jpg', 'test_images/jolie_output_2.jpg', and 'test_images/jolie_output_3.jpg'. Their sizes are 256, 512 and 1024 in short edge.
- Parameters:
--model : freezed model path
--input_image : image file path to stylize
--hierarchical_short_edges : three short edge length to generate images. (default is 256, 512, 1024)
Examples
Input | Output(256px) | Output(512px) | Output(1024px) | |
---|---|---|---|---|
Angelina Jolie | ||||
Dinosour | ||||
Ryan | ||||
Cheez | ||||
Herb |
Acknowledgement
- For instance normalization, I refer 'https://github.com/ghwatson/faststyle'.
- For pretrained VGG16 network, I refer 'https://www.cs.toronto.edu/~frossard/post/vgg16/'.
Note that the project description data, including the texts, logos, images, and/or trademarks,
for each open source project belongs to its rightful owner.
If you wish to add or remove any projects, please contact us at [email protected].