Natsu6767 / Generating Devanagari Using Draw
PyTorch implementation of DRAW: A Recurrent Neural Network For Image Generation trained on Devanagari dataset.
Stars: ✭ 82
Programming Languages
python
139335 projects - #7 most used programming language
Projects that are alternatives of or similar to Generating Devanagari Using Draw
Texturize
🤖🖌️ Generate photo-realistic textures based on source images. Remix, remake, mashup! Useful if you want to create variations on a theme or elaborate on an existing texture.
Stars: ✭ 366 (+346.34%)
Mutual labels: generative-model, image-generation
Lggan
[CVPR 2020] Local Class-Specific and Global Image-Level Generative Adversarial Networks for Semantic-Guided Scene Generation
Stars: ✭ 97 (+18.29%)
Mutual labels: generative-model, image-generation
Vae For Image Generation
Implemented Variational Autoencoder generative model in Keras for image generation and its latent space visualization on MNIST and CIFAR10 datasets
Stars: ✭ 87 (+6.1%)
Mutual labels: generative-model, image-generation
texturize
🤖🖌️ Generate photo-realistic textures based on source images. Remix, remake, mashup! Useful if you want to create variations on a theme or elaborate on an existing texture.
Stars: ✭ 495 (+503.66%)
Mutual labels: generative-model, image-generation
canvas-constructor
An ES6 utility for canvas with built-in functions and chained methods.
Stars: ✭ 96 (+17.07%)
Mutual labels: draw, image-generation
TriangleGAN
TriangleGAN, ACM MM 2019.
Stars: ✭ 28 (-65.85%)
Mutual labels: generative-model, image-generation
Gesturegan
[ACM MM 2018 Oral] GestureGAN for Hand Gesture-to-Gesture Translation in the Wild
Stars: ✭ 136 (+65.85%)
Mutual labels: generative-model, image-generation
swd
unsupervised video and image generation
Stars: ✭ 50 (-39.02%)
Mutual labels: generative-model, image-generation
Rnn Vae
Variational Autoencoder with Recurrent Neural Network based on Google DeepMind's "DRAW: A Recurrent Neural Network For Image Generation"
Stars: ✭ 39 (-52.44%)
Mutual labels: image-generation, draw
Dlf
Code for reproducing results in "Generative Model with Dynamic Linear Flow"
Stars: ✭ 65 (-20.73%)
Mutual labels: generative-model
Maker.js
📐⚙ 2D vector line drawing and shape modeling for CNC and laser cutters.
Stars: ✭ 1,185 (+1345.12%)
Mutual labels: draw
Tars
A deep generative model library in Theano and Lasagne
Stars: ✭ 61 (-25.61%)
Mutual labels: generative-model
Download
UI mod for Dota 2 Auto Chess that adds several QoL improvements to the UI
Stars: ✭ 65 (-20.73%)
Mutual labels: draw
Pytorch Pix2pix
Pytorch implementation of pix2pix for various datasets.
Stars: ✭ 74 (-9.76%)
Mutual labels: generative-model
Matlab Gan
MATLAB implementations of Generative Adversarial Networks -- from GAN to Pixel2Pixel, CycleGAN
Stars: ✭ 63 (-23.17%)
Mutual labels: image-generation
Semantic Object Accuracy For Generative Text To Image Synthesis
Code for "Semantic Object Accuracy for Generative Text-to-Image Synthesis" (TPAMI 2020)
Stars: ✭ 78 (-4.88%)
Mutual labels: image-generation
Vae protein function
Protein function prediction using a variational autoencoder
Stars: ✭ 57 (-30.49%)
Mutual labels: generative-model
Leaflet.draw.drag
Drag feature functionality for Leaflet.draw
Stars: ✭ 56 (-31.71%)
Mutual labels: draw
Inr Gan
Adversarial Generation of Continuous Images [CVPR 2021]
Stars: ✭ 81 (-1.22%)
Mutual labels: generative-model
Generating-Devanagari-Using-DRAW
PyTorch implementation of DRAW: A Recurrent Neural Network For Image Generation on the task of generating Devanagari Characters.
Training
Download the data and place it in the data/ directory. Run train.py
to start training. To change the hyperparameters of the network, update the values in the param
dictionary in train.py
.
Loss Curve
Generating New Images
To generate new images run generate.py
.
python3 evaluate.py -load_path /path/to/pth/checkpoint -num_output n
The checkpoint file for the model trained for 50 epochs is present in checkpoint/ directory.
Results
Devanagari Training Data | Generated Devanagari After 50 Epochs |
---|---|
Devanagari Numbers Only Training Data | Generated Devanagari Numbers After 50 Epochs |
---|---|
Some more generated images:
References
- Karol Gregor, Ivo Danihelka, Alex Graves, Danilo Jimenez Rezende, Daan Wierstra. DRAW: A Recurrent Neural Network For Image Generation. [arxiv]
- ericjang/draw [repo]
- What is DRAW (Deep Recurrent Attentive Writer)? [blog]
Data
The Devanagari Character dataset is available on kaggle. (Source)
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].