Counting 3,464 Big Data & Machine Learning Frameworks, Toolsets, and Examples...
Suggestion? Feedback? Tweet @stkim1


PyTorch implementation of DRAW: A Recurrent Neural Network For Image Generation on the task of generating Devanagari Characters.

Generated Data Animation


Download the data and place it in the data/ directory. Run to start training. To change the hyperparameters of the network, update the values in the param dictionary in

Loss Curve

Training Loss Curves

Generating New Images

To generate new images run

python3 -load_path /path/to/pth/checkpoint -num_output n

The checkpoint file for the model trained for 50 epochs is present in checkpoint/ directory.


Devanagari Training Data Generated Devanagari After 50 Epochs
Devanagari Numbers Only Training Data Generated Devanagari Numbers After 50 Epochs

Some more generated images:


  1. Karol Gregor, Ivo Danihelka, Alex Graves, Danilo Jimenez Rezende, Daan Wierstra. DRAW: A Recurrent Neural Network For Image Generation. [arxiv]
  2. ericjang/draw [repo]
  3. What is DRAW (Deep Recurrent Attentive Writer)? [blog]


The Devanagari Character dataset is available on kaggle. (Source)