Generating-Devanagari-Using-DRAW
Generating-Devanagari-Using-DRAW copied to clipboard
Published
20 hours ago •
Natsu6767
Natsu6767
PyTorch implementation of DRAW: A Recurrent Neural Network For Image Generation trained on Devanagari dataset.
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)
Natsu6767