81
GitHub - iShohei220/torch-gqn: PyTorch Implementation of Generative Query Networ...
source link: https://github.com/iShohei220/torch-gqn
Go to the source link to view the article. You can view the picture content, updated content and better typesetting reading experience. If the link is broken, please click the button below to view the snapshot at that time.
README.md
PyTorch implementation of Generative Query Network
Original Paper: Neural scene representation and rendering (Eslami, et al., 2018)
https://deepmind.com/blog/neural-scene-representation-and-rendering
Pixyz Implementation: https://github.com/masa-su/pixyzoo/tree/master/GQN
Requirement
- Python >=3.6
- PyTorch
- TensorBoardX
How to Train
python train.py --train_data_dir /path/to/dataset/train --test_data_dir /path/to/dataset/test
# Using multiple GPUs.
python train.py --device_ids 0 1 2 3 --train_data_dir /path/to/dataset/train --test_data_dir /path/to/dataset/test
Dataset
https://github.com/deepmind/gqn-datasets
Usage
dataset/convert2torch.py
Convert TFRecord of datasets for PyTorch implementation.
representation.py
Representation networks (See Figure S1 in Supplementary Materials of the paper).
core.py
Core networks of inference and generation (See Figure S2 in Supplementary Materials of the paper).
conv_lstm.py
Implementation of convolutional LSTM used in core.py.
gqn_dataset.py
Dataset class.
model.py
Main module of Generative Query Network.
train.py
Training algorithm.
scheduler.py
Scheduler of learning rate used in train.py.
Results (WIP)
Ground Truth
Generation
Shepard-Metzler objects
Mazes
Recommend
About Joyk
Aggregate valuable and interesting links.
Joyk means Joy of geeK