Pytorch implementation of Spatially Invariant Unsupervised Object Detection with VAE
Additional information can be found at supplementary paper
Implementation based on the original tensorflow implementation by Eric Crawford: https://github.com/e2crawfo/auto_yolo (Special thanks to Eric for patiently explaining the details of his implementation)
- Numpy
- Pytorch 1.0+
- Python 3.5+
- TensorboardX
spair/config.py contains hyperparameters used in the model with comments.
python train.py --gpu to start training with all available GPUs
Coming soon...