AutoEncoder

ShapeNet

Download the dataset for training and testing here. Clone the latest ocnn-pytorch repository, and enter the subdirectory projects. Unzip and place the data in the folder data/ShapeNetV1.
Run the following command to train the network. The training log and weights can be downloaded here.
```
python autoencoder.py --config configs/ae_shapenet.yaml
```
Run the following command to get the predictions on the testing dataest. The parameter following SOLVER.ckpt can be freely modified to test different trained weights. And the results are in the folder logs/ae_shapenet/ae_eval.
```
python autoencoder.py --config configs/ae_shapenet.yaml             \
       SOLVER.run evaluate  SOLVER.alias eval                       \
       SOLVER.ckpt logs/ae_shapenet/ae/checkpoints/00300.model.pth
```