We implemented our capsule net based on the code provided in here. The paper is submitted to MNRAS and you can find it on arXiv at arXiv:1809.08377. You can also read a news article about our work here
Datasets can be dowloaded from here. The files were to large so I had to share them through another way.
We used one NVIDIA Tesla P100 GPU unit along with 4 CPUs on Owen cluster at Ohio Supercomputer Center (OSC) with 16Gb of memory.
Read the data preprocessing part in the paper. To crop and downsample the dataset from Kaggle simply download the dataset to a folder and use the data_preprocess.py provided in preporcess folder. The preprocessed datasets are provided here.
Each folder contains the following structure:
- folder/
- code/
- data/
- results/
- epochs/ (only for CapsNet)
The CNN_Baseline_Morph_3_Drop_2fc folder contains the code for this scenario. The datasets have been provided above. The files are train_downsample_agreed_0.8.npy and train_labels_agreed_0.8.npy.
The Morph_2_new folder contains the code and data is the same as provided in baseline model. You can copy and paste it in the dataset folder here. The epochs folder is where the model after each epoch of training will be saved and if you want to restart your training from an specific epoch you can load the model and restart your training.
The CNN_Baseline_Reger folder contains the codes. The datasets have been provided above.The files are train_downsample.npy and train_labels_regression.npy.
The Morph_Reger folder contains the code and the dataset is the same as provided in baseline model.