Segmentation networks benchmark

Evaluation framework for testing segmentation networks in Keras and PyTorch. What segmentation network to choose for next Kaggle competition? This benchmark knows the answer!

What all this code is about?

It tries to show pros & cons of many existing segmentation networks implemented in Keras and PyTorch for different applications (biomed, sattelite, autonomous driving, etc). Briefly, it does the following:

for model in [Unet, Tiramisu, DenseNet, ...]:
    for dataset in [COCO, LUNA, STARE, ...]:
        for optimizer in [SGD, Adam]:
            history = train(model, dataset, optimizer)
            results.append(history)

summarize(results)

Roadmap

Write Keras train pipeline
Write Pytorch train pipeline

Models

Add ZF_UNET model (https://github.com/ZFTurbo/ZF_UNET_224_Pretrained_Model)
Add LinkNet model
Add Tiramisu model (https://github.com/0bserver07/One-Hundred-Layers-Tiramisu)
Add SegCaps model
Add VGG11,VGG16,AlbuNet models (https://github.com/ternaus/TernausNet)
Add FCDenseNet model (https://github.com/bfortuner/pytorch_tiramisu)

Datasets

Reporting

Add fancy plots