pytorch toolbelt

We have hosted the application pytorch toolbelt in order to run this application in our online workstations with Wine or directly.

Quick description about pytorch toolbelt:

A pytorch-toolbelt is a Python library with a set of bells and whistles for PyTorch for fast R&D prototyping and Kaggle farming. Easy model building using flexible encoder-decoder architecture. Modules: CoordConv, SCSE, Hypercolumn, Depthwise separable convolution and more. GPU-friendly test-time augmentation TTA for segmentation and classification. GPU-friendly inference on huge (5000x5000) images. Every-day common routines (fix/restore random seed, filesystem utils, metrics). Losses: BinaryFocalLoss, Focal, ReducedFocal, Lovasz, Jaccard and Dice losses, Wing Loss and more. Extras for Catalyst library (Visualization of batch predictions, additional metrics). By design, both encoder and decoder produces a list of tensors, from fine (high-resolution, indexed 0) to coarse (low-resolution) feature maps. Access to all intermediate feature maps is beneficial if you want to apply deep supervision losses on them or encoder-decoder of object detection task.

Features:

• Create Encoder-Decoder FPN model with pretrained encoder
• Create Encoder-Decoder U-Net model
• Create Encoder-Decoder FPN model with pretrained encoder
• Change number of input channels for the Encoder
• Count number of parameters in encoder/decoder and other modules
• Compose multiple losses

Programming Language: Python.
Categories: