This repository contains some common functionalities used in various works from the members of the Vision And Security Technology (VAST) Lab.
pip install git+https://github.com/Vastlab/vast.git
NOTE: There is an unadressed issue due to which the above install makes features like FINCH unable to end user. If you intend to use FINCH please follow the for developers instructions below.
git clone --recurse-submodules https://github.com/Vastlab/vast.git
pip install -e .[dev]
- Entropic Openset loss
- Objectosphere loss
- Center loss
- Objecto-center loss (Objectosphere + Center loss)
- LeNet
- LeNet++
- OpenMax
- Multimodal OpenMax
- Extreme Value Machine (EVM)
This repo contains a torch based reimplementation of the libMR repo It supports GPU based computation that speeds up the processing considerably, but in certain cases the weibull parameter computation may have slight variations. Reimplementation of libMR
- Concatenate multiple torch datasets Useful for openset learning.
- Feature Extraction to HDF5 file from a specific layer of a pytorch model
- Multiprocessing Logger
- 2D visualization e.g. features from LeNet++
- 3D visualization for decision planes
- OSRC curve plotter
- Histogram of scores
- OSRC curve using torch tensors and cuda operations
- FPR vs coverage plot
- Precision/Recall for binary class OOD problem
- F-ß Score
Unless a module has a separate license, this code is free for non-commercial use under a BSD-3 style license: We only ask that you cite one our papers, whichever paper is most appropriate from the many.
Some research works using this repo are: