Connectionist Temporal Classification (CTC) decoding algorithms: best path, prefix search, beam search and token passing. Implemented in Python and OpenCL.

Ever wondered how to code your Neural Network using NumPy, with no frameworks involved?

Torchélie is a set of utility functions, layers, losses, models, trainers and other things for PyTorch.

Prostate MR Image Segmentation 2012

YOLOv4 Pytorch implementation with all freebies and specials and 15+ more exclusive improvements. Easy to use!

Focal Loss of multi-classification in tensorflow

An implementation for mnist center loss training and visualization

遥感图像的语义分割，基于深度学习，在Tensorflow框架下，利用TF.Keras，运行环境TF2.0+

Implementation of "Anchor Loss: Modulating loss scale based on prediction difficulty"

Prostate MR Image Segmentation 2012

Loss & LAtency MAtrix

Library for testing and measuring network loss and latency between distributed endpoints.

Reproducing experimental results of LL4AL [Yoo et al. 2019 CVPR]

Weighted Focal Loss for multilabel classification

A loss function for categories with a hierarchical structure.

Software to visualize detectron training stats

IOU as loss for object detection tasks and IOU as metric for object detection tasks

A tensorflow batteries included kit to write tensorflow networks from scratch or use existing ones.

a simple pytorch implement of Multi-Sample Dropout

pyIncore is a component of IN-CORE. It is a python package consisting of two primary components: 1) a set of service classes to interact with the IN-CORE web services, and 2) IN-CORE analyses . The pyIncore allows users to apply various hazards to infrastructure in selected areas, propagating the effect of physical infrastructure damage and loss of functionality to social and economic impacts.

GraLLAMA panel for LLAMA data

generating problems on RTP streams : latency, delay, jitter

Bootstrapping loss function implementation in pytorch

📉 Visualize your Deep Learning training in static graphics

PyTorch implementation of DisturbLabel

Code for eccv2020 paper: Fixing Localization Errors to Improve Image Classification

investigating generative approaches to simulating depth of field in images

An example crypto trading bot that does a trailing stop loss on Binance and posts to Slack