Stars
A drop-in replacement for the standard Categorical Cross-Entropy (CCE) loss that significantly improves OOD and Calibration performance without reducing ID performance.
Implementation of Focal Loss (Lin et al., 2017, Facebook AI Research) for handling class imbalance by focusing learning on hard, misclassified examples.
PyTorch implementations of `BatchSampler` that under/over sample according to a chosen parameter alpha, in order to create a balanced training distribution.
The most simple, flexible, and comprehensive OpenAI Gym trading environment (Approved by OpenAI Gym)
Open source software that helps you create and deploy high-frequency crypto trading bots
PyTorch implementations of deep reinforcement learning algorithms and environments
A (PyTorch) imbalanced dataset sampler for oversampling low frequent classes and undersampling high frequent ones.
A library for differentiable nonlinear optimization
Python Sorted Container Types: Sorted List, Sorted Dict, and Sorted Set
Memory-Efficient Implementation of DenseNets via PyTorch 1.0
FC-DenseNet in PyTorch for Semantic Segmentation
PyTorch implementation of DenseNet and FCDenseNet
Semantic segmentation models with 500+ pretrained convolutional and transformer-based backbones.
Disciplina de Deep Learning (PPGIA - UFRPE)
WebSocket client for Python
better multiprocessing and multithreading in Python
Locally runnable server with built-in data caching, providing both tick-level historical and consolidated real-time cryptocurrency market data via HTTP and WebSocket APIs
Utils for streaming large files (S3, HDFS, gzip, bz2...)
A PyTorch implementation of Convolutional Sequence Embedding Recommendation Model (Caser)
Python client for Alpaca's trade API
WebSocket client for 38 cryptocurrency exchanges
Labels calculation&visualisation - comes with a small BTC/USDT database. Part of my research. Integral part of: https://arxiv.org/abs/2012.03078
Deep Adaptive Input Normalization for Time Series Forecasting
A unified trading API with more than 100 crypto exchanges and prediction markets in JavaScript / TypeScript / Python / C# / PHP / Go / Java / Rust

