Apprentissage automatique · GitHub

PFRL: a PyTorch-based deep reinforcement learning library

An All-in-One Algo-Trading Framework: Backtest -> Train -> Trade -> Monitor. Machine / Deep Learning Ready. Supports All Trading: TradFi+CeFi+DeFi. Code Once, Trade Anywhere.

• Supports vectorized and event-driven backtesting with different resolutions of data, e.g. tick data, second data and minute data etc.
• Dataframe-centric trading workflow

Optical Flow Prediction with TensorFlow. Implements "PWC-Net: CNNs for Optical Flow Using Pyramid, Warping, and Cost Volume," by Deqing Sun et al. (CVPR 2018)

Layers Outputs and Gradients in Keras. Made easy.

Keras Attention Layer (Luong and Bahdanau scores).

Keras Temporal Convolutional Network. Supports Python and R.

YOLO9000: Better, Faster, Stronger - Real-Time Object Detection. 9000 classes!

Traduction image-à-image avec des réseaux adverses conditionnels

A natively parallel dataloader for Python, written in Rust. Serving data at GB/s speeds, while covering aspect ratio bucketing, crop and resize for image ML workloads.

On-device wake word detection powered by deep learning

speech to text benchmark framework

A Keras port of Single Shot MultiBox Detector

A simple and extensible library to create Bayesian Neural Network layers on PyTorch.

PixlStash helps you find things in an image library that's gotten out of hand. It imports and tags your images automatically, then lets you search by content or face, sort the keepers from the rubbish, and serve data to other tools (like ComfyUI) with a REST API. Use the desktop version or run it headless as a server.

Physics-Informed Neural networks for Advanced modeling

Official repo for DAD-3DHeads: A Large-scale Dense, Accurate and Diverse Dataset for 3D Head Alignment from a Single Image (CVPR 2022).

🧬 Generative modeling of regulatory DNA sequences with diffusion probabilistic models 💨