Maschinelles Lernen · GitHub

Medical SAM 2: Segment 3D Medical Images Via Segment Anything Model 2

A high-performance RL training-inference weight synchronization framework, designed to enable second-level parameter updates from training to inference in RL workflows

• Extreme Sync Speed: Trillion-parameter models fully synchronized within 10 seconds; validated on thousand-GPU clusters with industry-leading performance.
• Unified Weight Adaptation Layer: Automatically handles tensor format/layout differences across parallel strategies and engine frameworks, supporting any model architecture.

:page_facing_up: A PyTorch implementation of Paragraph Vectors (doc2vec).

Intelligent Driver Monitoring system for Autonomous Vehicles

Production-ready C++/TensorRT inference engine for RF-DETR. Object detection and instance segmentation with FP32/FP16/INT8 support. Optimized for NVIDIA GPUs, Jetson (Orin, AGX Thor).

Library for modelling performance costs of different Neural Network workloads on NPU devices

The original transformer implementation from scratch. It contains informative comments on each block

IPython Cookbook, Second Edition, by Cyrille Rossant, Packt Publishing 2018

Plug-and-play 2D motion interface for real-world Motion Language Models

• 🔌 Plug-and-play, at very low training cost. The interface is an external module: no modification and no fine-tuning of the pretrained MoLM. E_2D has 9.6M parameters (~22 h) and the real-video adapter A_real only 0.3M (~1 h), both on a single A100 40GB.
• 📈 Comparable to 3D motion inputs. On HumanML3D motion captioning, Avg Drop vs 3D Input is −0.2% (TM2T), +0.4% (MotionGPT), and −2.8% (MG-MotionLLM).

Emotion recognition using DNN with tensorflow

Spatial modeling using machine learning concepts