State of the Art Natural Language Processing

SOTA low-bit LLM quantization (INT8/FP8/INT4/FP4/NF4) & sparsity; leading model compression techniques on TensorFlow, PyTorch, and ONNX Runtime

Intel® Graphics Compute Runtime for oneAPI Level Zero and OpenCL™ Driver

NVIDIA® TensorRT™ is an SDK for high-performance deep learning inference on NVIDIA GPUs. This repository contains the open source components of TensorRT.

State-of-the-Art Deep Learning scripts organized by models - easy to train and deploy with reproducible accuracy and performance on enterprise-grade infrastructure.

🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.

This repository is a home to Intel® Deep Learning Streamer (Intel® DL Streamer) Pipeline Framework. Pipeline Framework is a streaming media analytics framework, based on GStreamer* multimedia frame…

ParaDnn: A systematic performance analysis methodology for deep learning.

TensorFlow code and pre-trained models for BERT

DeepSD Super-resolution for Climate Downscaling in KDD 2017

Demo of running NNs across different frameworks

Tutorials on running distributed deep learning on Batch AI

LSTM and Hierarchical Attention Network on DSVM

Free to use online tool for labelling photos. https://makesense.ai

Explore the Capabilities of the TensorRT Platform

Models and examples built with TensorFlow

Image classification with NVIDIA TensorRT from TensorFlow models.

OpenVINO™ is an open source toolkit for optimizing and deploying AI inference

Open Images is a dataset of ~9 million images that have been annotated with image-level labels and bounding boxes spanning thousands of classes.

Quantized Neural Network PACKage - mobile-optimized implementation of quantized neural network operators

cuML - RAPIDS Machine Learning Library

General code to convert a trained keras model into an inference tensorflow model

PlaidML is a framework for making deep learning work everywhere.

The labels for object categories in COCO dataset

The world's simplest facial recognition api for Python and the command line

Library of deep learning models and datasets designed to make deep learning more accessible and accelerate ML research.

This repository contains code examples for the Stanford's course: TensorFlow for Deep Learning Research.

Joint Detection and Identification Feature Learning for Person Search