Generate a quantization parameter file for ncnn framework int8 inference

A repository that shares tuning results of trained models generated by TensorFlow / Keras. Post-training quantization (Weight Quantization, Integer Quantization, Full Integer Quantization, Float16 Quantization), Quantization-aware training. TensorFlow Lite. OpenVINO. CoreML. TensorFlow.js. TF-TRT. MediaPipe. ONNX. [.tflite,.h5,.pb,saved_model,tfjs,tftrt,mlmodel,.xml/.bin, .onnx]

Setup and customize deep learning environment in seconds.

Code repo for realtime multi-person pose estimation in CVPR'17 (Oral)

Largest list of models for Core ML (for iOS 11+)

Python library to easily log experiments and parallelize hyperparameter search for neural networks

LiteFlowNet: A Lightweight Convolutional Neural Network for Optical Flow Estimation, CVPR 2018 (Spotlight paper, 6.6%)

Face Mask Detection system based on computer vision and deep learning using OpenCV and Tensorflow/Keras

MMdnn is a set of tools to help users inter-operate among different deep learning frameworks. E.g. model conversion and visualization. Convert models between Caffe, Keras, MXNet, Tensorflow, CNTK, PyTorch Onnx and CoreML.

Original Caffe Version for LightCNN-9. Highly recommend to use PyTorch Version (https://github.com/AlfredXiangWu/LightCNN)

Porting caffe to android platform

An absolute beginner's guide to Machine Learning and Image Classification with Neural Networks

Joint Detection and Identification Feature Learning for Person Search

Joint Face Detection and Alignment using Multi-task Cascaded Convolutional Neural Networks

Keras version of Realtime Multi-Person Pose Estimation project

Code for paper "Synthesizing the preferred inputs for neurons in neural networks via deep generator networks"

Fabric for Deep Learning (FfDL, pronounced fiddle) is a Deep Learning Platform offering TensorFlow, Caffe, PyTorch etc. as a Service on Kubernetes

A caffe implementation of MobileNet-YOLO detection network

💻 Make machines learn so that you don't have to struggle to program them; The ultimate list

Evaluation of the CNN design choices performance on ImageNet-2012.