503 Open source projects that are alternatives of or similar to Stochastic-Quantization

ImageNet model implemented using the Keras Functional API

TF2 Deep FloorPlan Recognition using a Multi-task Network with Room-boundary-Guided Attention. Enable tensorboard, quantization, flask, tflite, docker, github actions and google colab.

arcface and retinaface model convert mxnet to onnx.

A review of change detection methods, including codes and open data sets for deep learning. From paper: change detection based on artificial intelligence: state-of-the-art and challenges.

pytorch to caffe by onnx

Squeeze-and-Excitation Networks

Caffe implementation for "Guided Optical Flow Learning"

No description or website provided.

Moore Machine Networks (MMN): Learning Finite-State Representations of Recurrent Policy Networks

Public scenarios to crowdsource experiments (such as DNN crowd-benchmarking and crowd-tuning) using Collective Knowledge Framework across diverse mobile devices provided by volunteers. Results are continuously aggregated at the open repository of knowledge:

Semantically consistent regularizer for zero-shot learning

pytorch 2 caffe

Automatic colorization using deep neural networks. "Colorful Image Colorization." In ECCV, 2016.

Transfer Learning with DCNNs (DenseNet, Inception V3, Inception-ResNet V2, VGG16) for skin lesions classification

Domain Guided Dropout for Person Re-identification

ImageNet pre-trained SharpPeleeNet can be used in real-time Semantic Segmentation/Objects Detection

ID-discriminative Embedding (IDE) for Person Re-identification

Depth Map Super-Resolution by Deep Multi-Scale Guidance, ECCV 2016

通用深度学习推理服务，可在生产环境中快速上线由TensorFlow、PyTorch、Caffe框架训练出的深度学习模型。

Scripts to work with LMDB + PyTorch for Imagenet training

Oriented Response Networks, in CVPR 2017

Mxnet2Caffe_Tensor RT

Weakly-Supervised Semantic Segmentation Network with Deep Seeded Region Growing (CVPR 2018).

State-of-the-art method for large-scale ANN search as of Oct 2016. Presented at ECCV 16.

MTCNN with Motion Detection, on Raspberry Pi with Love

在caffe应用到工程实现时，为了方便系统安装，需要尽可能减少软件的依赖库。 本项目以bash shell/PowerShell脚本实现将caffe依赖的所有第三方库与caffe静态编译一起，以满足全静态编译的要求。 通过本项目提供的脚本生成的caffe编译环境不需要在系统安装任何第三方库和软件，就可以自动完成caffe项目静态编译. 目前在centos6.5/ubuntu16/win7/win10上测试通过,windows上VS2013,VS2015,MinGW 5.2.0编译通过

Auto-ReID and Other Person Re-Identification Projects

[ECCV 2020] Scale Adaptive Network: Learning to Learn Parameterized Classification Networks for Scalable Input Images

A Lightweight Optical Flow CNN - Revisiting Data Fidelity and Regularization, TPAMI 2020

🎯 保姆级深度学习从入门到放弃 🤪 🤪

php wrapper for opencv

Caffe Wide-Residual-Network (WRN) Generator

Collective Knowledge workflow for Caffe to automate installation across diverse platforms and to collaboratively evaluate and optimize Caffe-based workloads across diverse hardware, software and data sets (compilers, libraries, tools, models, inputs):

Fast Image Retrieval (FIRe) is an open source project to promote image retrieval research. It implements most of the major binary hashing methods to date, together with different popular backbone networks and public datasets.

Toolbox for converting analog to spiking neural networks (ANN to SNN), and running them in a spiking neuron simulator.

Paper list for neural network compression techniques

Data Augmentation for Caffe

Re-implementation of tripletloss function in FaceNet

PyTorch implementation of EfficientNetV2 family

This repository was a fork of BVLC/caffe and includes the upsample, bn, dense_image_data and softmax_with_loss (with class weighting) layers of caffe-segnet (https://github.com/alexgkendall/caffe-segnet) to run SegNet with cuDNN version 5.

Train faster rcnn on imagine dataset, related blog post: https://andrewliao11.github.io/object/detection/2016/07/23/detection/

The NNEF Tools repository contains tools to generate and consume NNEF documents

Parametric Contrastive Learning (ICCV2021)

ResNet-20/32/44/56/110 on CIFAR-10 with Caffe

Convert image folder to lmdb, adapted from Efficient-PyTorch

SphereFace+ Implementation for <Learning towards Minimum Hyperspherical Energy> in NIPS'18.

The code for preparing the training data for crowd counting / segmentation algorithm.

Türkiye'de yapılan derin öğrenme (deep learning) ve makine öğrenmesi (machine learning) çalışmalarının derlendiği sayfa.

⚡ boost inference speed of T5 models by 5x & reduce the model size by 3x.

A caffe implementation of mobilenet's depthwise convolution layer.

ncnn is a high-performance neural network inference framework optimized for the mobile platform

Modified RefineDet

🤖 Cozmo the Robot recognizes objects with TensorFlow

Fine-grained classification via second order statistics in a compact end-to-end trainable model

Caffe implementation of Google MobileNet SSD detection network, with pretrained weights on VOC0712 and mAP=0.727.

Caffe-to-Keras weight converter. Can also export weights as Numpy arrays for further processing.

Real-World Anomaly Detection in Surveillance Videos

Bottleneck Transformers for Visual Recognition

Multi-layer Recurrent Neural Networks (with LSTM) for character-level language models in Caffe