Vgg Open Source Projects

A faster pytorch implementation of faster r-cnn

Keras code and weights files for popular deep learning models.

95.47% on CIFAR10 with PyTorch

Count the MACs / FLOPs of your PyTorch model.

An easy to use PyTorch to TensorRT converter

PlaidML is a framework for making deep learning work everywhere.

Single Shot MultiBox Detector in TensorFlow

Model summary in PyTorch similar to `model.summary()` in Keras

Generate image analogies using neural matching and blending.

Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network

Fast R-CNN

Directory of tutorials and open-source code repositories for working with Keras, the Python deep learning library

Semantic Segmentation on PyTorch (include FCN, PSPNet, Deeplabv3, Deeplabv3+, DANet, DenseASPP, BiSeNet, EncNet, DUNet, ICNet, ENet, OCNet, CCNet, PSANet, CGNet, ESPNet, LEDNet, DFANet)

Implementation of Segnet, FCN, UNet , PSPNet and other models in Keras.

Flops counter for neural networks in pytorch framework

Faster R-CNN

Caffe models in TensorFlow

Benchmarks for popular CNN models

An implementation of the paper 'A Neural Algorithm of Artistic Style'.

VGG19 and VGG16 on Tensorflow

Neural Artistic Style in Python

The Places365-CNNs for Scene Classification

A CNN based pytorch implementation on facial expression recognition (FER2013 and CK+), achieving 73.112% (state-of-the-art) in FER2013 and 94.64% in CK+ dataset

Deep Clustering for Unsupervised Learning of Visual Features

pip install antialiased-cnns to improve stability and accuracy

High quality, fast, modular reference implementation of SSD in PyTorch

MobileNetV1, MobileNetV2, VGG based SSD/SSD-lite implementation in Pytorch 1.0 / Pytorch 0.4. Out-of-box support for retraining on Open Images dataset. ONNX and Caffe2 support. Experiment Ideas like CoordConv.

Classification models trained on ImageNet. Keras.

TensorFlow 101: Introduction to Deep Learning

An Implementation of Fully Convolutional Networks in Tensorflow.

Tutorials on how to implement a few key architectures for image classification using PyTorch and TorchVision.

Learning Lightweight Lane Detection CNNs by Self Attention Distillation (ICCV 2019)

High level network definitions with pre-trained weights in TensorFlow

VGGFace implementation with Keras Framework

Fine-tune CNN in Keras

Memory consumption and FLOP count estimates for convnets

A tensorflow implementation for fast neural style!

Unofficial implementation of "Image Inpainting for Irregular Holes Using Partial Convolutions". Try at: www.fixmyphoto.ai

PyTorch Implementation of [1611.06440] Pruning Convolutional Neural Networks for Resource Efficient Inference

FastER RCNN built on tensorflow

This is a code repository for pytorch c++ (or libtorch) tutorial.

Pre-trained models, data, code & materials from the paper "ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness" (ICLR 2019 Oral)

Books, Presentations, Workshops, Notebook Labs, and Model Zoo for Software Engineers and Data Scientists wanting to learn the TF.Keras Machine Learning framework

Tensorflow (Python API) implementation of Deep Photo Style Transfer

Implementation of our paper 'PixelLink: Detecting Scene Text via Instance Segmentation' in AAAI2018

pytorch实现Grad-CAM和Grad-CAM++,可以可视化任意分类网络的Class Activation Map (CAM)图,包括自定义的网络;同时也实现了目标检测faster r-cnn和retinanet两个网络的CAM图;欢迎试用、关注并反馈问题...

这是一个孪生神经网络（Siamese network）的库，可进行图片的相似性比较。

An open-source PyTorch code for crowd counting

Fine-tune pretrained Convolutional Neural Networks with PyTorch

A skeleton-based real-time online action recognition project, classifying and recognizing base on framewise joints, which can be used for safety surveilence.

pytorch version of SSD and it's enhanced methods such as RFBSSD,FSSD and RefineDet

conversation of caffe vgg16 model to tensorflow

🏞 A content-based image retrieval (CBIR) system

Computer vision based ML training data generation tool :rocket:

food image to recipe with deep convolutional neural networks.

PyTorch implementation of two-stream networks for video action recognition

风格迁移三部曲

Repository for Single Shot MultiBox Detector and its variants, implemented with pytorch, python3.

仅使用numpy从头开始实现神经网络,包括反向传播公式推导过程; numpy构建全连接层、卷积层、池化层、Flatten层；以及图像分类案例及精调网络案例等,持续更新中... ...