1047 Open source projects that are alternatives of or similar to Chainer Pspnet

72.8% MobileNetV2 1.0 model on ImageNet and a spectrum of pre-trained MobileNetV2 models

[ICCV 2017] Torch code for Grad-CAM

Vehicle detection using YOLO in Keras runs at 21FPS

Pytorch Implementation of "Deep Iterative Down-Up CNN for Image Denoising".

Pixel-wise segmentation on VOC2012 dataset using pytorch.

Deep Learning and Reinforcement Learning Library for Scientists and Engineers 🔥

End-to-End Speech Processing Toolkit

常用的语义分割架构结构综述以及代码复现

High-efficiency floating-point neural network inference operators for mobile, server, and Web

Hardnet descriptor model - "Working hard to know your neighbor's margins: Local descriptor learning loss"

Tools to Design or Visualize Architecture of Neural Network

Face landmarks(fiducial points) detection benchmark

Tensorflow implementation of "Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network" (Ledig et al. 2017)

Real time emotion recognition

🔥 Reproducibly benchmarking Keras and PyTorch models

Convolutional Neural Network for 3D meshes in PyTorch

A general list of resources to image text localization and recognition 场景文本位置感知与识别的论文资源与实现合集 シーンテキストの位置認識と識別のための論文リソースの要約

Implementation of a hierarchical CNN based model to detect Big Five personality traits

Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering

RectLabel - An image annotation tool to label images for bounding box object detection and segmentation.

💃 Real-time single person pose estimation for Android and iOS.

Most popular metrics used to evaluate object detection algorithms.

🚖 Object Detection (YOLOv1) implentation in tensorflow, with training, testing and video features.

Keras- Multi Label Image Classification

🔥Deep Learning for 3D Point Clouds (IEEE TPAMI, 2020)

Light-Weight RefineNet for Real-Time Semantic Segmentation

Segmentation of ID Cards using Semantic Segmentation

Code for Universal Semi-Supervised Semantic Segmentation models paper accepted in ICCV 2019

TensorFlow Implementation of state-of-the-art models since 2012

MobileNetV3 in pytorch and ImageNet pretrained models

Code examples for new APIs of iOS 10.

Emotion recognition using DNN with tensorflow

YOLO: Real-Time Object Detection using Tensorflow and easy to use

[CVPR 2021] Involution: Inverting the Inherence of Convolution for Visual Recognition, a brand new neural operator

Tensorflow Implementation of the Semantic Segmentation DeepLab_V3 CNN

A Genetic Programming Approach to Designing CNN Architectures, In GECCO 2017 (oral presentation, Best Paper Award)

Cross-Domain Weakly-Supervised Object Detection through Progressive Domain Adaptation [Inoue+, CVPR2018].

SincNet is a neural architecture for efficiently processing raw audio samples.

unet for rgb images semantic segmentation

Play deep learning with CIFAR datasets

parsing scene images with understanding geometric perspective in the loop

Fast Deep Learning Library (DLL) for C++ (ANNs, CNNs, RBMs, DBNs...)

The deep semantic segmentation network for lane segmentation.

Complete Assignments for CS231n: Convolutional Neural Networks for Visual Recognition

Can Neural Networks Crack Sudoku?

Official Pytorch Implementation of "TResNet: High-Performance GPU-Dedicated Architecture" (WACV 2021)

Towards Automated Deep Learning: Efficient Joint Neural Architecture and Hyperparameter Search https://arxiv.org/abs/1807.06906

Next RecSys Library

Real-time object detection on Android using the YOLO network with TensorFlow

real-time network architecture for mobile devices and semantic segmentation

Generating proportional fonts with deep learning

End-to-end one-class instance segmentation based on U-Net architecture for Data Science Bowl 2018 in Kaggle

Chainer x TensorRT

Kaggle | Web Traffic Forecasting 📈

This work is based on our paper "DualConvMesh-Net: Joint Geodesic and Euclidean Convolutions on 3D Meshes", which appeared at the IEEE Conference On Computer Vision And Pattern Recognition (CVPR) 2020.

Equivariant Transformer (ET) layers are image-to-image mappings that incorporate prior knowledge on invariances with respect to continuous transformations groups (ICML 2019). Paper: https://arxiv.org/abs/1901.11399

Adaptive Real-Time Object Detection System with HOG and CNN Features

Trial on kaggle imagenet object localization by yolo v3 in google cloud

A large-scale dataset of both raw MRI measurements and clinical MRI images

Add bisenetv2. My implementation of BiSeNet