1339 Open source projects that are alternatives of or similar to Paz

Keras implementation of Real-Time Semantic Segmentation on High-Resolution Images

Model for document segmentation trained on the midv-500-models dataset.

Code for Fast Neural Architecture Search of Compact Semantic Segmentation Models via Auxiliary Cells, CVPR '19

VarifocalNet: An IoU-aware Dense Object Detector

Conditional Convolutions for Instance Segmentation, achives 37.1mAP on coco val

SECOND for KITTI/NuScenes object detection

Enabling Deep Residual Networks for Weakly Supervised Object Detection

Codebase of the paper "Feature Intertwiner for Object Detection", ICLR 2019

Pepper Programs : Object Detection Real Time without ROS

基于tensorflow的人脸识别

Semantic Scene Completion

SegSort: Segmentation by Discriminative Sorting of Segments

OpenMMLab's next-generation platform for general 3D object detection.

Convert any classification model or architecture trained in keras to an object detection model

Unofficial implemention of lanenet model for real time lane detection using deep neural network model https://maybeshewill-cv.github.io/lanenet-lane-detection/

PyTorch extensions for fast R&D prototyping and Kaggle farming

Non-maximum suppression for object detection in a neural network

Actor-Critic Instance Segmentation (CVPR 2019)

🍴 Annotations for the EPIC KITCHENS-55 Dataset.

YOLOv3 in PyTorch > ONNX > CoreML > TFLite

Project to train/test convolutional neural networks to extract buildings from SpaceNet satellite imageries.

Top 15% ranked solution to the Carvana Image Masking Challenge on Kaggle

Depth-wise Asymmetric Bottleneck for Real-time Semantic Segmentation (BMVC2019)

Trainable models and NN optimization tools

This is an ongoing re-implementation of DeepLab_v3_plus on pytorch which is trained on VOC2012 and use ResNet101 for backbone.

Using modified BiSeNet for face parsing in PyTorch

Looking up a generative latent vectors from (face) reference images.

Implementation of "Harmonizing Transferability and Discriminability for Adapting Object Detectors" (CVPR 2020)

Caffe implementation of multiple popular object detection frameworks

Human Pose Estimation from RGB Camera - The repo

A two stage multi-modal loss model along with rigid body transformations to regress 3D bounding boxes

To keep updates with VRU Grand Challenge, please use https://github.com/NExTplusplus/VidVRD-helper

Object Detection Progress Tracker

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

Finger pose classifier for hand landmarks detected by TensorFlow.js handpose model

Some of the ML and DL related reading materials, research papers that I've read

A photo OCR project aims to output DMS messages contained in sign structure images.

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

Web labeling tool for bitmap images and point clouds

Implementation of RefineNet to perform real time instance segmentation in the browser using TensorFlow.js

Face Recognition Using Keras/tensorflow coupled with Node.js Server

Insightface face detection and recognition model that just works out of the box.

Deep Learning and Reinforcement Learning Library for Scientists and Engineers 🔥

Unsupervised instance segmentation via active robot interaction

Data Augmentation For Object Detection

YOLOv5 🚀 in PyTorch > ONNX > CoreML > TFLite

🎨 🎨 深度学习 卷积神经网络教程 ：图像识别，目标检测，语义分割，实例分割，人脸识别，神经风格转换，GAN等🎨🎨 https://dataxujing.github.io/CNN-paper2/

YOLO3D: End-to-end real-time 3D Oriented Object Bounding Box Detection from LiDAR Point Cloud (ECCV 2018)

A curated list of awesome data labeling tools

Convolutional Pose Machines in TensorFlow

Tensorflow implementation : U-net and FCN with global convolution

SuperGlue: Learning Feature Matching with Graph Neural Networks (CVPR 2020, Oral)

Pytorch implementation of GCN architecture for semantic segmentation

[IROS 2020] EAO-SLAM: Monocular Semi-Dense Object SLAM Based on Ensemble Data Association

Change monitor screen when your boss is coming towards you!

Pytorch Implementation -- All about Structure: Adapting Structural Information across Domains for Boosting Semantic Segmentation, CVPR 2019

Create a smart video application using the Intel Distribution of OpenVINO toolkit. The toolkit uses models and inference to run single-class object detection.

ArcFace unofficial Implemented in Tensorflow 2.0+ (ResNet50, MobileNetV2). "ArcFace: Additive Angular Margin Loss for Deep Face Recognition" Published in CVPR 2019. With Colab.