939 Open source projects that are alternatives of or similar to Osmdeepod

Handwritten Digit Recognition using Machine Learning and Deep Learning

(This repo is no longer up-to-date. Any updates will be at https://github.com/DeepRegNet/DeepReg/) A demo of the re-factored label-driven registration code, based on "Weakly-supervised convolutional neural networks for multimodal image registration"

📚 A collection of papers about Referring Image Segmentation.

Semi-Supervised Video Object Segmentation (VOS) with Tensorflow. Includes implementation of *MaskRNN: Instance Level Video Object Segmentation (NIPS 2017)* as part of the NIPS Paper Implementation Challenge.

[ECCV 2018] Sparsely Aggreagated Convolutional Networks https://arxiv.org/abs/1801.05895

Convolutional Neural Networks to predict the aesthetic and technical quality of images.

Official Implementation of 'Fast AutoAugment' in PyTorch.

Super Resolution of picture images using deep learning

Text to Speech with PyTorch (English and Mongolian)

Speech Recognition model based off of FAIR research paper built using Pytorch.

Crack detection for an autonomous UAV

PSPNet in Chainer

Object classification with CIFAR-10 using transfer learning

Rethinking the Value of Network Pruning (Pytorch) (ICLR 2019)

Simple Convolutional Neural Network Library

PyTorch Implementation of QuickNAT and Bayesian QuickNAT, a fast brain MRI segmentation framework with segmentation Quality control using structure-wise uncertainty

Labelbox is the fastest way to annotate data to build and ship computer vision applications.

OpenMapTiles Vector Tile Schema Implementation

Download images from Google, Bing, Baidu. 谷歌、百度、必应图片下载.

TI-pooling: transformation-invariant pooling for feature learning in Convolutional Neural Networks

zip code, longitude / latitude of belgian cities | code postal, longitude / latitude des communes belges

A journey into Convolutional Neural Network visualization

🏥 Visualizing Convolutional Networks for MRI-based Diagnosis of Alzheimer’s Disease

Generating automatic trimap through pixel dilation and strongly-connected-component algorithms

Code for the Lovász-Softmax loss (CVPR 2018)

Real time face alignment

Tensorflow 2 implementation of complete pipeline for multiclass image semantic segmentation using UNet, SegNet and FCN32 architectures on Cambridge-driving Labeled Video Database (CamVid) dataset.

This project is an aid to the blind. Till date there has been no technological advancement in the way the blind navigate. So I have used deep learning particularly convolutional neural networks so that they can navigate through the streets.

Robust freeform surface modeling from user 2d sketches.

A sign language interpreter using live video feed from the camera.

دوره 12 ساعته یادگیری عمیق با چارچوب Keras

Video Object Segmentation

✏️ Web-based image segmentation tool for object detection, localization, and keypoints

Identifying people from small audio fragments

ConvNets for Audio Recognition using Google Commands Dataset

Tensorflow Implementation of "Recurrent Convolutional Neural Network for Text Classification" (AAAI 2015)

R interface to the keras library

CNN Image Retrieval in MatConvNet: Training and evaluating CNNs for Image Retrieval in MatConvNet

Deep-Atrous-CNN-Text-Network: End-to-end word level model for sentiment analysis and other text classifications

A Keras Implementation of "A Neural Algorithm of Artistic Style"

Detecting Pneumonia in Chest X-ray Images using Convolutional Neural Network and Pretrained Models

SHAInet - a pure Crystal machine learning library

A tensorflow implementation for EEGLearn

Repository for Region Ensemble Network based Hand Pose Estimation

Minkowski Engine is an auto-diff neural network library for high-dimensional sparse tensors

Trained A Convolutional Neural Network To Play 2048 using Deep-Reinforcement Learning

A Tensorflow implementation of CapsNet(Capsules Net) apply on german traffic sign dataset

Shortest Paths and Travel Time from OpenStreetMap with R

🗺️ Generate an interactive geo heatmap from your Google location data

[CVPR19] DeepCO3: Deep Instance Co-segmentation by Co-peak Search and Co-saliency (Oral paper)

Reducing the size of convolutional neural networks

Using Dijkstra's algorithm ("finding the shortest paths between nodes in a graph") to draw maps 🌍.

基于Tensorflow的常用模型，包括分类分割、新型激活、卷积模块，可在Tensorflow2.X下运行。

Vehicle make and model classification in Tensorflow by fine-tuning VGG16

Quantization of Convolutional Neural networks.

videos, lectures, blogs for Deep Learning

convolutional lstm implementation in pytorch

Brings together information about OpenStreetMap tags and makes it searchable and browsable

3D OpenStreetMap renderer