2022 Open source projects that are alternatives of or similar to Imgclsmob

Programming Assignments and Lectures for Stanford's CS 231: Convolutional Neural Networks for Visual Recognition

Image Test Time Augmentation with PyTorch!

A light-weight, power efficient, and general purpose convolutional neural network

Real-time pose estimation accelerated with NVIDIA TensorRT

RMDL: Random Multimodel Deep Learning for Classification

MobileNetV3 in pytorch and ImageNet pretrained models

Deep Neural Networks Improve Radiologists' Performance in Breast Cancer Screening

Curated list of Machine Learning, NLP, Vision, Recommender Systems Project Ideas

Gluon to PyTorch deep neural network model converter

Setup and customize deep learning environment in seconds.

a pytorch lib with state-of-the-art architectures, pretrained models and real-time updated results

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

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.

MXNet Gluon Synchronized Batch Normalization Preview

PyTorch Implementation of Stacked U-Nets (SUNets)

ResNet benchmark by Keras(TensorFlow), Keras(MXNet), Chainer, PyTorch using Google Colab

Gluon implementation of "Objects as Points", aka "CenterNet"

Classification models trained on ImageNet. Keras.

(ECCV 2020) Tensorflow implementation of A Generic Visualization Approach for Convolutional Neural Networks

Fast image augmentation library and an easy-to-use wrapper around other libraries. Documentation: https://albumentations.ai/docs/ Paper about the library: https://www.mdpi.com/2078-2489/11/2/125

Ranking made easy

🍊 🎑 Orange3 add-on for dealing with image related tasks

implement AlexNet with C / convolutional nerual network / machine learning / computer vision

SegNet implementation & experiments in Chainer

Generalized Data-free Universal Adversarial Perturbations

Simulate quantization and quantization aware training for MXNet-Gluon models.

Machine Learning University: Accelerated Computer Vision Class

A framework for training segmentation models in pytorch on labelme annotations with pretrained examples of skin, cat, and pizza topping segmentation

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

A lightweight convolutional neural network

CNNs for semantic segmentation using Keras library

3D point cloud datasets in HDF5 format, containing uniformly sampled 2048 points per shape.

An open source framework for deep learning on satellite and aerial imagery.

Keras-tensorflow implementation of PersonLab (https://arxiv.org/abs/1803.08225)

Towards Building an Intelligent Anti-Malware System: A Deep Learning Approach using Support Vector Machine for Malware Classification

PointCNN: Convolution On X-Transformed Points (NeurIPS 2018)

Grid-GCN for Fast and Scalable Point Cloud Learning

Classification with PyTorch.

Mobilenet V2(Inverted Residual) Implementation & Trained Weights Using Tensorflow

WB color augmenter improves the accuracy of image classification and image semantic segmentation methods by emulating different WB effects (ICCV 2019) [Python & Matlab].

[ICCV 2019] Harmonious Bottleneck on Two Orthogonal Dimensions

Crop/Weed Field Image Dataset

this simple tutorial will introduce how to use im2rec for mx.image.ImageIter , ImageDetIter and how to use im2rec for COCO DataSet

Collaborate & label any type of data, images, text, or documents, in an easy web interface or desktop app.

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

FrostNet: Towards Quantization-Aware Network Architecture Search

Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformers

CRF-RNN PyTorch version http://crfasrnn.torr.vision

Neural Style and MSG-Net

A label tool aim to reduce semantic segmentation label time, rectangle and polygon annotation is supported

Code for the neural architecture search methods contained in the paper Efficient Forward Neural Architecture Search

Collections of model quantization algorithms

Object classification with CIFAR-10 using transfer learning

Keras implementation for Pointnet

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

PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space

Test Time Augmentation (TTA) wrapper for computer vision tasks: segmentation, classification, super-resolution, ... etc.

An opensource lib. for vehicle vision applications (written by MATLAB), lane marking detection, road segmentation