Classification models trained on ImageNet. Keras.

This repository contains the source code of our work on designing efficient CNNs for computer vision

Detecting robot grasping positions with deep neural networks. The model is trained on Cornell Grasping Dataset. This is an implementation mainly based on the paper 'Real-Time Grasp Detection Using Convolutional Neural Networks' from Redmon and Angelova.

ImageNet file xml format to Darknet text format

Multi-label classification based on timm.

Nearly Perfect & Easily Understandable PyTorch Implementation of SKNet

Mobilenet v1 trained on Imagenet for STM32 using extended CMSIS-NN with INT-Q quantization support

ImageNet model implemented using the Keras Functional API

PyTorch implementation of DiracDeltaNet from paper Synetgy: Algorithm-hardware Co-design for ConvNet Accelerators on Embedded FPGAs

Identify objects in images using a third-generation deep residual network.

Image recognition and classification using Convolutional Neural Networks with TensorFlow

Making CNNs interpretable.

Machine Learning (Imagenet) User Interface Demo application using Streamlit

Android app containing an Image classifier based on transfer learning CNN using Tensorflow 1.4.1 on Stanford's Imagenet cars dataset

Binary classification to filter and block unsolicited NSFW content from annoying coworkers... --- ...

A deep learning based application which is entitled to help the visually impaired people. The application automatically generates the textual description of what's happening in front of the camera and conveys it to person through audio. It is capable of recognising faces and tell user whether a known person is standing in front of him or not.

Tensorflow implementations of ConvNeXt V1 + V2 models w/ weights, including conversion and evaluation scripts.

Node.js API for Image object detection using tensorflow.js

React UI for Image object detection using tensorflow.js

Fine grained image classification using Bi-linear CNN's and Attention models