DexiNed: Dense EXtreme Inception Network for Edge Detection
-
Updated
Mar 8, 2023 - Python
DexiNed: Dense EXtreme Inception Network for Edge Detection
real-time fire detection in video imagery using a convolutional neural network (deep learning) - from our ICIP 2018 paper (Dunnings / Breckon) + ICMLA 2019 paper (Samarth / Bhowmik / Breckon)
Conv-TasNet: Surpassing Ideal Time-Frequency Magnitude Masking for Speech Separation Pytorch's Implement
Joint scene classification and semantic segmentation with FuseNet
A Fast Dense Spectral-Spatial Convolution Network Framework for Hyperspectral Images Classification(Remote Sensing 2018)
DVDnet: A Simple and Fast Network for Deep Video Denoising
"LipNet: End-to-End Sentence-level Lipreading" in PyTorch
An Image classifier to identify whether the given image is Batman or Superman using a CNN with high accuracy. (From getting images from google to saving our trained model for reuse.)
A Benchmark for Semantic Segmentation of Waterbody Images
edepth is an open-source, trainable CNN-based model for depth estimation from single images, videos, and live camera feeds.
Framework for the automatic creation of CNN architectures
A tensorflow implementation of recognition of handwritten Chinese characters.
Code for the paper "Curriculum Dropout", ICCV 2017
Using Cartesian Genetic Programming to find an efficient Convolutional Neural Network architecture
Code for the paper "Training CNNs with Selective Allocation of Channels" (ICML 2019)
Glaucoma detection automation project. Trained a binary image classifier using CNNs and deployed as a streamlit web app. It takes eye (retinal scan) image as input and outputs whether the person is affected by glaucoma or not.
Using Convolutional Neural Networks to predict aesthetics of photographs
pyTorch-text-classification
The goal of the project is to classify the vehicles, count their frequency, track them using unique ID and provide safety measures to the users by flagging the suspicious ones.
The final project for ECE C147/C247, which evaluates the performance of CNN + Transformer and CNN + GRU + SimpleRNN models on an EEG dataset.
Add a description, image, and links to the cnn-architecture topic page so that developers can more easily learn about it.
To associate your repository with the cnn-architecture topic, visit your repo's landing page and select "manage topics."