A toolbox for receptive field analysis and visualizing neural network architectures

[BMVC 2024] Official repository of the paper titled "MSA^2 Net: Multi-scale Adaptive Attention-guided Network for Medical Image Segmentation"

Seamless analysis of your PyTorch models (RAM usage, FLOPs, MACs, receptive field, etc.)

A fast and versatile implementation of spike-triggered non-negative matrix factorization (STNMF) based on accelerated/fast HALS algorithms

A Python 3 toolbox for neural receptive field estimation using splines and Gaussian priors.

Revisiting Image Deblurring with an Efficient ConvNet - An efficient CNN performs better than Transformer

Compute CNN receptive field size in pytorch in one line

High-Performance Transformers for Table Structure Recognition Need Early Convolutions

This repository serves as a collection of implementations and resources for various computational neuroscience techniques, including Hopfield's network,hebbian learning and common spatial patterns etc.

This simple web app allows to user to map the receptive field of a chosen artificial neuron in AlexNet, Vgg16, and ResNet18. Deployed on GitHub Pages, but also under construction.

Extract the receptive field of a fully connected cnn.

A repository to work on Deep Learning course. ANN, CNN, VGG, ResNet, etc.

Compute receptive fields as input masks for single neurons in any CNN written in PyTorch.

A simple receptive field calculator for convolutional neural networks (CNN).

This repo contains submissions of all assignments of a EVA by TSAI

Implementation of research paper : "PraNet: Parallel Reverse Attention Network for Polyp Segmentation" in Tensorflow

Numerically compute the Receptive Field of a conv block in PyTorch

Often we spend lots of time calculating the Receptive field of a CNN model.This Module can calculate the receptive field, Output image size from a model object

Compute the theoretical/analytical receptive field of deep neural networks in plain Python.

Program implements a convolutional neural network for classifying images of numbers in the MNIST dataset as either even or odd using GPU framework.