Code for DCASE 2020 task 1a and task 1b.

Replace FC2, LeNet-5, VGG, Resnet, Densenet's full-connected layers with MPO

Implementation of "Weight Averaging Improves Knowledge Distillation under Domain Shift" (ICCV 2023 OOD-CV Workshop)

Stochastic Downsampling for Cost-Adjustable Inference and Improved Regularization in Convolutional Networks

Code for paper "EdgeKE: An On-Demand Deep Learning IoT System for Cognitive Big Data on Industrial Edge Devices"

This is an AI-powered advertisement platform that performs Face Detection using Haar Cascade Frontal Face and Wide ResNet to detect your age and gender via an external camera and then show you video advertisements related to the products that suit your corresponding age and gender in real-time.

Weighted Skip Connections are Not Harmful for Deep Nets

Residual Embedding Similarity-based Network Selection (RESNets) for forecasting network dynamics.

The experiment of project

👣 “恒锐杯”鞋印花纹图像类别判定挑战赛

A computer vision web-app that uses deep learning and Residual Neural Networks to identify your Pokémon and then tells you all about it.

Yolov3 with multi backbone

Simple Multi-GPU Implementation of ResNet in Tensorflow

This repository contains the implementation, data-generation pipelines, and trained behavior-cloning models for a kitchen pick-and-place task using IsaacLab. Task: a Franka Emika manipulator picks a tomato soup can (container) from inside a fridge and places it inside the microwave cavity.

High Accuracy ResNet Model under 5 Million parameters.

This repository contains the code of the Bachelor's thesis "Approximation Properties of Residual Neural Networks", supervised by JProf. Diyora Salimova at the University of Freiburg in 2025.

An experiment in training a fully connected residual net to learn the argmax function.

A set of experiments inspired by the paper "Training BatchNorm and Only BatchNorm: On the Expressive Power of Random Features in CNNs" by Jonathan Frankle, David J. Schwab, Ari S. Morcos