[MICCAI'23] Official implementation of "RCS-YOLO: A Fast and High-Accuracy Object Detector for Brain Tumor Detection".

[ICIP'24 Lecture Presentation] Official implementation of "CST-YOLO: A Novel Method for Blood Cell Detection Based on Improved YOLOv7 and CNN-Swin Transformer".

This is a midterm assignment for the Introduction to Artificial Intelligence course at YNU.

💎An easy-to-use PyTorch library for face landmarks detection: training, evaluation, inference, and 100+ data augmentations.🎉

Architectures of convolutional neural networks for image classification in PyTorch

Circle detection model trained from scratch using Shufflenet, Adam optimizer, MSE loss, and IoU (0.5, 0.5-0.95) for evaluation, with 10k/1k/2k train/val/test split, leveraging "reduce lr on plateau" and "early stopping," while pretrained models and augmentation proved less effective.

PyTorch implementations of image classification networks

A project based on deep learning and camera coordinate transformation to achieve human-computer interaction

Models for Computer Vision

Implemented multiple face detection algorithms to accurately count and save recognized faces in a designated folder, enhancing detection accuracy. Integrated ShuffleNet and MTCNN successfully. Developed intelligent graphics for project analysis in Excel. Implemented facial recognition using PCA and Eigenfaces for dataset matching.

A collection of deep learning models (PyTorch implemtation)

More readable and flexible yolov5 with more backbone(gcn, resnet, shufflenet, moblienet, efficientnet, hrnet, swin-transformer, etc) and (cbam，dcn and so on), and tensorrt

NanoDet-Plus⚡Super fast and lightweight anchor-free object detection model. 🔥Only 980 KB(int8) / 1.8MB (fp16) and run 97FPS on cellphone🔥

YOLO5Face: Why Reinventing a Face Detector (https://arxiv.org/abs/2105.12931) ECCV Workshops 2022)

Practice on cifar100(ResNet, DenseNet, VGG, GoogleNet, InceptionV3, InceptionV4, Inception-ResNetv2, Xception, Resnet In Resnet, ResNext,ShuffleNet, ShuffleNetv2, MobileNet, MobileNetv2, SqueezeNet, NasNet, Residual Attention Network, SENet, WideResNet)

A semester project using ShuffleNet, MobileNetV3 Small & ResNet50 to classify real and fake faces with the specified dataset that taken from Kaggle.

Skin Cancer Detection: Leveraging Hybrid Deep Learning Models and Traditional Machine Learning Classifiers

Various codes and scripts used during AI research. Orginally developed in the Binary_label_predictions_with_CNNs repository

Various codes and scripts used during AI research, all neatly organised

This code includes classification and detection tasks in Computer Vision, and semantic segmentation task will be added later.