A Benchmark for Lung and Infection Segmentation in COVID-19 CT scans
Implementation of "CycleMLP: A MLP-like Architecture for Dense Prediction"
Real-time face detection and emotion/gender classification using fer2013/imdb datasets with a keras CNN model and openCV.
🍔🍟🍗 Food analysis baseline with Theseus. Integrate object detection, image classification and multi-class semantic segmentation. 🍞🍖🍕
This is a Kalman filter used to calculate the angle, rate and bias from from the input of an accelerometer/magnetometer and a gyroscope.
Image Polygonal Annotation with Python (polygon, rectangle, circle, line, point and image-level flag annotation).
✅ Solutions to LeetCode by Go, 100% test coverage, runtime beats 100% / LeetCode 题解
MobileNet-SSD, MobileNetV2-SSD/SSDLite on VOC, BDD100K Datasets.
PyTorch implementation of multi-task learning architectures, incl. MTI-Net (ECCV2020).
Multiple Object Tracker, Based on Hungarian algorithm + Kalman filter.
Development of Deep Learning algorithms for Drivable Area Segmentation, Lane Segmentation, Traffic Sign Detection and Classification with data collected and labeled by Ford Otosan.
Objects recognition and classification using machine learning, computer vision and real-time object detection algorithm
My implementation of the original GAT paper (Veličković et al.). I've additionally included the playground.py file for visualizing the Cora dataset, GAT embeddings, an attention mechanism, and entropy histograms. I've supported both Cora (transductive) and PPI (inductive) examples!
QuarkDet lightweight object detection in PyTorch .Real-Time Object Detection on Mobile Devices.
Retinal blood vessel segmentation based on U-Net.
RODSNet: End-to-end Real-time Obstacle Detection Network for Safe Self-driving via Multi-task Learning
Official implementation of "SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers"
Web labeling tool for bitmap images and point clouds
The official project of SimSwap (ACM MM 2020)
This is an official implementation for "Swin Transformer: Hierarchical Vision Transformer using Shifted Windows".
Implementation of the Swin Transformer in PyTorch.
This is an official implementation for "Swin Transformer: Hierarchical Vision Transformer using Shifted Windows" on Semantic Segmentation.
The first competitive instance segmentation approach that runs on small edge devices at real-time speeds.
You Only Look Once for Panopitic Driving Perception.（https://arxiv.org/abs/2108.11250）
A multi-task(detection, tracking, dense estimation, object counting) frame-work based on yolov5+deepsort
multi-task yolov5 with detection and segmentation
🔥🔥🔥🔥 YOLO with Transformers and Instance Segmentation, with TensorRT acceleration! 🔥🔥🔥