该项目的目标是使用深度学习回归模型预测0至3分的路面质量分数，其中0分用于未磨损的道路，3分用于严重磨损的道路。使用加利福尼亚州湾区周围路面的实时视频和KITTI图像数据集进行训练和测试。Bokeh和Google Maps API用于可视化...
The goal of this project was to predict road surface quality score on scale of 0 to 3 with 0 for unworn roads up to 3 for heavily worn-out roads using deep learning regression models. Real time videos of the road surface around Bay Area, CA and KITTI image dataset was used for training and testing. Bokeh and Google Maps API was used for (2018-06-18, Jupyter Notebook, 20519KB, 下载0次)
计算机视觉大学课程，我在德国法兰克福歌德大学计算机视觉课程（2020年秋季）的作业，
Assignments from my Computer Vision Course (Fall 2020) at Goethe University
Frankfurt, Germany.
, (2021-02-07, Jupyter Notebook, 371248KB, 下载0次)
fpl-ai，一个预测玩家fpl点数的机器学习系统，
A machine learning system that predicts fpl points of players
, (2022-08-18, Jupyter Notebook, 6348KB, 下载0次)
我在德国法兰克福歌德大学的计算机视觉课程（2020年秋季）中的计算机视觉项目。基于Berkeley DeepDrive（BDD100K）数据集的最先进的对象检测算法YOLO和Faster R-CNN之间的性能比较。
My Computer Vision project from my Computer Vision Course (Fall 2020) at
Goethe University Frankfurt, Germany. Performance comparison between state-of-
the-art Object Detection algorithms YOLO and Faster R-CNN based on the
Berkeley DeepDrive (BDD100K) Dataset.
, (2021-03-16, Jupyter Notebook, 498799KB, 下载0次)
斯坦福大学CS231n的PyTorch Tensorflow解决方案：“用于视觉识别的细胞神经网络”
PyTorch/Tensorflow solutions for Stanford s CS231n: "CNNs for Visual
Recognition"
, (2021-01-27, Jupyter Notebook, 24698KB, 下载0次)
我为斯坦福大学的CS231n（用于视觉识别的细胞神经网络）和密歇根大学的EECS 498-007 598-005（用于计算机视觉的深度学习）提供的作业解决方案，2020版。
My assignment solutions for Stanford’s CS231n (CNNs for Visual Recognition)
and Michigan’s EECS 498-007/598-005 (Deep Learning for Computer Vision),
version 2020.
, (2021-04-04, Jupyter Notebook, 82069KB, 下载0次)