ultraopxt Goto Github PK

-using-transfer-learning-and-data-agmentation-to-predict-cifar10

我们将使用resent18模型架构，然后进行数据增强和迁移学习之微调方法，来训练和预测数据库CIFAR-10.准确率94.729%

analyzing-cia-factbook-data-using-sqlite-and-python

In this project, we will analyze CIA Factbook Data Using SQLite and Python.

analyzing-new-york-city-high-school-data

In this project,we will explore relationships between SAT scores and demographic factors(like Safety,Race,Gender and AP Scores)in New York City public schools

anti-fraud-prediction-model-of-credit-card

用XGBoost算法训练信用卡反欺诈预测模型。数据集太大（175MB）超过限制，未能上传，可查询。

arima-time-series-analysis-forecasting-restaurant-sales

ARIMA时间序列分析：预测餐厅销量

clean-and-analyze-employee-exit-surveys

python

cluster-analysis-of-airline-customer-value-based-on-rfm

基于RFM的航空公司客户价值聚类分析

deeplabv3plus-pytorch

DeepLabv3, DeepLabv3+ and pretrained weights on VOC & Cityscapes

designing-and-creating-a-database

SQL数据库项目：创建一个稳健的SQL数据库，储存美国职业棒球大联盟19世纪至今的比赛和球队等数据（包含127个相互关联的CSV文件） 方法： I.资料分析 II.将数据导入SQLite III.设计规范框图 IV.创建无外键表格 V.连接表格

explore-chinook-database-using-sqlite

face-recognize

目标检测项目-视频中的人脸识别，对比mobilenet和YOLO的速度

find-patterns-from-questions-of-the-tv-show-jeopardy

In this project, we'll work with a dataset of Jeopardy questions to figure out some patterns in the questions that could help us win.

finding-high-comment-rates-ways-exploring-hacker-news-posts-

This is a Python project will give hands-on experience with real world examples

finding-the-best-two-markets-to-advertise-in

数据分析项目：帮一家编程网站找到最好的两个市场来投放广告 方法： 1.设定目标 2.理解数据 3.数据清洗：缺失值处理，文字分析（拆分),异常值分析和处理，可视化数据

forecast-customer-purchase-volume-based-on-arima-time-series-analysis

基于ARIMA时间序列分析-预测客户申购量

generative-chatbot

基于seq2seq+attention的生成式（开放式）聊天机器人

hello-world

it's another repository

image-classification-and-prediction-of-skin-cancer

皮肤癌图片分类和预测，kaggle数据集，基于pytorch,通过均衡采样，数据预处理，数据增强，densenet,adam优化器，交叉熵损失函数等技术。结果：precision0.9,recall0.85(仅训练4个周期）

industrial-quality-inspection-project

图像分割实战-工业质检

investigating-fandango-movie-ratings

In October 2015, Walt Hickey from FiveThirtyEight published a popular article where he presented strong evidence which suggest that Fandango's movie rating system was biased and dishonest. In this project, we'll analyze more recent movie ratings data to determine whether there has been any change in Fandango's rating system after Hickey's analysis.

librealsense

Intel® RealSense™ SDK

lottery-addiction-mobile-app

我们希望开发一款专门的手机应用程序，帮助彩票成瘾者更好地估计自己中奖的几率，以此来帮助彩票成瘾者脱离瘾症。我们在这里创建应用程序的逻辑核心并计算概率。

machine-learning-project-predicting-house-prices

机器学习项目：研究美国爱荷华州艾姆斯市2006年至2010年的住房数据，来建立预测模型 方法： I.通过特征工程来 a.去除缺失值超过5%的特征 b.去除有缺失值的非数值特征 c.其他有缺失值的数值列填充众数 d.转换时间列 e.去除明显无关特征 II.通过特征选择来 a.去除和目标相关系数小于0.4的特征 b.去除共线性特征（通过heatmap图） c.去除低方差/变化（小于0.015）特征 d.类型类特征的虚拟化（dummy code,去除分类超过10的特征） III.通过scikit-learn线性回归模型来训练和预测 IV.通过KFolds方法来检验证Mean Squared Error

mobile-app-for-lottery-addiction

movie-recommendation-on-spark

基于Spark的电影推荐,ALS交替最小二乘法，基于矩阵分解的协同过滤推荐。

new-coronavirus-development-trend-feb-6

objectdatasettools

Tools to create pixel-wise object masks, bounding box labels (2D and 3D) and 3D object model (PLY triangle mesh) for object sequences filmed with an RGB-D camera. This project prepares training and testing data for various deep learning projects such as 6D object pose estimation projects singleshotpose, as well as object detection and instance segmentation projects.

ocr-paddle

PaddleOCR识别中英文产品信息

online-3d-bpp-drl

pandas-project-analyzing-used-car-listings-on-ebay-kleinanzeigen