电商产品图片分类数据库及相关资源

数据集

Kaggle数据集

• Fashion Product Images Dataset（25G）
  描述： 44k products with multiple category labels, descriptions and high-res images.

• Fashion Product Images (Small)（593MB）
  描述： 44000 products with category labels and images.（上面那个数据集的精简版）

• Quera Bootcamp Product Image Classification（246MB）
  描述： Images of E-Commerce Products for Building Image Classifier Models.Images of E-Commerce products in 10 different classes.

• E-commerce Products Image Dataset（42MB）
  描述： This dataset contains images of Television, Sofas, Jeans and T-shirt. It Actual raw and unstructured image data extracted from online sites.

• E-commerce Product Images（10GB）
  描述： 118,000 labelled images belonging to 42 categories that can be used for classification tasks. The images are from eCommerce websites and classified according to product type.

• E-Commerce Product Images (Multi-label Data)（627MB）
  描述： Multi label image classification

• Cdiscount’s Image Classification Challenge（78.12G）比赛
  描述： 比赛数据集，时间：Dec 15, 2017，可自行查看。

• Shoe Dataset（339MB）
  描述：Shoe Type Classification Data（boots、flip_flops loafers、sandals、sneakers、soccer_shoes）

代码相关资源可以在数据集对应的Code中查看，比赛可以查看高分代码，也可以自行查看Notebook寻找代码资源。

另外，此处只罗列了一些热门的电商产品图片分类数据集资源，如果没有找到合适的，可以进入Datasets或比赛中自行检索。

其他数据集

• UT Zappos50K
  描述： UT Zappos50K (UT-Zap50K) is a large shoe dataset consisting of 50,025 catalog images collected from Zappos.com. The images are divided into 4 major categories — shoes, sandals, slippers, and boots

• UT-Austin Computer Vision Group Datasets
  描述： 许多数据集的集合，带论文

• Amazon product data（很大）
  描述： This dataset contains product reviews and metadata from Amazon, including 143.7 million reviews spanning May 1996 - July 2014.This dataset includes reviews (ratings, text, helpfulness votes), product metadata (descriptions, category information, price, brand, and image features), and links (also viewed/also bought graphs).

代码与文章分享

• product-matching-model
• E-commerce-product-image-classification
  Build a model that automatically classifies the products based on their images for Cdiscount.com
• E-commerce-products-classification-using-images-and-text
• A Dataset and Benchmark for E-commerce Clothing Product Categorization
  Performs automatic taxonomy prediction of Clothing images.Provides a dataset of 183,996 clothing images from 52 categories along with image description and pre-defined taxonomy
• Classifying e-commerce products based on images and text
• Deep Learning Research Papers in Product Matching (Ecommerce)

不足部分欢有兴趣的共同补充维护

其余数据集搜集网站补充

• Google
• UC Irvine Machine Learning Repository
• paperswithcode