graviti
产品服务
解决方案
知识库
公开数据集
关于我们
Fashion Product Images (Small)
2D Classification
Aesthetics
|...
许可协议: CC-BY-SA 4.0

Overview

Context

Thr growing e-commerce industry presents us with a large dataset waiting to be scraped and researched upon. In addition to professionally shot high resolution product images, we also have multiple label attributes describing the product which was manually entered while cataloging. To add to this, we also have descriptive text that comments on the product characteristics.

Content

Each product is identified by an ID like 42431. You will find a map to all the products in styles.csv. From here, you can fetch the image for this product from images/42431.jpg. To get started easily, we also have exposed some of the key product categories and it's display name in styles.csv.

Inspiration

So what can you try building? Here are some suggestions:

  • Start with an image classifier. Use the masterCategory column from styles.csv and train a convolutional neural network.
  • The same can be achieved via NLP. Extract the product descriptions from styles/42431.json and then run a classifier to get the masterCategory.
  • Try adding more sophisticated classification by predicting the other category labels in styles.csv

Once you are ready to upgrade, go to the high resolution image (2400x1600) dataset:
https://www.kaggle.com/paramaggarwal/fashion-product-images-dataset

数据概要
数据格式
image,
数据量
44.441K
文件大小
70.64MB
发布方
Param Aggarwal
| 数据量 44.441K | 大小 70.64MB
Fashion Product Images (Small)
2D Classification
Aesthetics
许可协议: CC-BY-SA 4.0

Overview

Context

Thr growing e-commerce industry presents us with a large dataset waiting to be scraped and researched upon. In addition to professionally shot high resolution product images, we also have multiple label attributes describing the product which was manually entered while cataloging. To add to this, we also have descriptive text that comments on the product characteristics.

Content

Each product is identified by an ID like 42431. You will find a map to all the products in styles.csv. From here, you can fetch the image for this product from images/42431.jpg. To get started easily, we also have exposed some of the key product categories and it's display name in styles.csv.

Inspiration

So what can you try building? Here are some suggestions:

  • Start with an image classifier. Use the masterCategory column from styles.csv and train a convolutional neural network.
  • The same can be achieved via NLP. Extract the product descriptions from styles/42431.json and then run a classifier to get the masterCategory.
  • Try adding more sophisticated classification by predicting the other category labels in styles.csv

Once you are ready to upgrade, go to the high resolution image (2400x1600) dataset:
https://www.kaggle.com/paramaggarwal/fashion-product-images-dataset

0
立即开始构建AI
graviti
wechat-QR
长按保存识别二维码,关注Graviti公众号

Copyright@Graviti
沪ICP备19019574号
沪公网安备 31011002004865号