Marqo/amazon-products-eval-100k

该数据集名为GoogleShopping-1m，用于评估Marqo Ecommerce Embedding Models的性能。数据集包含图像、商品ID、查询、标题和位置等特征。测试集包含100,000个样本，大小为1,443,194,395字节。该数据集主要用于电子商务产品的图像和文本检索任务，评估模型在真实世界电子商务搜索场景中的表现。

The GoogleShopping-1m dataset is used to evaluate the Marqo-Ecommerce-B and Marqo-Ecommerce-L models, which are state-of-the-art models for ecommerce product embeddings. The dataset includes features such as images, item_ID, query, title, and position, and provides detailed information about the test set. This dataset is used to evaluate the performance of the models across various tasks, such as Google Shopping Text-to-Image, Google Shopping Category-to-Image, and Amazon Products Text-to-Image tasks.