places365
places365-256pxPlaces365-customi1-places365-challenge2016-tfrecordi1: A Simple and Fully Open Recipe for Strong Text-to-Image Models
Boya Zeng, Tianze Luo, Shu Pu, Jucheng Shen, Taiming Lu, Gabriel Sarch, Zhuang Liu
Princeton University
[arXiv][code][model][project page]
Overview
To prepare the dataset for training, we store the image-caption pairs as TFRecords.
This HuggingFace dataset contains the TFRecords corresponding to the places365-challenge2016 dataset at 256×256 resolution.
It also serves as an example of what a dataset… See the full description on the dataset page: https://huggingface.co/datasets/zlab-princeton/i1-places365-challenge2016-tfrecord.i1-places365-challenge2016-512-resolution-1m-tfrecordi1: A Simple and Fully Open Recipe for Strong Text-to-Image Models
Boya Zeng, Tianze Luo, Shu Pu, Jucheng Shen, Taiming Lu, Gabriel Sarch, Zhuang Liu
Princeton University
[arXiv][code][model][project page]
Overview
To prepare the dataset for training, we store the image-caption pairs as TFRecords.
This HuggingFace dataset contains the TFRecords corresponding to the places365-challenge2016 dataset at 512×512 resolution. Concretely, we only retain raw images with a shorter… See the full description on the dataset page: https://huggingface.co/datasets/i1-datasets/i1-places365-challenge2016-512-resolution-1m-tfrecord.Places365-custom-trainPlaces365-Validation
