CEM500K is a collection of 496,544 images (224x224 unsigned 8 bit .tiff) of cellular EM images, curated specifically for deep learning applications. See for more details: https://doi.org/10.1101/2020.12.11.421792
data/metadata/cem500k_image_metadata.csv file contains the details of each image file in CEM500K: image_name, source_experiment, doi, imaging_mode, organism, tissue
ResNet50 weights pretrained on CEM500K using MoCoV2 algorithm in PyTorch format are stored in data/pretrained_models/cem500k_mocov2_resnet50_200ep_pth.tar
Files:
Available download options:
Archives and downloads the selected files into an uncompressed zip file.
Depending on the number and size of files to be downloaded, this can take an enormous amount of time.
Also, this feature is unstable and may not work properly, and checksums of downloaded files are not verified.
We recommend using rsync, aspera, globus, etc.
Download a list of selected files.
It is possible to download files by specifying the file list with rsync command, etc.
Archives and downloads the selected files into an uncompressed zip file.
Depending on the number and size of files to be downloaded, this can take an enormous amount of time.
Also, this feature is unstable and may not work properly, and checksums of downloaded files are not verified.
We recommend using rsync, aspera, globus, etc.
Download a list of selected files.
It is possible to download files by specifying the file list with rsync command, etc.