Dataset Open Access

Rotation Equivariant CNNs for Digital Pathology

B. S. Veeling, J. Linmans, J. Winkens, T. Cohen, M. Welling

The PatchCamelyon benchmark is a new and challenging image classification dataset. It consists of 327.680 color images (96 x 96px) extracted from histopathologic scans of lymph node sections. Each image is annoted with a binary label indicating presence of metastatic tissue. PCam provides a new benchmark for machine learning models: bigger than CIFAR10, smaller than imagenet, trainable on a single GPU.

Files (8.0 GB)
Name Size
camelyonpatch_level_2_split_test_meta.csv
md5:3455fd69135b66734e1008f3af684566
1.6 MB Download
camelyonpatch_level_2_split_test_x.h5.gz
md5:d8c2d60d490dbd479f8199bdfa0cf6ec
800.9 MB Download
camelyonpatch_level_2_split_test_y.h5.gz
md5:60a7035772fbdb7f34eb86d4420cf66a
3.0 kB Download
camelyonpatch_level_2_split_train_meta.csv
md5:5a3dd671e465cfd74b5b822125e65b0a
15.0 MB Download
camelyonpatch_level_2_split_train_x.h5.gz
md5:1571f514728f59376b705fc836ff4b63
6.4 GB Download
camelyonpatch_level_2_split_train_y.h5.gz
md5:35c2d7259d906cfc8143347bb8e05be7
21.4 kB Download
camelyonpatch_level_2_split_valid_meta.csv
md5:67589e00a4a37ec317f2d1932c7502ca
1.9 MB Download
camelyonpatch_level_2_split_valid_x.h5.gz
md5:d5b63470df7cfa627aeec8b9dc0c066e
806.0 MB Download
camelyonpatch_level_2_split_valid_y.h5.gz
md5:2b85f58b927af9964a4c15b8f7e8f179
3.0 kB Download
1,569
6,666
views
downloads
Views 1,569
Downloads 6,666
Data volume 10.3 TB
Unique views 1,400
Unique downloads 1,917

Share

Cite as