Cryo
Datasets
All datasets matching “Cryo”CryoLithe-training-datasetThe training Dataset for CryoLithe Models
The dataset contains selected tilt series, tilt angles, and corresponding cryo-CARE+IsoNet and Icecream reconstructions using odd/even pairs. For EMPIAR-11058
Icecream reconstructions were obtained by splitting across angles.
Whenever available, we also provide dose-fractionated tilt series.
Dataset format:
Files ending with '.rawtlt' or '.tlt' correspond to the tilt angles.
Files ending with '_corrected.mrc' correspond to cryo-CARE+IsoNet… See the full description on the dataset page: https://huggingface.co/datasets/sada-group/CryoLithe-training-dataset.CryoAnomalymotif-cryomap-dbcryocare-v0.3.0-parity-evidence
cryoCARE v0.3 CPU parity evidence
This dataset contains only JSON and Safetensors. It preserves deterministic inputs,
the exact extracted Keras-layout tensor inventory, vendor TensorFlow outputs, native
PyTorch outputs, and numerical metrics. The original HDF5 is not uploaded; its exact
hash and size remain in vendor/vendor-capture.json and the model conversion record.
The corresponding native Safetensors package is
scitomo/cryocare-v0.3.0-synthetic-parity.
cryosentinel-glof-v3
CryoSentinel-GLOF v3 — Multimodal Glacial Lake Chips for High Mountain Asia
A multimodal Earth-observation dataset of 42,237 image chips centred on glacial lakes across twelve High Mountain Asia sub-regions. Each chip stacks three co-registered modalities — Sentinel-1 SAR (VV, VH), Sentinel-2 optical (12 bands, L2A), and Copernicus DEM (1 band) — together with a binary water-extent mask derived from the Kumar & Vijay (2026) PANGAEA glacial-lake inventory.
This dataset is the… See the full description on the dataset page: https://huggingface.co/datasets/abzal-glw/cryosentinel-glof-v3.cryoem-acquisition
Cryo-EM Autonomous Acquisition Dataset
Data for training agents that decide which grid square and foil hole to image next during a cryo-EM session, so a sample reaches its target in the fewest acquisitions and the least instrument time.
Four EPU sessions derived from public EMPIAR depositions. Every acquisition carries what a live cryoSPARC Live session reports about 70 s after the exposure (particles, CTF fit, ice, 2D-class orientation profile), plus pre-acquisition hole… See the full description on the dataset page: https://huggingface.co/datasets/xkronosx/cryoem-acquisition.