BraggNN Validation Dataset
This dataset contains
13799
samples from the training dataset,
and is used to evaluate, and provide metrics for, the models
that were trained on the larger training dataset.
Data
The data are located in the
/data
folder, and store the collected peaks and frames.
There are two datasets in the hdf5 file:
-
Patch
: input to the BraggNN model. It is a 3D array where its first dimension is the index of samples, i.e., 13799. The second and third dimension are the height and width of the patch/peak respectively.
-
ploc
: the peak location for each of the 13799 peaks, i.e., label of the dataset.
Code
** Important **
To run the DLHub versions of these models using GPU resources, users must first request access to the following Globus group:
https://app.globus.org/groups/d0b13474-c265-11ec-9444-51db4d10f5bd/about
Notebooks are provided in the
code-examples
folder to showcase how to load the datasets and run the PyTorch, TRT, and SambaNova models.