accuracy.md

July 7, 2017 ยท View on GitHub

Basenji

Sequential regulatory activity predictions with deep convolutional neural networks.

Accuracy

basenji_test.py

Compute accuracy statistics for a trained model on a held out test set.

ArgumentsTypeDescription
params_fileText tableModel configuration parameters.
model fileTensorFlow Saver fileTrained Basenji model.
test_hdf5_fileHDF5Output HDF5 file with test_in/test_out keys.

basenji_test_genes.py

Compute accuracy statistics for a trained model at gene TSSs.

ArgumentsTypeDescription
params_fileText tableModel configuration parameters.
model fileTensorFlow Saver fileTrained Basenji model.
genes_hdf5_fileHDF5HDF5 file with gene sequences and descriptions.