-
-
Save Avsecz/38ba2a5c1a601094fef8668400960f9a to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
# model type and relative file path to the weights | |
type: keras | |
args: | |
weights: model_files/model.h5 | |
# information about the model. Rendered on kipoi.org | |
info: | |
authors: | |
- name: My Name | |
github: myname | |
name: MyKerasModel | |
doc: > | |
Description of the model shown on kipoi.org. | |
cite_as: https://doi.org/x/y # link to the paper, blog post, ... | |
tags: # under which category dos this model fall | |
- DNA accessibility | |
# which dataloader to use by default (file path) | |
default_dataloader: . | |
# required pip and conda dependencies | |
dependencies: | |
conda: | |
- python>=3.5 | |
- h5py | |
- bioconda::pyfaidx | |
pip: | |
- tensorflow<=1.4.1 | |
- keras==1.2.2 | |
- kipoiseq | |
# input and output array shapes | |
schema: | |
inputs: | |
shape: (600,4) # batch axis is not specified | |
doc: DNA sequence | |
# (Note: The above example shows where the model requires a single array | |
# lists of arrays or dictionary of arrays can be specified by using the yaml synthax) | |
targets: | |
shape: (150, ) | |
doc: Probability of 150 different binary classes | |
column_labels: # Associated names for the predictions | |
- target_labels.txt |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment