You can use SigOpt to optimize any parameter than can be specified as a command line parameter in DeepDIVA (see Customizing Experiments).
To use SigOpt, you must specify:
sig-opt-token
specifies the API token for your SigOpt accountsig-opt-runs
specifies how many optimization runs to re-run the experiment onsig-opt
specifies the path to a text file containing a dictionary with SigOpt parameter valuesFor example
python template/RunMe.py --dataset-folder toy_dataset/MNIST --sig-opt-token <API_token> --sig-opt-runs 10 --sig-opt <path_to_sig_opt_text_file>
A SigOpt text file should be structured as a list of dictionaries, with a dictionary per parameter.
For example, to optimize model-name
and lr
, the SigOpt text file should look like:
[
{"name": "model-name","type": "categorical","categorical_values": ["resnet18", "resnet152"]},
{"name": "lr", "type": "double", "bounds": { "min" : 0.001, "max": 0.01 }}
]
For more information, refer to the SigOpt Docs.