-
Notifications
You must be signed in to change notification settings - Fork 2
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Updated training script for torch prescriptors to allow config #75
Conversation
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Basic config file similar to the ESP one.
parser.add_argument("--config_path", type=str, required=True) | ||
args = parser.parse_args() | ||
with open(Path(args.config_path), "r", encoding="utf-8") as f: | ||
config = json.load(f) |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
The only argument we need is a config file. More customizability can come in the subset of data we use, what type of predictor we use, etc. but for now this simple one works
"hidden_size": 16, | ||
"out_size": len(constants.RECO_COLS)} | ||
if "seed_dir" in config["evolution_params"].keys(): | ||
config["evolution_params"]["seed_dir"] = Path(config["evolution_params"]["seed_dir"]) |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Convert seed dir string into Path object here so that we don't have to do it inside the TorchPrescriptor object and can continue assuming that what gets passed in is a Path
No description provided.