Skip to content

fix(model): add explicit pretrain toggle to HIST initialization #2105

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.

Sign up for GitHub

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

Open
ayushozha wants to merge 1 commit into
base: main
Choose a base branch
from
Open

fix(model): add explicit pretrain toggle to HIST initialization #2105

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
39 changes: 21 additions & 18 deletions qlib/contrib/model/pytorch_hist.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -54,6 +54,7 @@ def __init__(
loss="mse",
base_model="GRU",
model_path=None,
pretrain=True,
stock2concept=None,
stock_index=None,
optimizer="adam",
Expand All @@ -78,6 +79,7 @@ def __init__(
self.loss = loss
self.base_model = base_model
self.model_path = model_path
self.pretrain = pretrain
self.stock2concept = stock2concept
self.stock_index = stock_index
self.device = torch.device("cuda:%d" % (GPU) if torch.cuda.is_available() and GPU >= 0 else "cpu")
Expand Down Expand Up @@ -277,24 +279,25 @@ def fit(
evals_result["valid"] = []

# load pretrained base_model
if self.base_model == "LSTM":
pretrained_model = LSTMModel()
elif self.base_model == "GRU":
pretrained_model = GRUModel()
else:
raise ValueError("unknown base model name `%s`" % self.base_model)

if self.model_path is not None:
self.logger.info("Loading pretrained model...")
pretrained_model.load_state_dict(torch.load(self.model_path))

model_dict = self.HIST_model.state_dict()
pretrained_dict = {
k: v for k, v in pretrained_model.state_dict().items() if k in model_dict # pylint: disable=E1135
}
model_dict.update(pretrained_dict)
self.HIST_model.load_state_dict(model_dict)
self.logger.info("Loading pretrained model Done...")
if self.pretrain:
if self.base_model == "LSTM":
pretrained_model = LSTMModel()
elif self.base_model == "GRU":
pretrained_model = GRUModel()
else:
raise ValueError("unknown base model name `%s`" % self.base_model)

if self.model_path is not None:
self.logger.info("Loading pretrained model...")
pretrained_model.load_state_dict(torch.load(self.model_path))

model_dict = self.HIST_model.state_dict()
pretrained_dict = {
k: v for k, v in pretrained_model.state_dict().items() if k in model_dict # pylint: disable=E1135
}
model_dict.update(pretrained_dict)
self.HIST_model.load_state_dict(model_dict)
self.logger.info("Loading pretrained model Done...")

# train
self.logger.info("training...")
Expand Down