Skip to content
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

Jump to bottom

Cleaner early stopping #48

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

Cleaner early stopping #48

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
50 changes: 17 additions & 33 deletions dsm/utilities.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -57,14 +57,10 @@ def pretrain_dsm(model, t_train, e_train, t_valid, e_valid,
risks=model.risks,
optimizer=model.optimizer)
premodel.double()

optimizer = get_optimizer(premodel, lr)

oldcost = float('inf')
patience = 0
costs = []
oldcost, patience = float('inf'), 0
for _ in tqdm(range(n_iter)):

optimizer.zero_grad()
loss = 0
for r in range(model.risks):
Expand All @@ -75,15 +71,18 @@ def pretrain_dsm(model, t_train, e_train, t_valid, e_valid,
valid_loss = 0
for r in range(model.risks):
valid_loss += unconditional_loss(premodel, t_valid, e_valid, str(r+1))
valid_loss = valid_loss.detach().cpu().numpy()
costs.append(valid_loss)
#print(valid_loss)
if np.abs(costs[-1] - oldcost) < thres:
valid_loss = valid_loss.item()

if np.abs(valid_loss - oldcost) < thres:
patience += 1
if patience == 3:
break
oldcost = costs[-1]
elif oldcost > valid_loss:
patience = 0
best_weight = deepcopy(premodel.state_dict())
oldcost = valid_loss

premodel.load_state_dict(best_weight)
return premodel

def _reshape_tensor_with_nans(data):
Expand Down Expand Up @@ -180,30 +179,15 @@ def train_dsm(model,
elbo=False,
risk=str(r+1))

valid_loss = valid_loss.detach().cpu().numpy()
costs.append(float(valid_loss))
dics.append(deepcopy(model.state_dict()))

if costs[-1] >= oldcost:
if patience == 2:
minm = np.argmin(costs)
model.load_state_dict(dics[minm])

del dics
gc.collect()

return model, i
else:
patience += 1
valid_loss = valid_loss.item()
if valid_loss > oldcost:
patience += 1
if patience == 3:
break
else:
patience = 0
best_weights = deepcopy(model.state_dict())
oldcost = valid_loss

oldcost = costs[-1]

minm = np.argmin(costs)
model.load_state_dict(dics[minm])

del dics
gc.collect()

model.load_state_dict(best_weights)
return model, i