Skip to content
Snippets Groups Projects

Implementation of Deep Learning unit tests, as well as paths to the 2d data for windows users in the UNet jupyter notebook.

Merged ofhkr requested to merge DL_unittests into main
1 file
+ 3
11
Compare changes
  • Side-by-side
  • Inline
+ 3
11
@@ -20,6 +20,7 @@ def train_model(model, hyperparameters, train_loader, val_loader, eval_every = 1
@@ -20,6 +20,7 @@ def train_model(model, hyperparameters, train_loader, val_loader, eval_every = 1
val_loader (torch.utils.data.DataLoader): DataLoader for the validation data.
val_loader (torch.utils.data.DataLoader): DataLoader for the validation data.
eval_every (int, optional): frequency of model evaluation. Defaults to every epoch.
eval_every (int, optional): frequency of model evaluation. Defaults to every epoch.
print_every (int, optional): frequency of log for model performance. Defaults to every 5 epochs.
print_every (int, optional): frequency of log for model performance. Defaults to every 5 epochs.
 
Returns:
Returns:
tuple:
tuple:
@@ -65,12 +66,7 @@ def train_model(model, hyperparameters, train_loader, val_loader, eval_every = 1
@@ -65,12 +66,7 @@ def train_model(model, hyperparameters, train_loader, val_loader, eval_every = 1
for data in train_loader:
for data in train_loader:
inputs, targets = data
inputs, targets = data
inputs = inputs.to(device)
inputs = inputs.to(device)
targets = targets.to(device).unsqueeze(1)
if torch.cuda.is_available():
targets = targets.to(device).type(torch.cuda.FloatTensor).unsqueeze(1)
else:
targets = targets.to(device).type(torch.FloatTensor).unsqueeze(1)
optimizer.zero_grad()
optimizer.zero_grad()
outputs = model(inputs)
outputs = model(inputs)
@@ -100,11 +96,7 @@ def train_model(model, hyperparameters, train_loader, val_loader, eval_every = 1
@@ -100,11 +96,7 @@ def train_model(model, hyperparameters, train_loader, val_loader, eval_every = 1
for data in val_loader:
for data in val_loader:
inputs, targets = data
inputs, targets = data
inputs = inputs.to(device)
inputs = inputs.to(device)
targets = targets.to(device).unsqueeze(1)
if torch.cuda.is_available():
targets = targets.to(device).type(torch.cuda.FloatTensor).unsqueeze(1)
else:
targets = targets.to(device).type(torch.FloatTensor).unsqueeze(1)
with torch.no_grad():
with torch.no_grad():
outputs = model(inputs)
outputs = model(inputs)
Loading