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

Added dice loss metric + hdf metrics #7

Open
wants to merge 2 commits into
base: main
Choose a base branch
from
Open

Added dice loss metric + hdf metrics #7

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
5d8b8a1
Finished dice loss metric
itsmandrew Jun 13, 2024
74068e7
Added hdf file
itsmandrew Jun 13, 2024
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
36 changes: 18 additions & 18 deletions imageCAS-marimo.py → imageCAS-diceloss.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -143,7 +143,7 @@ def __(os):
@app.cell
def __(data_dicts):
print(len(data_dicts))
train_files, val_files = data_dicts[:-975], data_dicts[-975:]
train_files, val_files = data_dicts[:25], data_dicts[25:35]
print(len(train_files))
print(len(val_files))
return train_files, val_files
Expand Down Expand Up @@ -277,12 +277,9 @@ def __():
def __(
CacheDataset,
DataLoader,
Dataset,
pad_list_data_collate,
train_files,
train_transforms,
val_files,
val_transforms,
):
train_ds = CacheDataset(data=train_files, transform=train_transforms, cache_rate=1.0, num_workers=4)
# train_ds = Dataset(data=train_files, transform=train_transforms)
Expand All @@ -291,17 +288,22 @@ def __(
# to generate 2 x 4 images for network training
train_loader = DataLoader(train_ds, batch_size=4, shuffle=True,
num_workers=1, collate_fn=pad_list_data_collate)
return train_ds, train_loader

# val_ds = CacheDataset(data=val_files, transform=val_transforms, cache_rate=1.0, num_workers=4)
val_ds = Dataset(data=val_files, transform=val_transforms)
val_loader = DataLoader(val_ds, batch_size=1, num_workers=1)

# debug_loader = DataLoader(train_ds, batch_size=1, num_workers=0)
# for i, bruh in enumerate(debug_loader):
# print({key: value.shape for key, value in bruh.items()})
# if i > 10: # Limit the number of batches to inspect
# break
return train_ds, train_loader, val_ds, val_loader
@app.cell
def __(
CacheDataset,
DataLoader,
pad_list_data_collate,
val_files,
val_transforms,
):
val_ds = CacheDataset(data=val_files, transform=val_transforms, cache_rate=1.0, num_workers=4)
# val_ds = Dataset(data=val_files, transform=val_transforms)
val_loader = DataLoader(val_ds, batch_size=4, shuffle=True,
num_workers=1, collate_fn=pad_list_data_collate)
return val_ds, val_loader


@app.cell(hide_code=True)
Expand Down Expand Up @@ -349,16 +351,14 @@ def __(
loss_function,
model,
optimizer,
os,
root_dir,
sliding_window_inference,
torch,
train_ds,
train_loader,
val_loader,
):
max_epochs = 100
val_interval = 101
val_interval = 2
best_metric = -1
best_metric_epoch = -1
epoch_loss_values = []
Expand Down Expand Up @@ -414,8 +414,8 @@ def __(
if metric > best_metric:
best_metric = metric
best_metric_epoch = epoch + 1
torch.save(model.state_dict(), os.path.join(root_dir, "best_metric_model.pth"))
print("saved new best metric model")
# torch.save(model.state_dict(), os.path.join(root_dir, "best_metric_model.pth"))
# print("saved new best metric model")
print(
f"current epoch: {epoch + 1} current mean dice: {metric:.4f}"
f"\nbest mean dice: {best_metric:.4f} "
Expand Down
Loading