Skip to content

set chunk numpy to pandas df #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.

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

set chunk numpy to pandas df #2

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
16 changes: 15 additions & 1 deletion tbccsi/tbccsi_main.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -73,6 +73,13 @@ def run_virchow_pred(sample_id,
print(f"Processing {len(coords_df)} tiles in {len(df_chunks)} RAM batches...")

for i, chunk in enumerate(tqdm(df_chunks, desc="Processing Batches")):

if isinstance(chunk, np.ndarray):
if chunk.ndim == 2 and chunk.shape[1] == len(coords_df.columns):
chunk = pd.DataFrame(chunk, columns=coords_df.columns)
else:
chunk = pd.DataFrame(chunk)

if chunk.empty: continue

batch_images = []
Expand Down Expand Up @@ -232,10 +239,17 @@ def run_virchow_embed(sample_id,
# Process in chunks to manage RAM
num_chunks = max(1, len(coords_df) // RAM_BATCH_SIZE)
df_chunks = np.array_split(coords_df, num_chunks)

print(f"Processing {len(coords_df)} tiles in {len(df_chunks)} RAM batches...")

for i, chunk in enumerate(tqdm(df_chunks, desc="Extracting Embeddings")):

if isinstance(chunk, np.ndarray):
if chunk.ndim == 2 and chunk.shape[1] == len(coords_df.columns):
chunk = pd.DataFrame(chunk, columns=coords_df.columns)
else:
chunk = pd.DataFrame(chunk)

if chunk.empty:
continue

Expand Down