Skip to content
Open
Changes from all commits
Commits
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
21 changes: 8 additions & 13 deletions DocumentUnderstanding/VGT/object_detection/create_grid_input.py
Original file line number Diff line number Diff line change
Expand Up @@ -134,7 +134,7 @@ def create_grid_dict(tokenizer, page_data):
return grid


def save_pkl_file(grid, output_dir, output_file, model="doclaynet"):
def save_pkl_file(grid, output_dir, filename, model):
"""Save the grid dictionary as a pickle file.

Parameters
Expand All @@ -153,18 +153,13 @@ def save_pkl_file(grid, output_dir, output_file, model="doclaynet"):
-------
None
"""
if model == "doclaynet" or model == "publaynet":
extension = "pdf.pkl"
#os.makedirs(output_dir, exist_ok=True)
if model == 'doclaynet':
with open(os.path.join(output_dir, f"{filename}.pkl"), 'wb') as f:
pickle.dump(grid, f)
else:
extension = "pkl"

pkl_save_location = os.path.join(
output_dir,
f'{output_file}.{extension}')

with open(pkl_save_location, 'wb') as handle:
pickle.dump(grid, handle)

with open(os.path.join(output_dir, f"{filename}.pdf.pkl"), 'wb') as f:
pickle.dump(grid, f)

def select_tokenizer(tokenizer):
"""Select the tokenizer to be used.
Expand Down Expand Up @@ -212,4 +207,4 @@ def select_tokenizer(tokenizer):
for page in range(len(word_grid)):

grid = create_grid_dict(tokenizer, word_grid[page])
save_pkl_file(grid, args.output, f"page_{page}", page, args.model)
save_pkl_file(grid, args.output, f"page_{page}", args.model)