Skip to content

GitLab

Unverified Commit 8aa61b0e authored by Xiaomeng Zhao's avatar Xiaomeng Zhao Committed by GitHub
Browse files

Merge pull request #2166 from icecraft/fix/doc_analyze 

fix: support page range
parents 8e8103a8 29c42a1a
Hide whitespace changes
Inline Side-by-side
Showing with 3 additions and 2 deletions
magic_pdf/model/doc_analyze_by_custom_model.py
View file @ 8aa61b0e
...@@ -146,10 +146,11 @@ def doc_analyze( ...@@ -146,10 +146,11 @@ def doc_analyze(
img_dict = page_data.get_image() img_dict = page_data.get_image()
images.append(img_dict['img']) images.append(img_dict['img'])
page_wh_list.append((img_dict['width'], img_dict['height'])) page_wh_list.append((img_dict['width'], img_dict['height']))
if lang is None or lang == 'auto': if lang is None or lang == 'auto':
images_with_extra_info = [(images[index], ocr, dataset._lang) for index in range(len(dataset))] images_with_extra_info = [(images[index], ocr, dataset._lang) for index in range(len(images))]
else: else:
images_with_extra_info = [(images[index], ocr, lang) for index in range(len(dataset))] images_with_extra_info = [(images[index], ocr, lang) for index in range(len(images))]
if len(images) >= MIN_BATCH_INFERENCE_SIZE: if len(images) >= MIN_BATCH_INFERENCE_SIZE:
batch_size = MIN_BATCH_INFERENCE_SIZE batch_size = MIN_BATCH_INFERENCE_SIZE
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment