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

fix: linknet hyperparameters postprocessing + demo for rotation model #865

Merged
merged 3 commits into from
Mar 22, 2022
+21 −16
Merged

fix: linknet hyperparameters postprocessing + demo for rotation model #865

Show file tree
Hide file tree
Changes from 1 commit
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
ddec3a8
fix: linknet parameters
charlesmindee Mar 16, 2022
5e10407
feat: add demo rotation
charlesmindee Mar 16, 2022
bbdcce3
feat: add rotation in demo
charlesmindee Mar 16, 2022
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
Prev Previous commit
feat: add rotation in demo
  • Loading branch information
@charlesmindee
charlesmindee committed Mar 16, 2022
commit bbdcce3916f241d39487b65b5ee3682a758cdc7d
10 changes: 7 additions & 3 deletions demo/app.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -73,7 +73,10 @@ def main():

else:
with st.spinner('Loading model...'):
predictor = ocr_predictor(det_arch, reco_arch, pretrained=True)
predictor = ocr_predictor(
det_arch, reco_arch, pretrained=True,
assume_straight_pages=(det_arch != "linknet_resnet18_rotation")
)

with st.spinner('Analyzing...'):

Expand All @@ -97,8 +100,9 @@ def main():

# Page reconsitution under input page
page_export = out.pages[0].export()
img = out.pages[0].synthesize()
cols[3].image(img, clamp=True)
if det_arch != "linknet_resnet18_rotation":
charlesmindee marked this conversation as resolved.
Show resolved Hide resolved
img = out.pages[0].synthesize()
cols[3].image(img, clamp=True)

# Display JSON
st.markdown("\nHere are your analysis results in JSON format:")
Expand Down
18 changes: 10 additions & 8 deletions doctr/utils/visualization.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -219,13 +219,16 @@ def visualize_page(
int(page['dimensions'][1] * word['geometry'][0][0]),
int(page['dimensions'][0] * word['geometry'][0][1])
)
ax.text(
*text_loc,
word['value'],
size=10,
alpha=0.5,
color=(0, 0, 1),
)

if len(word['geometry']) == 2:
charlesmindee marked this conversation as resolved.
Show resolved Hide resolved
# We draw only if boxes are in straight format
ax.text(
*text_loc,
word['value'],
size=10,
alpha=0.5,
color=(0, 0, 1),
)

if display_artefacts:
for artefact in block['artefacts']:
Expand All @@ -252,7 +255,6 @@ def visualize_page(
def synthesize_page(
page: Dict[str, Any],
draw_proba: bool = False,
font_size: int = 13,
font_family: Optional[str] = None,
) -> np.ndarray:
"""Draw a the content of the element page (OCR response) on a blank page.
Expand Down