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

Accelerate titles' embeddings. #4492

Merged
merged 1 commit into from
Jan 15, 2025
Merged

Accelerate titles' embeddings. #4492

Show file tree
Hide file tree
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
2 changes: 1 addition & 1 deletion deepdoc/vision/layout_recognizer.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -78,7 +78,7 @@ def __is_garbage(b):
"x0": b["bbox"][0] / scale_factor, "x1": b["bbox"][2] / scale_factor,
"top": b["bbox"][1] / scale_factor, "bottom": b["bbox"][-1] / scale_factor,
"page_number": pn,
} for b in lts if float(b["score"]) >= 0.8 or b["type"] not in self.garbage_layouts]
} for b in lts if float(b["score"]) >= 0.4 or b["type"] not in self.garbage_layouts]
lts = self.sort_Y_firstly(lts, np.mean(
[lt["bottom"] - lt["top"] for lt in lts]) / 2)
lts = self.layouts_cleanup(bxs, lts)
Expand Down
13 changes: 3 additions & 10 deletions rag/svr/task_executor.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -354,16 +354,9 @@ def embedding(docs, mdl, parser_config=None, callback=None):

tk_count = 0
if len(tts) == len(cnts):
tts_ = np.array([])
for i in range(0, len(tts), batch_size):
vts, c = mdl.encode(tts[i: i + batch_size])
if len(tts_) == 0:
tts_ = vts
else:
tts_ = np.concatenate((tts_, vts), axis=0)
tk_count += c
callback(prog=0.6 + 0.1 * (i + 1) / len(tts), msg="")
tts = tts_
vts, c = mdl.encode(tts[0: 1])
tts = np.concatenate([vts for _ in range(len(tts))], axis=0)
tk_count += c

cnts_ = np.array([])
for i in range(0, len(cnts), batch_size):
Expand Down