-
Notifications
You must be signed in to change notification settings - Fork 366
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.
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
OCR example #6560
OCR example #6560
Conversation
Deployed docs
|
please add a bit of a description and screenshots to the PR so that if someone comes here from the changelog they know what this is about :) |
having issues running the example on mac.
is the example generally not mac compatible? |
…ndreasnaoum-ocr-example
I still can't run it on Mac:
|
after install in a fresh virtual env I get:
installing |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
I reckon this example is one of those that only runs on a single core for an eternity if you don't have an nvidia gpu? Takes ages to do anything on my Mac. Needs a note in the description, probably even in the --help text.
As of writing it has been running for 10min without any response (wtf, it's ocr, we used to do this in the 70s -.-), would it be possible to show some progress bar on the model execution? At least there should be a message when it starts, right now I'm not sure if the process is actually just stuck
examples/python/ocr/ocr.py
Outdated
|
||
|
||
def main() -> None: | ||
parser = argparse.ArgumentParser(description="OCR Example - Layout Analysis and Text Detections") |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
maybe add a note that this will automatically download the model 🤔
which btw. in my case took ages since it downloaded it with less than 100kib/s 😞
it hasn't done anything after 20min runtime on my M1max macbook. We probably should just earmark it as not supported on Mac..? |
I'm also using it on an M1 macbook and the maximum wait time was 30 seconds. I will try to build it on an new environment to check the time @Wumpf |
Run guidelines Co-authored-by: Andreas Reich <andreas@rerun.io>
Co-authored-by: Andreas Reich <andreas@rerun.io>
Do you have any suggestions for the name? The description is this: I wanted to keep a simple name; that's why it was set it as OCR, but we can change it. |
|
pixi environment fix confirmed |
demo now also works from pixi |
Name changed to PaddleOCR @Wumpf |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
left one more question / thing that needs fixing, but otherwise I believe we're good to go!
Readme looks fine to me @Wumpf |
What
New example for Document Analysis and Text Detection (OCR).
This example demonstrates the ability to visualize and verify the document layout analysis and text detection using the PaddleOCR. PP-Structure used for this task, which is an intelligent document analysis system developed by the PaddleOCR team, which aims to help developers better complete tasks related to document understanding such as layout analysis and table recognition. In the layout analysis task, the image first goes through the layout analysis model to divide the image into different areas such as text, table, figure and more, and then analyze these areas separately. The classification of layouts and the text detection (including confidence levels) are visualized in the Rerun viewer. Finally, the recovery text document section presents the restored document with sorted order. By clicking on the restored text, the text area will be highlighted.
Checklist
main
build: rerun.io/viewernightly
build: rerun.io/viewerTo run all checks from
main
, comment on the PR with@rerun-bot full-check
.