-
### What?
- mmseg의 model type에는 EncoderDecoder 말고도 CascadeEncoderDecoder가 있다 https://github.com/open-mmlab/mmsegmentation/blob/master/mmseg/models/segmentors/cascade_encoder_decoder.py
- CascadeEnco…
km9mn updated
2 years ago
-
**Is your feature request related to a problem? Please describe.**
Maybe it will run better when dealing with large files on small memory devices.
**Describe the solution you'd like**
Reduce peak…
-
This has a few of purposes that I can think of right now:
* Statistical analysis of the entire document when we don't care about organization
* Regex extraction -- e.g. extract all dates even if we …
-
Do I guess correctly that kraken, similarily as the recent versions of tesseract, is unable to distinguish e.g. bold, roman and italics?
-
Using Ubuntu 22.04.
I have tried a fresh new native installation of ocrd_all following standard setup (https://ocr-d.de/en/setup).
Unfortunately, I get the error below - please clarify:
```
...
…
-
如题，附ttl日志：
```
Format: Log Type - Time(microsec) - Message - Optional Info
Log Type: B - Since Boot(Power On Reset), D - Delta, S - Statistic
S - QC_IMAGE_VERSION_STRING=BOOT.BF.3.0.C4.4-00010
…
-
I like to segment roads, curbs, line markings, and backgrounds on a dataset similar to cityscape or camvid. I see ocrnet is the SOTA for the cityscape dataset and tried to pretrained the model of ocrn…
-
Should the OCR-D processor run on a RGB or a binarized image input group?
I think it would be best if the README listed an example, e.g.:
`ocrd-eynollah-segment -I -O SEG-LINE -P xyz abc`
-
In our current OCR predictor, there is a potential issue with rotation at the detection stage:
- by default, `expand=False` in rotations: this means that a segment at the very top right end of the im…
-
This is mainly to aid in documentation. Most components (aside from some preprocessors which already have them) do not include a README file. A per-component README file would be an excellent place to…