-
Hi @csxmli2016
Thank you for creating such a good project!
I want to train this model for English data. I also have some custom LR and HR-paired image data. After reading your paper, I came to …
-
Generally I would love to have some bounding boxes come back with the text response. Primarily for highlighting locations in the original document where the text got pulled. Not sure exactly how I wou…
-
### Feature Name
mPLUG-DocOwl 1.5
### Feature Description
Research about mPLUG-DocOwl 1.5
### Research Findings
## mPLUG-DocOwl 1.5
mPLUG-DocOwl 1.5 is a state-of-the-art multimodal large lang…
-
Recently, I have read a research paper called [`Fooling OCR Systems with Adversarial Text Images`](https://arxiv.org/pdf/1802.05385.pdf)
Basically, it states that making minor changes to an image co…
-
I used V100-32GB to test the lpr-rsr-ext. But it can not train and CUDA out of memory.
![LJB4$XX1IL}UF@J N@E%4FC](https://github.com/Valfride/lpr-rsr-ext/assets/104287808/dba0e101-9a56-49b1-83e2-5312…
-
## Reference
- [paper - 2018 Calamari A High-Performance Tensorflow-based Deep Learning Package for Optical Character Recognition](https://arxiv.org/ftp/arxiv/papers/1807/1807.02004.pdf)
- [paper …
-
![Screenshot 2024-08-24 160058](https://github.com/user-attachments/assets/d5e6993a-982d-4377-b9a7-2698a50a1340)
Debug log shows "non empty source txt list"
OG comic language is Dutch (Netherlan…
-
**Is your feature request related to a problem? Please describe.**
Taking handwritten notes is useful for quickly writing down things with sketches or math without the need for a keyboard, as a repla…
-
Hi, in function process_boxes net.forward_ocr is called 3 times. I am not clear about it.
those lines no are 270,276,381 in train.py
By reading paper, what I understand is the function process_box…
-
Hi,
I Couldn't find in your paper any reference about the OCR-NET, which I would like to train to recognize only numbers (Thought about using transfer learning for the last softmax layer).
I rea…