-
Hi all,
I'm trying to run the SOTA [CPPD model](https://github.com/PaddlePaddle/PaddleOCR/blob/dygraph/doc/doc_en/algorithm_rec_cppd_en.md) fro Scene Text Recognition, but I'm affraid it is not ful…
-
### 🚀 The feature
Ensure that each model has a pretrained available checkpoint
**TensorFlow:**
classification:
- [x] ViT
- [x] MAGC
- [x] MobileNetV3
detection:
- [x] DB_MobileNet…
-
## Description
I converted parseq ocr model from pytorch to onnx and tested it on onnx model and every thing is ok, but when I convert onnx to fp32 or fp16 tensorrt engine, output of the model is ver…
-
### Bug description
I'm using the latest public release and trying to load `vitstr_base` or `parseq` models on PyTorch.
While release notes clearly states `Two new recognition models was added (Vi…
-
As discussed in several GH issues, docTR could very well welcome new architectures for OCR :+1:
Let's use this issue to track this for the next release!
A few things to consider:
- docTR is not …
frgfm updated
8 months ago
-
### Bug description
First of all, good job guys. Keep it up.
My issue is I tried the dbnet + master / sar_resnet31 combination and got very strange results from text recognizers. It looks like a m…
-
### Bug description
While training a Doctr model with my own dataset, I encountered an UnboundLocalError in the compute_loss function of the differentiable_binarization module.
### Code snippet to r…
-
Hello,
I hope you are having a good day. I was working on a task to create a recognizer for Handwriting images.
I am training Visual Transformer Base for my training and using IAM HW dataset (fo…
-
### Bug description
Running doctr for multiple images in a loop causes massive memory leak.
### …
-
### Bug description
I want to use docTR for training of Recognition of Turkish language data. I have created a dataset as specified. The images in the dataset are mixed shapes but all images widht an…