tesseract

tesseract copied to clipboard

Feature Request: Dequantization - convertion of int model to float model

4

@stweil You had mentioned at one point that it should be possible to finetune `fast` models. It will be useful to have this feature as many `fast` models use a...

Shreeshrii

centos 7.9 tesseract5.2 cmake failed! boxchar.cpp:65:75: error...

13

error INFO: /home/engine/wy/3rd/tesseract-5.2.0/src/training/pango/boxchar.cpp: In member function ‘void tesseract::BoxChar::GetDirection(int*, int*) const’: /home/engine/wy/3rd/tesseract-5.2.0/src/training/pango/boxchar.cpp:65:75: error: ‘U_RIGHT_TO_LEFT_ISOLATE’ was not declared in this scope; did you mean ‘U_RIGHT_TO_LEFT_OVERRIDE’? 65 | if (dir == U_RIGHT_TO_LEFT ||...

wuyang-dl

Use Arm Neon equivalent instructions to Intel VNNI

3

... for int dot product.

amitdo

Add framework for implementation of support for AVX512VNNI

9

Using AVX512VNNI instructions is still missing.

stweil

Use Intel VNNI for int dot product

17

There are two variants: * AVX512_VNNI (Tiger Lake, Rocket Lake) - 512bit/256bit/128bit * AVX_VNNI - (upcoming Alder Lake) - 256bit/128bit VNNI replaces 3 simd instructions with one instruction. It seems...

amitdo

Create pain points before running associator to resolve #3892

3

See #3892

Balearica

### Environment * **Tesseract Version**: 5.2.0 * **Commit Number**: 15200c6fe7733f71a6cf52fbc1e4d94150f9f168 * **Platform**: Linux ubuntu 5.15.0-43-generic ### Current Behavior: The legacy engine often fails to recognize words where characters towards the...

Balearica

### Environment * **Tesseract Version**: * **Commit Number**: * **Platform**: windows 10 home 64 bits ### Current Behavior: === Starting training for language 'chi_tra' [Tue Aug 2 16:44:08 2022] /c/Program...

joecheung051

tesseract ocr big size pic dump

2

hi, void TessBaseAPI::SetImage(Pix *pix) API function has a coredump problem when handling a big size pic(system memory no enough) void TessBaseAPI::SetImage(Pix *pix) { if (InternalSetImage()) { if (pixGetSpp(pix) == 4...

wuyang-dl

While running box.train I am getting this error. file name is correct. I was first trying it on tesseract 5.1 but it was giving just error during processing. then i downgraded to 4.0 alpha but it's giving this error.

1

C:\Users\SAMSUNG\Desktop\tesseract training\train>tesseract eng.arial.exp1.tif train.my.exp1 box.train Tesseract Open Source OCR Engine v4.00.00alpha with Leptonica Page 1 Error during processing. ObjectCache(660C5A88)::~ObjectCache(): WARNING! LEAK! object 01015950 still has count 1 (id \Program Files...

ammar3010