deep-text-recognition-benchmark

deep-text-recognition-benchmark copied to clipboard

Training my dataset

1

Hi, t using create_lmdb_dataset.py done, I have data.mdb and lock.mdb but when i using this file .mdb to training, I have error is: Filtering the images containing characters which are...

farshokat

problem with training

1

I try to run training, but I have an issue: ``` Traceback (most recent call last): File "train.py", line 15, in from deep_text_recognition_benchmark.utils import CTCLabelConverter, CTCLabelConverterForBaiduWarpctc, AttnLabelConverter, Averager ModuleNotFoundError: No...

yustiks

How did you create lmdb of MjSynth?

7

Hi, I want to know how you guys converted the MjSynth dataset to lmdb using their provided annotations?

SaeedArisha

hello, i'm try to train on my Chinese datasets. During the data processing , i have some confusion below. 1. Should i **Normalize the data into same size** to get...

BENHSU0723

Validation images cannot be read properly even with high accuracy

2

Hi, i am trying to train an ocr model for recognising license plate. I am currently training with None-VGG-BiLSTM-CTC to be used with easyocr. i have a training dataset of...

IAmGreyBunny

video

1

Has anyone try to modify the model to consecutive video frames? It will require to add time dimension (another LSTM)? I wonder if it gives much improvement Regards,

soldierofhell

How to recognize mathematical expressions?

2

Would it be possible to recognize mathematical expressions like fractions (5/7 or 4/9) with this repo?

thrfdth

hello everyone. I was able to run it. I will use this for license plate identification. It takes it very well when there are only letters. But since there is...

ozlem-atiz

I have a recognizer which take a variable length of width but fixed in height, does spatial transformer networks able to train with this kind of network? Maybe we should...

luvwinnie

forward() missing 2 required positional arguments: 'input' and 'text'

4

When I use demo.py predict my images, I modify 'batch_size' from 192->32, 'parser.add_argument('--batch_size', type=int, default=192, help='input batch size')' 'parser.add_argument('--batch_size', type=int, default=32, help='input batch size')' The last cycle will report an...

dikers