deep-text-recognition-benchmark

deep-text-recognition-benchmark copied to clipboard

Unable to load the best accuracy model for prediction

4

### Trained the model with custom dataset and when trying to test it with demo.py file, It gives an the below error #Error ['model input parameters 32 100 20 1...

ashwiniimnair

(Attn-RGB / CTC-RGB) case-sensitive pretrained models

2

@ku21fan Thanks for sharing this wonderful work. You did really a good job. I need to do transfer learning to train the model with a small dataset of mine and...

information-security

test.py is not using CTCLabelConverterForBaiduWarpctc https://github.com/clovaai/deep-text-recognition-benchmark/blob/68a80fe97943a111ff1efaf52a63ad8f0f1c0e5d/test.py#L192-L195 which conflicts with https://github.com/clovaai/deep-text-recognition-benchmark/blob/68a80fe97943a111ff1efaf52a63ad8f0f1c0e5d/test.py#L113-L115 using CTCLabelConverterForBaiduWarpctc can fix it https://github.com/clovaai/deep-text-recognition-benchmark/blob/68a80fe97943a111ff1efaf52a63ad8f0f1c0e5d/train.py#L47-L53

yuyq96

ValueError: num_samples should be a positive integer value, but got num_samples=0

1

When I create lmdb dataset with custom data(e.g. with trdg create multi words in per image), I followed the guide to create dataset, and I trained with below code: `CUDA_VISIBLE_DEVICES=0,1,2,3...

youngsirsk

Korean recognition model

1

Hi, do you have a recognition model trained on Korean characters? Or even better, English+Korean?

barbacot

demo.py ignores characters the weights were trained on

1

Hi First I fine-tuned the None-VGG-BiLSTM-CTC on [pre-trained weights](https://drive.google.com/file/d/1GGC2IRYEMQviZhqQpbtpeTgHO_IXWetG/view) with these characters: `+-/0123456789ABCDEFGHJKLMNPQRSTUVWYZ` ``` CUDA_VISIBLE_DEVICES=0 python3 train.py --train_data result/train --valid_data result/val \ --Transformation None --FeatureExtraction VGG --SequenceModeling BiLSTM --Prediction CTC...

HSILA

How should a cropped image pass to this model?

1

How could I join the Craft model with this when I already have the texts trimmed.

JoelUser

Handwritten OCR

1

I'm starting to work on an handwritten OCR. I would like to know if someone manage to train an handwritten OCR (with recognition rate you were able to produce) and...

v-retoux

Saved model names may be wrong? issue while fine tuning

1

Hello, As many people referenced before me there is an issue while fine tuning the saved model on your own dataset #73 #275 #145 There were multiple solutions suggested: -...

ezzaimsoufiane

Overfitting quickly vs. Data Augmentation

6

I hace almost 25W images to digital recognition by hand , 5W are real and others are Simulation。 It overfitting very fast. both adam(lr = 0.001) and Adadelta(lr = 1)...

macqueen09