E2E-MLT icon indicating copy to clipboard operation
E2E-MLT copied to clipboard

E2E-MLT - an Unconstrained End-to-End Method for Multi-Language Scene Text

Results 31 E2E-MLT issues
Sort by recently updated
recently updated
newest added

I have difficulty in understanding the parameters of affine_grid. The Corresponding line number is 233,234 in train.py As per my understanding, the following things are happening in function process_boxes to...

Respected Sir, Thanks for your work. I am working on images that have only horizontal text. During training following loss values eventually become nan after few steps. Those loss are...

When I use the pre-trained model you provide to continue training on the MLT-2019 dataset, the ctc_loss gets inf values at most steps. Is there something wrong with it? Also,...

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...

Hi, thanks for sharing your amazing code! I have some question, can you help me? 1. I don't know the function of process_boxes in train.py. ` if step > 10000...

make: Entering directory '/media/ai/ashish/OCR/mrz_newTest/E2E-MLT/nms' make: 'adaptor.so' is up to date. make: Leaving directory '/media/ai/ashish/OCR/mrz_newTest/E2E-MLT/nms' Traceback (most recent call last): Command- python3 demo.py -model=e2e-mlt.h5 Error-: ``` File "/media/ai/ashish/OCR/mrz_newTest/E2E-MLT/net_utils.py", line 30, in...

Hi, Sorry for the naïve question, I have downloaded the synthetic images (~38GB), depth maps (15GB), segmentation maps(7GB), and raw images (~9GB) from the SynthText repo. I'm wondering how did...

when i run the demo.py, then the errors as follows: g++: error: unrecognized command line option ‘-fno-plt’ Makefile:10: recipe for target 'adaptor.so' failed make: *** [adaptor.so] Error 1 Anyone can...