Intel® Distribution of OpenVINO™ Toolkit
Community support and discussions about the Intel® Distribution of OpenVINO™ toolkit, OpenCV, and all things computer vision-related on Intel® platforms.
5762 Discussions

any documentation for training text detection

AR92
New Contributor I
452 Views

Hi,

i am trying to train text detection https://github.com/opencv/openvino_training_extensions/tree/develop/tensorflow_toolkit/text_detectio...  and default it is set for image size 1280*768 , but i want to train  it on cropped number plate, i have resized my images to 200*120px size   

 

is there any doc available to understand config.yaml, 

some fields there are like 

min_area: 300

score_map_shape: [128,128]

train_image_shape : [512,512] 

 

can someone please explain these. 

 

Thanks & Regards

A Rawat 

 

Labels (3)
0 Kudos
1 Solution
Munesh_Intel
Moderator
429 Views

Hi Amit,


I would suggest you study the config.py of the original implementation of PixelLink, available at the following link:

https://github.com/ZJULearning/pixel_link/blob/master/config.py


Additionally, I would also encourage you to read the paper, “PixelLink: Detecting Scene Text via Instance Segmentation”, available at the following link:

https://arxiv.org/abs/1801.01315


Regards,

Munesh


View solution in original post

2 Replies
Munesh_Intel
Moderator
430 Views

Hi Amit,


I would suggest you study the config.py of the original implementation of PixelLink, available at the following link:

https://github.com/ZJULearning/pixel_link/blob/master/config.py


Additionally, I would also encourage you to read the paper, “PixelLink: Detecting Scene Text via Instance Segmentation”, available at the following link:

https://arxiv.org/abs/1801.01315


Regards,

Munesh


Munesh_Intel
Moderator
401 Views

Hi Amit,


Intel will no longer monitor this thread since we have provided a solution. If you need any additional information from Intel, please submit a new question.


Regards,

Munesh


Reply