MaskTextSpotter

MaskTextSpotter copied to clipboard

Hi @MhLiao I encountered an error when i try to finetuning pretrain model. Can you help me solving this error? Thanks in advance. Traceback (most recent call last): File "/media/datngo/DATA/Projects/Cores/MaskTextSpotter/tools/train_net.py",...

datnnt1997

Hi, this error occur when running test.sh, anyone have idea how to solve it? Thank you! Here are the details: > File "tools/test_net.py", line 95, in main() File "tools/test_net.py", line...

littlered111

I've tried to recognize the character inside of an image. But I need to recognize the character from the real time video frame. Anyone know how to figure it out...

adifdwimaulana

Why the model trained by this version is stabler than caffe2 version?what's different between this version and caffe2?

1

I had trained masktext spotter model with my own dataset(1000 pics) by pytorch and caffe2 version. I found pytorch model is stabler, acc is higher, and it has better perform...

Rosesor

Calculated!{"precision": 0, "recall": 0.0, "hmean": 0, "AP": 0}

2

i have run the command "python -m torch.distributed.launch --nproc_per_node=1 test_net.py ". In the config file, i used the download “model_finetune.pth” and test it on icdar_test dataset. The output images seems...

zhongdajian

train for long text line detection and recognition

4

Hello @MhLiao , my scenario is mostly long text line included. Should I retrain the model by changing the parameter "MODEL.ROI_MASK_HEAD.POOLER_RESOLUTION_W" from 64 to wider, say 128 or 196 (with...

JimmyJuan

Can you release the total-text's model

1

I want to test the results on total-text, if you release the total-text's model, i will be very grateful.

rkshuai

Typo. It should be 'config_file'

1

https://github.com/MhLiao/MaskTextSpotter/blob/afe22795833dd93bc0b208de06b768ff1144eba9/tools/demo.py#L234

vishaljainai

The released trained model - what datasets was it trained on?

1

@MhLiao Thanks for your work!

ramanishka

RuntimeError: _th_or not supported on CUDAType for Bool

1

On ubuntu16.04, cuda9.0, there is a running error, do not know how to modify it? Traceback (most recent call last): File "tools / train_net.py", line 173, in main () File...

tangtangqin