-
Hi, Thanks for your work :)
I'm trying to train CRNN for Synthetic data from VGG lab(about 7 milion) and Focused Scene Text data from ICDAR(about 800).
However, my train loss seems to be not conve…
-
Traceback (most recent call last):
File "train.py", line 249, in
main()
File "train.py", line 246, in main
history = parallel_model.fit_generator(train_data_generator, epochs=FLAGS.ma…
-
hi @argman
I use icdar2017 data to train, based on your results on icdar2015 and 2013（model.ckpt-49491）, but why the test results are zero? 0 text boxes before nms ? This problem has troubled me …
-
@MhLiao There is an error when running train_icdar13.py.
The console shows that:
I0614 14:06:31.362638 9607 layer_factory.hpp:77] Creating layer data
I0614 14:06:31.371596 9607 net.cpp:100] Cre…
-
Hello,
I tried to retrain on ICDAR13 dataset by generating the XML files as mentioned in the readme. I ran the create_data.sh in the data/voc folder after creating the train and test lists. After g…
-
when I train the model ,error occur:
TypeError: batch() got an unexpected keyword argument 'drop_remainder
Could you help me ?
thank you very much.
-
The function `restore_rectangle_rbox` in icdar.py is so complicate that after spent a lot time to read and study it, but I still can't understand it! Could you provide more information or comments ab…
rolai updated
6 years ago
-
Is there an example code integrating this with FasterRCNN as mentioned in the paper?
It seems to me like this solution has potential impact on localization tasks applied to OCR. I'd be curious to s…
-
Thank you for sharing your code! I want to train your model on icdar dataset,but the convert_data_to_tfrecords.py is useless for icdar dataset because the data format in pascalVOC and icdar are diffe…
-
Hi,
I'm trying to reproduce the result in the paper. But it seems not reproducible.
…