text-detection-ctpn icon indicating copy to clipboard operation
text-detection-ctpn copied to clipboard

Published 20 hours ago • verified publisher icon eragonruan

When running train.py code,the code be terminated with no error message

Open Allen-lz opened this issue 6 years ago • 11 comments

Hello, author. After I entered the command ‘python ./main/train.py’.then,without any error message, the ccode was stopped running . The terminal output the following:

/home/cv_user/anaconda3/lib/python3.6/site-packages/tensorflow/python/ops/gradients_impl.py:112: UserWarning: Converting sparse IndexedSlices to a dense Tensor of unknown shape. This may consume a large amount of memory. "Converting sparse IndexedSlices to a dense Tensor of unknown shape. " WARNING:tensorflow:Variable Conv/weights missing in checkpoint data/vgg_16.ckpt WARNING:tensorflow:Variable Conv/biases missing in checkpoint data/vgg_16.ckpt WARNING:tensorflow:Variable BiLSTM/bidirectional_rnn/fw/lstm_cell/kernel missing in checkpoint data/vgg_16.ckpt WARNING:tensorflow:Variable BiLSTM/bidirectional_rnn/fw/lstm_cell/bias missing in checkpoint data/vgg_16.ckpt WARNING:tensorflow:Variable BiLSTM/bidirectional_rnn/bw/lstm_cell/kernel missing in checkpoint data/vgg_16.ckpt WARNING:tensorflow:Variable BiLSTM/bidirectional_rnn/bw/lstm_cell/bias missing in checkpoint data/vgg_16.ckpt WARNING:tensorflow:Variable BiLSTM/weights missing in checkpoint data/vgg_16.ckpt WARNING:tensorflow:Variable BiLSTM/biases missing in checkpoint data/vgg_16.ckpt WARNING:tensorflow:Variable bbox_pred/weights missing in checkpoint data/vgg_16.ckpt WARNING:tensorflow:Variable bbox_pred/biases missing in checkpoint data/vgg_16.ckpt WARNING:tensorflow:Variable cls_pred/weights missing in checkpoint data/vgg_16.ckpt WARNING:tensorflow:Variable cls_pred/biases missing in checkpoint data/vgg_16.ckpt continue training from previous checkpoint 50000

If you know how to solve it, please tell me the solution. Thank you!

Allen-lz avatar Feb 24 '19 03:02 Allen-lz

I have been trying to train the model, but the training process stops without any error message.

continue training from previous checkpoint 50000 WARNING:tensorflow:From /home/paperspace/.local/lib/python3.6/site-packages/tensorflow/python/training/saver.py:1266: checkpoint_exists (from tensorflow.python.training.checkpoint_management) is deprecated and will be removed in a future version. Instructions for updating: Use standard file APIs to check for files with this prefix.

Any suggestion?

niddal-imam avatar Mar 01 '19 19:03 niddal-imam

I have the same problem. How do you resolve it ?

yuzy007 avatar Mar 09 '19 16:03 yuzy007

有人解决这个问题吗

18813055625 avatar Mar 13 '19 13:03 18813055625

tf.app.flags.DEFINE_boolean('restore', True, '') set the 'True' to 'False',and you can run

Allen-lz avatar Mar 14 '19 16:03 Allen-lz

tf.app.flags.DEFINE_boolean('restore', True, '') set the 'True' to 'False',and you can run

Thanks,this solve my problem，thanks again

LeiGan0215 avatar Mar 31 '19 07:03 LeiGan0215

tf.app.flags.DEFINE_boolean('restore', True, '') set the 'True' to 'False',and you can run

Thanks,this solve my problem，thanks again

An error appears after running AttributeError: Can't pickle local object 'GeneratorEnqueuer.start..data_generator_task'

(D:\Anaconda3) C:\Users\s\Desktop\ctpn3>Traceback (most recent call last): File "", line 1, in File "D:\Anaconda3\lib\multiprocessing\spawn.py", line 106, in spawn_main exitcode = _main(fd) File "D:\Anaconda3\lib\multiprocessing\spawn.py", line 116, in _main self = pickle.load(from_parent) EOFError: Ran out of input

What should I do

Donaghys avatar Apr 09 '19 09:04 Donaghys

https://github.com/eragonruan/text-detection-ctpn/issues/272

cellphonef avatar May 08 '19 09:05 cellphonef

tf.app.flags.DEFINE_boolean('restore', True, '') set the 'True' to 'False',and you can run

it works

cvnli avatar May 15 '19 01:05 cvnli

tf.app.flags.DEFINE_boolean('restore', True, '') set the 'True' to 'False',and you can run

Thanks,this solve my problem，thanks again

An error appears after running AttributeError: Can't pickle local object 'GeneratorEnqueuer.start..data_generator_task'

(D:\Anaconda3) C:\Users\s\Desktop\ctpn3>Traceback (most recent call last): File "", line 1, in File "D:\Anaconda3\lib\multiprocessing\spawn.py", line 106, in spawn_main exitcode = _main(fd) File "D:\Anaconda3\lib\multiprocessing\spawn.py", line 116, in _main self = pickle.load(from_parent) EOFError: Ran out of input

What should I do

Have resolved this EOF error? I am facing the same problem

GangaraniRajendran avatar Oct 16 '19 07:10 GangaraniRajendran

tf.app.flags.DEFINE_boolean('restore', True, '') set the 'True' to 'False',and you can run

Thanks,this solve my problem，thanks again

An error appears after running AttributeError: Can't pickle local object 'GeneratorEnqueuer.start..data_generator_task' (D:\Anaconda3) C:\Users\s\Desktop\ctpn3>Traceback (most recent call last): File "", line 1, in File "D:\Anaconda3\lib\multiprocessing\spawn.py", line 106, in spawn_main exitcode = _main(fd) File "D:\Anaconda3\lib\multiprocessing\spawn.py", line 116, in _main self = pickle.load(from_parent) EOFError: Ran out of input What should I do

Have resolved this EOF error? I am facing the same problem

Found the solution.... changing num_workers to 1 and multiprocessing to False solved the issue

GangaraniRajendran avatar Oct 18 '19 11:10 GangaraniRajendran

multiprocessing

Can you be more specific? Where is this variable?3Q~

titan27149 avatar Feb 02 '20 08:02 titan27149