error at the last epoch

[Jiazheng-Yuan]

error at the last epoch

[Xiaocong6]

hi, I met the same error. How do you solve it?
Hope for your help. Thanks!

[titu1994]

This code wasn't built for eager execution mode on Tensorflow, that may be one of the issues. Otherwise see whether you can drop theast batch inside the dataset.batch method. Maybe that will fix it.

[ranju2015]

Same error I am getting. I have not used eager execution mode.

Epoch 00020: val_loss did not improve from 0.08821
Exception ignored in: <generator object train_generator at 0x7f7ee96fb308>
Traceback (most recent call last):
File "/home/bigdata/s2830250/nima-master-titu1994/utils/data_loader.py", line 128, in train_generator
yield (X_batch, y_batch)
File "/home/bigdata/s2830250/rvenv/lib/python3.5/site-packages/tensorflow/python/client/session.py", line 1587, in exit
self._default_graph_context_manager.exit(exec_type, exec_value, exec_tb)
File "/usr/local/lib/python3.5/contextlib.py", line 77, in exit
self.gen.throw(type, value, traceback)
File "/home/bigdata/s2830250/rvenv/lib/python3.5/site-packages/tensorflow/python/framework/ops.py", line 5233, in get_controller
context.context().context_switches.pop()
File "/home/bigdata/s2830250/rvenv/lib/python3.5/site-packages/tensorflow/python/eager/context.py", line 141, in pop
self.stack.pop()
IndexError: pop from empty list

[ranju2015]

This code wasn't built for eager execution mode on Tensorflow, that may be one of the issues. Otherwise see whether you can drop theast batch inside the dataset.batch method. Maybe that will fix it.

Do you think the training sample needs to be divisible by 200 if my batchsize is 200? My dataset remainder is 21 if I divide total samples by 200.

[ranju2015]

Epoch 00020: val_loss did not improve from 0.04966
Exception ignored in: <generator object val_generator at 0x7f588c71da20>
Traceback (most recent call last):
File "/home/tiger/jiazheng/neural-image-assessment/utils/data_loader.py", line 158, in val_generator
yield (X_batch, y_batch)
File "/home/tiger/jiazheng/venv34/lib/python3.4/site-packages/tensorflow/python/client/session.py", line 1596, in exit
self._default_graph_context_manager.exit(exec_type, exec_value, exec_tb)
File "/usr/lib/python3.4/contextlib.py", line 77, in exit
self.gen.throw(type, value, traceback)
File "/home/tiger/jiazheng/venv34/lib/python3.4/site-packages/tensorflow/python/framework/ops.py", line 5267, in get_controller
context.context().context_switches.pop()
File "/home/tiger/jiazheng/venv34/lib/python3.4/site-packages/tensorflow/python/eager/context.py", line 136, in pop
self.stack.pop()
IndexError: pop from empty list
Exception ignored in: <generator object train_generator at 0x7f58ac2835e8>
Traceback (most recent call last):
File "/home/tiger/jiazheng/neural-image-assessment/utils/data_loader.py", line 123, in train_generator
yield (X_batch, y_batch)
File "/home/tiger/jiazheng/venv34/lib/python3.4/site-packages/tensorflow/python/client/session.py", line 1596, in exit
self._default_graph_context_manager.exit(exec_type, exec_value, exec_tb)
File "/usr/lib/python3.4/contextlib.py", line 77, in exit
self.gen.throw(type, value, traceback)
File "/home/tiger/jiazheng/venv34/lib/python3.4/site-packages/tensorflow/python/framework/ops.py", line 5267, in get_controller
context.context().context_switches.pop()
File "/home/tiger/jiazheng/venv34/lib/python3.4/site-packages/tensorflow/python/eager/context.py", line 136, in pop
self.stack.pop()
IndexError: pop from empty list

after the last epoch, this error happened. I checked the dataset, the ava.txt matches the training images. all the epochs before were good. Thanks!

Did you solve the problem?

[ranju2015]

This code wasn't built for eager execution mode on Tensorflow, that may be one of the issues. Otherwise see whether you can drop theast batch inside the dataset.batch method. Maybe that will fix it.

Would you please elaborate this point little more? I am stuck at this point.

[Jackyinuo]

This code wasn't built for eager execution mode on Tensorflow, that may be one of the issues. Otherwise see whether you can drop theast batch inside the dataset.batch method. Maybe that will fix it.

Would you please elaborate this point little more? I am stuck at this point.

HI， I have been stuck in this error, would you addressed this error???