Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

StopIteration #21

Open
gydlcc opened this issue Mar 13, 2018 · 12 comments
Open

StopIteration #21

gydlcc opened this issue Mar 13, 2018 · 12 comments

Comments

@gydlcc
Copy link

gydlcc commented Mar 13, 2018

stn-ocr
stn-ocr

Hello dear B:
it is seems like only run 10 epochs
how could i resolve this ?!

@Bartzi
Copy link
Owner

Bartzi commented Mar 13, 2018

Yes running for only 10 epochs is intended behaviour. You can set the number of epochs with the command-line switch --num-epochs.

@gydlcc
Copy link
Author

gydlcc commented Mar 14, 2018

yeah, thank you, as in the picture i uploaded, i wonder that the information between Traceback and StopIteration, is that t means i can't plot the logs? i wanna plot logs, how could i solve it.

@Bartzi
Copy link
Owner

Bartzi commented Mar 14, 2018

I think it can not plot the logs, because the log output of MXNet is not as expected (this changes from time to time, especially if you are using a version of MXNet, other than 0.9.3).
In order to fix this you would have to check the log parsing code in utils/plot_log.py and determine whats different with the log_output and fix the code 😅

@gydlcc
Copy link
Author

gydlcc commented Mar 14, 2018

alright, thank you pretty much

@gydlcc
Copy link
Author

gydlcc commented Mar 18, 2018

Hello there, sorry to bother you again. I noticed that your groundtruth file only include label and didn't include the groundtruth bbox coordinates, if my own data have groundtruth bbox coordinates, is that code still work?

@Bartzi
Copy link
Owner

Bartzi commented Mar 19, 2018

I think it should still work, but you will need to separate the bbox coordinates from the labels.

@gydlcc
Copy link
Author

gydlcc commented Mar 20, 2018

Alright, thank you pretty much

@avasisht-celadon
Copy link

hi, I still get the above error with 100 epochs.
Could you please tell how I would solve it?
capture

@Bartzi
Copy link
Owner

Bartzi commented Nov 15, 2018

It seems that the output of your training looks different than what is expected by the log_plotter are you sure that you are using MXNet in version 0.9.3?

@avasisht-celadon
Copy link

Yes, it was not v0.9.3.
I cloned mxnet again and checked out v0.9.3. Then, I issued "make" to build mxnet. But, I do get the error:-

Makefile:27: mshadow/make/mshadow.mk: No such file or directory
Makefile:28: /home/mxnet/dmlc-core/make/dmlc.mk: No such file or directory
Makefile:126: /home/mxnet/ps-lite/make/ps.mk: No such file or directory
make: *** No rule to make target '/home/mxnet/ps-lite/make/ps.mk'. Stop.

I then did git clone --recursive , the same above error persists.

@avasisht-celadon
Copy link

I solved the above issue, by cloning the submodules. But, Now, ended up with lot of compilation errors.
These errors are absent in latest mxnet versions though.

@Bartzi
Copy link
Owner

Bartzi commented Nov 19, 2018

Well, that is a problem... You could try to use a more modern version of MXNet, but then you'll need to adapt the code that examines the log file and scrapes all the number necessary for plotting from it. You could PR your changes that make the code compatible to a newer version if you like ;)

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

3 participants