Comments (12)
Yes running for only 10 epochs is intended behaviour. You can set the number of epochs with the command-line switch --num-epochs
.
from stn-ocr.
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.
from stn-ocr.
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 😅
from stn-ocr.
alright, thank you pretty much
from stn-ocr.
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?
from stn-ocr.
I think it should still work, but you will need to separate the bbox coordinates from the labels.
from stn-ocr.
Alright, thank you pretty much
from stn-ocr.
hi, I still get the above error with 100 epochs.
Could you please tell how I would solve it?
from stn-ocr.
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
?
from stn-ocr.
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.
from stn-ocr.
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.
from stn-ocr.
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 ;)
from stn-ocr.
Related Issues (20)
- compiling on Windows HOT 2
- Stop Iteration exception raised while training. HOT 1
- test on dataset of my own HOT 1
- train accuracy on svhn dataset doesn't improve HOT 9
- i read the paper and have a question: what is the order of the labels? HOT 2
- no file /train/0.png HOT 4
- Install error HOT 8
- Shape error eval_svhn_model.py for SVHN demos. HOT 8
- opencv error HOT 4
- Training HOT 9
- Training does not end. HOT 9
- question about the N grids in paper HOT 3
- ctc_loss.cpp:509:10: fatal error: 'ctc.h' file not found HOT 15
- 2 details questions HOT 5
- can you just give a pretrained model to us? Or a runnable demo that no need for us to train HOT 1
- Evaluation fail! HOT 6
- Train text recognition fail
- train original svhn datasets HOT 1
- load pretrained model error HOT 1
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from stn-ocr.