wptoux / attention-ocr Goto Github PK
View Code? Open in Web Editor NEWA pytorch implementation of the attention based ocr
License: MIT License
A pytorch implementation of the attention based ocr
License: MIT License
Can you offer the dataset?
for i in range(decoder_output.size(1)):
loss += criterion(decoder_output[:, i, :].squeeze(), target_tensor[:, i + 1])
line 55 in train_utils
throws the following error -
IndexError: index 7 is out of bounds for dimension 1 with size 7
if i change the i+1
in the above mentioned line to i
, the script runs fine but my evaluation accuracy doesn't change at all even though after 100 epochs training accuracy reaches 85%.
To make this hack work, i also have to change i+1
to i
in line 64.
Similar lines are there in train_batch
function too but that doesn't throw an error. Only eval does.
Could you tell me what these particular lines do and how I can fix this issue?
Thanks in advance.
would you mind giving a little more detail about your code
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.