Comments (2)
@yuvval I don't think this should be the intended behaviour. You can make change the code to allow it to be user-definable in the function definition in optimizers.py
.
The version of Adam implemented here has now been superseeded, so you might want to check the latest version of the paper for more details on the default hyperparameters.
I have implemented both of these changes in my fork of the code.
from arctic-captions.
Thanks @elliottd!
from arctic-captions.
Related Issues (20)
- Instructions to re-train the model: where to start?
- Instruction to visualize hard attention HOT 3
- argument 'model' in the 'main function' (generate_caps.py)
- Split problem
- cannot figure out the code
- How soon does the sanity check look like working fine?
- where is model_name.npz? HOT 2
- Bug in doubly stochastic attention?
- Trained Models HOT 2
- Questions or bugs in the adam optimizer HOT 1
- why don't finetune cnn? HOT 1
- question about "doubly stochastic attention" HOT 2
- How to get start and How the convolution works out HOT 3
- Can I get pkl files?
- f_init = theano.function([ctx], [ctx]+init_state+init_memory, name='f_init', profile=False)
- Where can I get "model_name.npz" to run the Jupyter Notebook example? HOT 1
- Dataset Format and Flow of Code
- Tensoflow implementation of this model?
- Step by step readme file
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 arctic-captions.