Comments (8)
For the omniglot experiments, I trained on 1-shot and evaluated on 5-shot.
To evaluate on 5-shot using a model trained on 1-shot, use the flags --train=False --update_batch_size=5 --train_update_batch_size=1
If you want to train a model on 5-shot, you can also reduce the meta-batch size so that it fits in memory.
from maml.
OK, I see. Thank you very much! I reduced the meta_batch_size to 1 and num_updates to 1, but it still raised the same error. Also, I did these experiments several times and I got different results. It seems that there are some random factors, such as initialization of the network. How much of these random factors will have an effect on the results?
from maml.
from maml.
I also use a GPU with 12GB. It seems that this is the restriction of tensorflow. It cannot create a tensor larger than 2GB.
from maml.
from maml.
from maml.
Thank you for your reply! I think the error is caused by this line:
https://github.com/cbfinn/maml/blob/master/data_generator.py#L86
I reduced the num_total_batches to 100000 and I can train the model on 5-shot.
from maml.
from maml.
Related Issues (20)
- ModuleNotFoundError: No module named 'tensorflow.contrib' HOT 1
- Pretrained weights for omniglot
- Some question about cross-entropy loss xent
- How to open the results in LOGs
- Memory efficient MAML
- wrong comparison in maml.py
- What weights you are using during testing
- Prelosses and Postlosses HOT 2
- First-order approximation HOT 11
- Sinusoid results
- include how to cite paper on read me
- Definition of tasks in the Meta Phase
- Why 20000 tasks are set, but only one batch task is used HOT 1
- something about Computational Graph
- Testing always creates same results across 600 test points
- Why was a scheduler/annealing rate not used?
- itr is referenced before assignment in main.py, line 160
- model parameters of meta-training
- Interpretation of the results HOT 1
- Create tests file to highlight usage
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 maml.