Comments (6)
Dear,
How to start the project ?
I just want to test the regression using MAML in predicting the price of stock.
Any help?
from maml.
It seems like it is not finding the images, causing folders
to be an empty list. It looks for the images in ./data/omniglot_resized
(on this line of code https://github.com/cbfinn/maml/blob/master/data_generator.py#L40)
Are you calling the code from the maml/ directory? e.g. python main.py
Can you see if the folders
is indeed an empty list?
from maml.
Yes, I was running main.py
from maml/
directory,
I found that when I run main.py
, it was able to execute the line https://github.com/cbfinn/maml/blob/master/main.py#L272, and generate the tensor shape (32, 10, 784) (32, 10, 784) for image_tensor, label_tensor
respectively , and the folders
in https://github.com/cbfinn/maml/blob/master/data_generator.py#L95 was not a empty list.
but when it continue and execute the line https://github.com/cbfinn/maml/blob/master/main.py#L280, it print out the error message I describe above, and the folders
in https://github.com/cbfinn/maml/blob/master/data_generator.py#L95 was empty list when I print len(folders)
, it shows zero.
So it was able to generate image_tensor
when calling data_generator.make_data_tensor()
, but not data_generator.make_data_tensor(train=False)
Thank you for your response, really looking forward to test and play with the model !
Max.
from maml.
Ah, okay. Make sure you download both images_background and images_evaluation from the omniglot website, and put them in the same directory (and run the preprocessing for all images)
That should solve your problem. (It seems to be that there are <= 1200 character classes in the dataset that you downloaded)
If this solves your issue, then I will clarity the Omniglot data instructions.
from maml.
Yes! This solves the problem. Thank you very much.
from maml.
Hi, I am having a similar problem. I can't find any dataset to download on the omniglot website, so I got them from here: https://github.com/brendenlake/omniglot
Where can we get the right dataset?
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.