Comments (10)
Dear Chelsea,
following up on this discussion - In your paper you say that the split is 64 train / 12 validation / 24 test classes. The original split (https://github.com/twitter/meta-learning-lstm/tree/master/data/miniImagenet) is 64/16/20 though. Is that just a typo, or did you use a different split?
If anybody is still looking for the dataset, I found this source: dragen1860/LearningToCompare-Pytorch#4
from maml.
@jongchyisu @imaxpayne Hi, I have sent email to Sachin, but got no response, could you share the solution to this problem? Thanks a lot.
from maml.
Yes, it is a typo.
from maml.
Sorry this is unclear. I got the dataset from Ravi & Larochelle '17. If you email Sachin, he should be able to help.
from maml.
I updated the instructions in proc_images.py
from maml.
Thank you! I will contact him via email.
from maml.
Hi Chelsea,
Sorry for opening this issue again, but from the csv files in Sachin's GitHub, I can't find some of the images in the imagenet by the ID. For example, the first training image is n0153282900000005.jpg,n01532829
but there is no n01532829_5.jpg can be found in
http://www.image-net.org/api/text/imagenet.synset.geturls.getmapping?wnid=n01532829
How did you solve this issue? Thank you very much!
from maml.
@jongchyisu You should contact Sachin via email.
from maml.
Yes I just sent him an email.
from maml.
I also sent him an emial and there was no response. It would be great if you could provide that dataset.
@cbfinn
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.