Comments (4)
Thanks for your interest in my work.
If you want to directly download the processed images for miniImageNet, you may visit the following link: https://meta-transfer-learning.yaoyao-liu.com/download/
As the miniImageNet dataset is sampled from the ImageNet, you need agree to the terms of ImageNet, and use these processed images only for non-commercial research and educational purposes.
from mini-imagenet-tools.
ok, thanks.
just one more question, is it possible to store it in untarred format, and is there any issue in storing it in untarred format, because most of the programs require it in untarred format.
from mini-imagenet-tools.
I uploaded the tar file because it would be more convenient to download and verify md5sum
for the dataset. The speed would be very slow when uploading and downloading many small files.
You could download the tar file, untar it and re-upload by yourself. You may create a pull request to share your re-upload files' link in the repo. Thanks a lot for your contributions.
from mini-imagenet-tools.
Thanks for the contributions by @vainaijr. As the google drive sharing link has been added to the README.md
, I'm going the close this issue. Feel free to create another issue if you have any other questions.
from mini-imagenet-tools.
Related Issues (9)
- How to create the csv files? HOT 4
- Google drive link for preprocessed mini-imagenet is down. HOT 1
- What is "episode num"? HOT 1
- Hello, do you know how to generate the pickle file for miniImagenet? HOT 2
- Reference Ravi and Larochelle in About section HOT 1
- Missing images when compared to the provided csv files HOT 1
- Are images sorted in the classes? HOT 3
- mini_imagenet_dataloader.py: 189 should be self.num_samples_per_class*self.way_num HOT 2
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 mini-imagenet-tools.