learn2learn | A PyTorch Library for Meta-learning Research | Machine Learning library

by learnables Python Version: 0.2.0 License: MIT

X-Ray Key Features Code Snippets Community Discussions(3)Vulnerabilities Install Support

kandi X-RAY | learn2learn Summary

learn2learn is a Python library typically used in Artificial Intelligence, Machine Learning, Deep Learning, Pytorch applications. learn2learn has no bugs, it has no vulnerabilities, it has build file available, it has a Permissive License and it has medium support. You can install using 'pip install learn2learn' or download it from GitHub, PyPI.

learn2learn is a software library for meta-learning research.

Support

Quality

Security

License

Reuse

Support

learn2learn has a medium active ecosystem.

It has 2264 star(s) with 325 fork(s). There are 33 watchers for this library.

It had no major release in the last 12 months.

There are 6 open issues and 230 have been closed. On average issues are closed in 394 days. There are 6 open pull requests and 0 closed requests.

It has a neutral sentiment in the developer community.

The latest version of learn2learn is 0.2.0

Quality

learn2learn has 0 bugs and 0 code smells.

Security

learn2learn has no vulnerabilities reported, and its dependent libraries have no vulnerabilities reported.

learn2learn code analysis shows 0 unresolved vulnerabilities.

There are 0 security hotspots that need review.

License

learn2learn is licensed under the MIT License. This license is Permissive.

Permissive licenses have the least restrictions, and you can use them in most projects.

Reuse

learn2learn releases are available to install and integrate.

Deployable package is available in PyPI.

Build file is available. You can build the component from source.

Installation instructions are not available. Examples and code snippets are available.

learn2learn saves you 4777 person hours of effort in developing the same functionality from scratch.

It has 12463 lines of code, 611 functions and 142 files.

It has medium code complexity. Code complexity directly impacts maintainability of the code.

Top functions reviewed by kandi - BETA

kandi has reviewed learn2learn and discovered the below as its top functions. This is intended to give you an instant insight into learn2learn implemented functionality, and help decide if they suit your requirements.

Start pretraining
Train the model
Adapt a batch of training data
Clone the AMLPL
Resets gradients
Runs l2l vision
Fast adaptation function
Compute the MAM policy loss
Compute the generalized advantage
Loop forever
Compute the classifier
Create a Google spreadsheet service
Forward computation
Compute a random block of data
Compute prototypes
Main loop
Download data files
Forward a single action
Perform an action
Compute generalized advantage
Run SVM logits
Return a pretrained model
Adapt the loss function
Adapts the loss function
Adapts a trained model
Clone the MAML object
Performs the training
Learn the model
Compute the Kronecker algorithm

Get all kandi verified functions for this library.

learn2learn Key Features

No Key Features are available at this moment for learn2learn.

learn2learn Examples and Code Snippets

No Code Snippets are available at this moment for learn2learn.

Community Discussions

Trending Discussions on learn2learn

When should one call .eval() and .train() when doing MAML with the PyTorch higher library?

How does one install pytorch 1.9 in an HPC that seems to refuse to cooperate?

Mix pytorch lightning with vanilla pytorch

QUESTION

When should one call .eval() and .train() when doing MAML with the PyTorch higher library?

Asked 2021-Nov-25 at 19:54

I was going through the omniglot maml example and saw that they have net.train() at the top of their testing code. This seems like a mistake since that means the stats from each task at meta-testing is shared:

...

ANSWER

Answered 2021-Nov-25 at 19:54

TLDR: Use mdl.train() since that uses batch statistics (but inference will not be deterministic anymore). You probably won't want to use mdl.eval() in meta-learning.

BN intended behaviour:

Importantly, during inference (eval/testing) running_mean, running_std is used - that was calculated from training(because they want a deterministic output and to use estimates of the population statistics).
During training the batch statistics is used but a population statistic is estimated with running averages. I assume the reason batch_stats is used during training is to introduce noise that regularizes training (noise robustness)
in meta-learning I think using batch statistics is the best during testing (and not calculate the running means) since we are supposed to be seeing new /tasksdistribution anyway. Price we pay is loss of determinism. Could be interesting just out of curiosity what the accuracy is using population stats estimated from meta-trian.

This is likely why I don't see divergence in my testing with the mdl.train().

So just make sure you use mdl.train() (since that uses batch statistics https://pytorch.org/docs/stable/generated/torch.nn.BatchNorm2d.html#torch.nn.BatchNorm2d) but that either the new running stats that cheat aren't saved or used later.

Source https://stackoverflow.com/questions/69845469

QUESTION

How does one install pytorch 1.9 in an HPC that seems to refuse to cooperate?

Asked 2021-Sep-27 at 15:21

I've been trying to install PyTorch 1.9 with Cuda (ideally 11) on my HPC but I cannot.

The cluster says:

...

ANSWER

Answered 2021-Sep-23 at 06:45

First of all, as @Francois suggested, try to uninstall the CPU only version of pytorch. Also in your installation script, you should use either conda or pip3.

Then you may want to try the following attempts:

using conda: add conda-forge channel to your command (conda install pytorch torchvision torchaudio cudatoolkit=11.1 -c pytorch -c nvidia -c conda-forge). And make sure conda is updated.
using pip: insert --no-cache-dir into your command (pip3 --no-cache-dir install torch==1.9.0+cu111 torchvision==0.10.0+cu111 torchaudio==0.9.0 -f https://download.pytorch.org/whl/torch_stable.html) to avoid the MemoryError.

Source https://stackoverflow.com/questions/69230502

QUESTION

Mix pytorch lightning with vanilla pytorch

Asked 2021-Jul-14 at 18:27

I am doing a meta learning research and am using the MAML optimization provided by learn2learn. However as one of the baseline, I would like to test a non-meta-learning approach, i.e. the traditional training + testing.

Due to the lightning's internal usage of optimizer it seems that it is difficult to make the MAML work with learn2learn in lightning, so I couldn't use lightning in my meta-learning setup, however for my baseline, I really like to use lightning in that it provides many handy functionalities like deepspeed or ddp out of the box.

Here is my question, other than setting up two separate folders/repos, how could I mix the vanilia pytorch (learn2learn) with pytorch lightning (baseline)? What is the best practice?

Thanks!

...

ANSWER

Answered 2021-Jul-14 at 18:27

Decided to answer my question. So I ended up using the torch lightning's manual optimization so that I can customize the optimization step. This would make both approaches using the same framework, and I think is better than maintaining 2 separate repos.

Source https://stackoverflow.com/questions/68359563

Community Discussions, Code Snippets contain sources that include Stack Exchange Network

Vulnerabilities

No vulnerabilities reported

Install learn2learn

You can install using 'pip install learn2learn' or download it from GitHub, PyPI.
You can use learn2learn like any standard Python library. You will need to make sure that you have a development environment consisting of a Python distribution including header files, a compiler, pip, and git installed. Make sure that your pip, setuptools, and wheel are up to date. When using pip it is generally recommended to install packages in a virtual environment to avoid changes to the system.

Support

For any new features, suggestions and bugs create an issue on GitHub. If you have any questions check and ask questions on community page Stack Overflow .

Find more information at: