learn2learn
learn2learn copied to clipboard
learnables
A PyTorch Library for Meta-learning Research
How about developing audio examples with MAML or Reptile for W2V2, Whisper, MMS and so on?
Hello All, I didn't know where to pose this question as there is no Discussions tab. I was wondering if this package could be used with a Random Forest model...
Hi, amazing work! I am wondering do you have other optimizer mimicking in fast_adapt function. It seemed that only SGD is implented.
Hi, I tested MAML and Reptile algorithms using mini-imagenet dataset, and the data are sampled using a TasksetDataset, Question: Is it normal that after the set of tasks are created,...
Hi @seba-1511, First of all thank you for this awesome repository! :slightly_smiling_face: I'm currently unable to reproduce the results of the script [anil_fc100.py](https://github.com/learnables/learn2learn/blob/master/examples/vision/anil_fc100.py). I took the script and only adjusted...
Hello, I am running the `toy_example.py` and printing out the loss and adapt_loss as shown below. ``` for t in range(TASKS_PER_STEP): # Sample a task task_params = task_dist.sample() mu_i, sigma_i...
D:\Anaconda\python.exe D:\py\learn2learn-master\examples\rl\maml_trpo.py D:\Anaconda\lib\site-packages\gym\spaces\box.py:73: UserWarning: WARN: Box bound precision lowered by casting to float32 logger.warn( Traceback (most recent call last): File "D:\Anaconda\lib\site-packages\cherry\wrappers\base_wrapper.py", line 82, in __getattr__ Traceback (most recent call last):...
You can't assume the users have e.g. `gcc` and all the needed headers on their system, i've hear cibuildwheel is pretty good.
### Description Failed building wheel for learn2learn using `pip install learn2learn` on Python 3.11. On Python 3.10 there is no problem. This seems to be caused by a Cython update...
error during installation: _Building wheel for learn2learn (pyproject.toml) ... error error: subprocess-exited-with-error × Building wheel for learn2learn (pyproject.toml) did not run successfully. │ exit code: 1 ╰─> [153 lines of...
Metadata
Owner
Metadata
A PyTorch Library for Meta-learning Research