Skip to content
This repository has been archived by the owner on Oct 31, 2023. It is now read-only.

Issues: facebookresearch/higher

58 Open 50 Closed
58 Open 50 Closed
Author
Filter by author
Loading
Label
Filter by label
Loading
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Loading
Milestones
Filter by milestone
Loading
Assignee
Filter by who’s assigned
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Issues list

Support of AdamW
#140 opened May 6, 2023 by ridiculouz
Does higher work with huggingface (hugging face, HF) models? e.g. ViT?
#139 opened Mar 17, 2023 by brando90
2
CUDA out of memory
#138 opened Mar 1, 2023 by aooating
once_differentiable
#137 opened Mar 1, 2023 by aooating
1
grad clip correctness
#136 opened Jan 6, 2023 by Whalefishin
Using higher for hyperparameter optimization
#135 opened Dec 21, 2022 by aruniyer
1
Non scalar loss
#134 opened Dec 14, 2022 by janglinko-dac
1
Intialize Differentiable Optimizer with non-leaf tensort
#133 opened Aug 8, 2022 by andrearosasco
1
higher for dpt architectures?
#132 opened Jul 22, 2022 by Ainaz99
2
How to Update/Optimize subset of params
#130 opened Mar 11, 2022 by blake-camp
2
Potential bug with first order MAML using only higher, setting track_higher_grads = False leads to .grad field to not be populated and be None, is that a bug?
#129 opened Feb 2, 2022 by brando90
4
Would making the gradient "data" by detaching them implement first order MAML?
#128 opened Feb 1, 2022 by brando90
Mixed precision training
#127 opened Jan 31, 2022 by zhiqihuang
In DifferentiableAdam, sqrt() is non-differentiable at zero
#125 opened Dec 10, 2021 by rickyloynd-microsoft
6
Does higher work with hugging face Adafactor?
#124 opened Nov 30, 2021 by brando90
2
second-order deravative
#123 opened Nov 14, 2021 by xugy16
Setting up a templates got gitissues that invite users to post to pytorch forum
#121 opened Nov 4, 2021 by brando90
What does the warning flag in testing for maml mean? what does it mean to "fine tune for testing"?
#120 opened Nov 4, 2021 by brando90
How does one return an adapted model without using the context manager?
#119 opened Nov 2, 2021 by brando90
8
Does higher work with DDP only test time evaluation (no training just testing)?
#118 opened Oct 26, 2021 by brando90
When will higher allow the use of DDP (distributed data parallel)?
#116 opened Sep 28, 2021 by brando90
4
implementing MAML with MiniImageNet
#115 opened Sep 23, 2021 by ligeng0197
metaclass issue with fastai
#113 opened Aug 3, 2021 by shayanfazeli
4
maml omniglot - finetuning / test
#111 opened Jul 29, 2021 by shayanfazeli
5
variables work outside of context manager scope
#110 opened Jun 22, 2021 by hughperkins
2
ProTip! Add no:assignee to see everything that’s not assigned.