digantamisra98/Mish issues and pull requests

#43 - Which CNN architecture is considered for the experimentation of "Test accuracy versus initializers"?

Issue - State: closed - Opened by MeenalNarkhede 3 months ago - 1 comment

#42 - doc(README): remove typo

Pull Request - State: closed - Opened by Vinay0508 about 1 year ago

#41 - Spelling error in repo description

Issue - State: closed - Opened by aicrumb over 2 years ago

#40 - Issue about Table.1

Issue - State: closed - Opened by LeungWaiHo over 2 years ago - 3 comments

#39 - Need help with Mish-Metal

Issue - State: closed - Opened by philipturner about 3 years ago - 7 comments
Labels: help wanted, question

#37 - Correct gain value during kaiming weight initialization

Issue - State: closed - Opened by evanatyourservice almost 4 years ago - 9 comments
Labels: enhancement

#36 - Visualization code hyperlink page is not found.

Issue - State: closed - Opened by vanche about 4 years ago - 1 comment

#35 - Mish and alternatives, including my own

Issue - State: closed - Opened by PallHaraldsson about 4 years ago - 11 comments

#34 - Application of Mish on ReXNet

Issue - State: closed - Opened by chris-ha458 over 4 years ago - 2 comments
Labels: enhancement

#33 - [Snyk] Security upgrade pillow from 6.2.2 to 6.2.3

Pull Request - State: closed - Opened by snyk-bot over 4 years ago

#32 - Comparison with TanhExp

Issue - State: closed - Opened by chris-ha458 over 4 years ago - 3 comments
Labels: question

#31 - Bump psutil from 5.4.8 to 5.6.6

Pull Request - State: closed - Opened by dependabot[bot] over 4 years ago
Labels: dependencies

#30 - Source Code Implentation - "404" Error

Issue - State: closed - Opened by njcurtis3 almost 5 years ago - 1 comment
Labels: bug

#29 - Demo Jupyter Notebooks - Link "404" error

Issue - State: closed - Opened by njcurtis3 almost 5 years ago - 1 comment
Labels: bug

#28 - Why does mish return significantly worse result than elu?

Issue - State: closed - Opened by qo4on almost 5 years ago - 9 comments
Labels: question

#27 - Discussion regarding GAN benchmarks

Issue - State: closed - Opened by DonaldTsang almost 5 years ago - 1 comment

#26 - Extended Coverage of other CNNs

Issue - State: closed - Opened by DonaldTsang almost 5 years ago - 1 comment
Labels: enhancement

#25 - Computational cost of Mish vs GELU vs Swish

Issue - State: closed - Opened by DonaldTsang almost 5 years ago - 6 comments
Labels: enhancement, question

#24 - More comparison with existing methods?

Issue - State: closed - Opened by DonaldTsang almost 5 years ago - 10 comments
Labels: question

#22 - Equivalent, faster (?) formulation

Issue - State: closed - Opened by tmassingham-ont almost 5 years ago - 34 comments
Labels: enhancement

#21 - how to use mish in tensorflow slim.conv2d????

Issue - State: closed - Opened by henbucuoshanghai almost 5 years ago - 5 comments
Labels: help wanted, question

#20 - Should be mish used before or after batchnorm?

Issue - State: closed - Opened by hadaev8 almost 5 years ago - 2 comments
Labels: question

#19 - The result is not good (Fixed, improved mAP)

Issue - State: closed - Opened by DrewdropLife almost 5 years ago - 5 comments
Labels: question

#18 - PyTorch Mish - 1.5x slower training, 2.9X more memory usage vs LeakyReLU(0.1)

Issue - State: closed - Opened by glenn-jocher almost 5 years ago - 6 comments
Labels: question

#17 - TF-Keras module name

Issue - State: closed - Opened by mehmetalianil about 5 years ago - 3 comments

#16 - When trying to change cifar-10 to cifar-100(In cifar-10-senet-18-mish) it raises RuntimeError: CUDA error: device-side assert triggered.

Issue - State: closed - Opened by SkeletonOne about 5 years ago - 6 comments
Labels: bug, torch

GitHub / digantamisra98/Mish issues and pull requests