Skip to content
This repository was archived by the owner on Sep 28, 2024. It is now read-only.

Conversation

yuehhua
Copy link
Collaborator

@yuehhua yuehhua commented Aug 11, 2021

No description provided.

@yuehhua yuehhua requested a review from foldfelis August 11, 2021 05:09
loss(𝐱, 𝐲) = sum(abs2, 𝐲 .- m(𝐱)) / size(𝐱)[end]
data = [(𝐱[:, :, 1:5], 𝐲[:, 1:5])]
Flux.train!(loss, params(m), data, Flux.ADAM())
@test true
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

This is redundant

Copy link
Collaborator Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Due to the use of Flux.train, it is a nondeterministic process. @test true is added to make sure the process is passed.

Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

The test case will still passed if the train! failed

loss(𝐱, 𝐲) = sum(abs2, 𝐲 .- m(𝐱)) / size(𝐱)[end]
data = [(𝐱[:, :, 1:5], 𝐲[:, 1:5])]
Flux.train!(loss, params(m), data, Flux.ADAM())
@test true
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

This is redundant

loss(x, y) = Flux.mse(real.(m(x)), y)
data = [(T.(𝐱[:, :, 1:5]), rand(T, 64, 1024, 5))]
Flux.train!(loss, params(m), data, Flux.ADAM())
@test true
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

This is redundant

@foldfelis
Copy link
Contributor

Thanks in advance

@foldfelis foldfelis mentioned this pull request Aug 11, 2021
Copy link
Contributor

@foldfelis foldfelis left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

This PR can be safely closed due to #4 and #5

Feel free to rebased if you got extra task to do.

@yuehhua yuehhua closed this Aug 11, 2021
Sign up for free to subscribe to this conversation on GitHub. Already have an account? Sign in.
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

2 participants