Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

add new feature for tfdbg that ignoring specific layers #16619

Closed
mercy0387 opened this issue Jan 31, 2018 · 5 comments
Closed

add new feature for tfdbg that ignoring specific layers #16619

mercy0387 opened this issue Jan 31, 2018 · 5 comments
Assignees
@caisq
Labels
type:feature Feature requests

Comments

@mercy0387
Copy link

mercy0387 commented Jan 31, 2018 •
edited

Using tfdbg, has_inf_or_nan filter is very useful. But when I need inf at some calculations in the network explicitly, this filter catches inf every time. (e.g. keras-team/keras#9161 )

So I want to suggest new feature, ignore option, to add_tensor_filter. (I think it's around here. right?)

This option can take layer's names and layers which is selected to this option are ignored explicitly when tfdbg check inf_or_nan in the network.

This is also useful other than in my case above. If my understanding is not correct, let me know.

Thanks.
@mercy0387 mercy0387 mentioned this issue Jan 31, 2018
Closed
@caisq caisq self-assigned this Jan 31, 2018
@caisq caisq added the type:feature Feature requests label Jan 31, 2018
@caisq
Copy link
Contributor

caisq commented Feb 2, 2018

@mercy0387 thanks for filing the feature request. I agree that adding arguments to tfdbg filters like has_inf_or_nan will be useful. I will work on the new feature.

@tensorflowbutler
Copy link
Member

Nagging Assignee: It has been 14 days with no activity and this issue has an assignee. Please update the label and/or status accordingly.

@tensorflowbutler
Copy link
Member

Nagging Assignee @caisq: It has been 14 days with no activity and this issue has an assignee. Please update the label and/or status accordingly.

1 similar comment
@tensorflowbutler
Copy link
Member

Nagging Assignee @caisq: It has been 14 days with no activity and this issue has an assignee. Please update the label and/or status accordingly.

@caisq
Copy link
Contributor

caisq commented Mar 26, 2018

Update: We have a CL under review for fulfilling this feature request.

@xiejw xiejw closed this as completed in 04b1e73 Mar 27, 2018
copybara-service bot pushed a commit that referenced this issue Jul 11, 2022
@ageron @tensorflower-gardener
PR #16619: Add support for Keras mask & causal mask to MultiHeadAtten…
f2a40a5 
…tion

This is a first go at adding Keras masking support and causal support to the `MultiHeadAttention` layer.

See the discussion in [#16248](keras-team/keras#16248).

Imported from GitHub PR #16619

Copybara import of the project:

  - c0293ded9abe8ac7719cceb0095fa9dff807d2fe Add support for Keras masking and causal masking by Aurélien Geron <ageron@users.noreply.github.com>
  - 015625fb981212a97c282b71a0479b6e7cada6b3 Replace causal in init with use_causal_mask in call by Aurélien Geron <ageron@users.noreply.github.com>
  - ebf46bf42166a36068017d12d999d0ecd6e55d69 Reformat code using shell/format.sh by Aurélien Geron <ageron@users.noreply.github.com>
  - 9ec97ba141354c8b34b7735942ffb207766b2d96 Fix docstring indentation and missing line breaks by Aurélien Geron <ageron@users.noreply.github.com>
  - b00b4b462d74d3f3a387a07550945c1d19e6ebe2 Merge branch 'master' into mha_automask by Aurélien Geron <ageron@users.noreply.github.com>
  - 76055673c562571c088f80184c70034221a6ee7e Add defensive casting to bool for implicit and explicit m... by Aurélien Geron <ageron@users.noreply.github.com>
  - 1f724936ce4753fd83d4cdb7bec03b49b3def98f Merge 76055673c562571c088f80184c70034221a6ee7e into e1d39... by Aurélien Geron <ageron@users.noreply.github.com>

PiperOrigin-RevId: 460320823
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees

@caisq caisq

Labels
type:feature Feature requests
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
3 participants
@mercy0387 @caisq @tensorflowbutler