Skip to content

Move computing of output dims from InferShape to Compute.#9978

Closed
wanghaoshuang wants to merge 2 commits into
PaddlePaddle:developfrom
wanghaoshuang:fix_im2sequence
Closed

Move computing of output dims from InferShape to Compute.#9978
wanghaoshuang wants to merge 2 commits into
PaddlePaddle:developfrom
wanghaoshuang:fix_im2sequence

Conversation

@wanghaoshuang
Copy link
Copy Markdown
Contributor

fix ##9977

Copy link
Copy Markdown

@tonyyang-svail tonyyang-svail left a comment

Choose a reason for hiding this comment

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

The runtime infershape and compile time infer shape are using the same code. The batchsize should be known at the runtime.

@wanghaoshuang
Copy link
Copy Markdown
Contributor Author

@tonyyang-svail Should I realize different computing according to whether it is runtime in Infer_Shape?

@wanghaoshuang wanghaoshuang deleted the fix_im2sequence branch May 20, 2022 03:59
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants