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.

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

Reshape Input for Dynamic Batch Size #24

Closed
akurniawan opened this issue Dec 11, 2017 · 2 comments
Closed

Reshape Input for Dynamic Batch Size #24

akurniawan opened this issue Dec 11, 2017 · 2 comments

Comments

@akurniawan
Copy link

Hey guys, as I have written on this issue before, is there any way we can modify the input shape so that it can be more dynamic? Not only the batch_size though, if we use RNN for example, we might want to keep the length size dynamic as well

@tjingrant
Copy link
Collaborator

tjingrant commented Dec 12, 2017

This might be more of a issue for the ONNX Spec repository. Specifically, whether it is possible to specify dimension of unknown size (I do not have an answer by searching around the ONNX spec repository). However, there seems to be a somewhat related discussion regarding the RNN feature you requested (onnx/onnx#140).

@chinhuang007
Copy link
Collaborator

Handling dynamic input shape is a general concern in onnx-tf. A more recent issue is opened, #464. Let's close this one and use 464 to provide updates.

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

No branches or pull requests

3 participants