-
Notifications
You must be signed in to change notification settings - Fork 57
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
Update TF to 2.6.0rc2 #52
base: master
Are you sure you want to change the base?
Conversation
This commit also updates bindings for flatbuffer schema following the latest definition (schema_v3b).
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Thanks for the PR.
But, CI failed to build the package in linux.
Apologies for the delayed response. I updated the branch accordingly. I also want to ask you to check this. "model.buffers" here only have 24 elements, and erasing 23-rd element in the second line was impossible. |
@@ -374,7 +394,7 @@ mod tests { | |||
model.version = 2; | |||
model.operator_codes.erase(4); | |||
model.buffers.erase(22); | |||
model.buffers.erase(23); | |||
model.buffers.erase(22); // why it was okay before fixing it from 23 to 22? |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
I think you are right.
I will look into what's behind.
@@ -3,4 +3,4 @@ | |||
url = https://github.com/tensorflow/tensorflow.git | |||
[submodule "submodules/downloads"] | |||
path = submodules/downloads | |||
url = https://github.com/boncheolgu/tflite-rs-downloads | |||
url = https://github.com/yotarok/tflite-rs-downloads |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Could you also submit a PR for the changes to https://github.com/boncheolgu/tflite-rs-downloads?
(Sending this with assuming that previous attempts to updating it to 2.4.1 is halting now.)
This PR updates the base Tensorflow version to 2.6.0rc2.
I think it is easy to again upgrade it to the official 2.6.0 once this is merged.
Upgrading to 2.6.0rc2 required a strange patch for making it compatible with macOS+LLVM environment.
yotarok/tflite-rs-downloads@29c578e
I hope it is okay, but I think I should dive a bit deeper to find a root cause of this.