Skip to content

Export uint8 tensors as byte string in mobile_exporter and add GivenTensorStringToUInt8FillOp (#10354)#10385

Closed
3l1 wants to merge 1 commit intopytorch:masterfrom
3l1:export-D9004839
Closed

Export uint8 tensors as byte string in mobile_exporter and add GivenTensorStringToUInt8FillOp (#10354)#10385
3l1 wants to merge 1 commit intopytorch:masterfrom
3l1:export-D9004839

Conversation

@3l1
Copy link
Contributor

@3l1 3l1 commented Aug 9, 2018

Summary:
Pull Request resolved: #10354

Pull Request resolved: #10316

Because Protobuf encodes uint8_t tensors using a less space efficient varint uin32_t encoding, we are adding a new operator that reads back a byte string into a uint8_t tensor.

Differential Revision: D9004839

…ensorByteStringToUInt8FillOp (#10385)

Summary:
Pull Request resolved: #10385

Pull Request resolved: #10354

Pull Request resolved: #10316

Because Protobuf encodes uint8_t tensors using a less space efficient varint uin32_t encoding, we are adding a new operator that reads back a byte string into a uint8_t tensor.

Reviewed By: harouwu

Differential Revision: D9004839

fbshipit-source-id: 7ae70c4248a8fc9900af8a31c60eb44e5b3090b2
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

Projects

None yet

Development

Successfully merging this pull request may close these issues.

3 participants