[4/N] Nnapi backend delegation preprocess: List Tensors & Comment Updates #61752
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
…ates
Updated Android NNAPI preprocess, so that it can accept both single Tensor inputs and Tensor List inputs.
-The inputs are not real data, but input parameters for shape, dtype, quantization, and dimorder that are bundled as a Tensor. Comments were updated to make this clearer.
-In the future, preprocess will also accept a dedicated NnapiArg object.
Compile_spec should have the following format:
{"forward": {"inputs": at::Tensor}} OR {"forward": {"inputs": c10::List<at::Tensor>}}
Example input Tensor:
torch.tensor([[1.0, -1.0, 2.0, -2.0]]).unsqueeze(-1).unsqueeze(-1)
###Testing
OSS testing is blocked by #61594. Testing was done locally in
TODO: Add OSS tests for single Tensor and Tensor List inputs.
Differential Revision: [D29726432](https://our.internmc.facebook.com/intern/diff/D29726432/)
[ghstack-poisoned]
💊 CI failures summary and remediationsAs of commit d18fa5d (more details on the Dr. CI page and at hud.pytorch.org/pr/61752):
🕵️ 1 new failure recognized by patternsThe following CI failures do not appear to be due to upstream breakages:
|
Amyh11325
pushed a commit
that referenced
this pull request
Jul 16, 2021
…ates
Updated Android NNAPI preprocess, so that it can accept both single Tensor inputs and Tensor List inputs.
-The inputs are not real data, but input parameters for shape, dtype, quantization, and dimorder that are bundled as a Tensor. Comments were updated to make this clearer.
-In the future, preprocess will also accept a dedicated NnapiArg object.
Compile_spec should have the following format:
{"forward": {"inputs": at::Tensor}} OR {"forward": {"inputs": c10::List<at::Tensor>}}
Example input Tensor:
torch.tensor([[1.0, -1.0, 2.0, -2.0]]).unsqueeze(-1).unsqueeze(-1)
###Testing
OSS testing is blocked by #61594. Testing was done locally in
TODO: Add OSS tests for single Tensor and Tensor List inputs.
Differential Revision: [D29726432](https://our.internmc.facebook.com/intern/diff/D29726432/)
ghstack-source-id: 133656416
Pull Request resolved: #61752
…Comment Updates"
Updated Android NNAPI preprocess, so that it can accept both single Tensor inputs and Tensor List inputs.
- The inputs are not real data, but input parameters for shape, dtype, quantization, and dimorder that are bundled as a Tensor. Comments were updated to make this clearer.
- In the future, preprocess will also accept a dedicated NnapiArg object.
Compile_spec should have the following format:
{"forward": {"inputs": at::Tensor}} OR {"forward": {"inputs": c10::List<at::Tensor>}}
Example input Tensor:
torch.tensor([[1.0, -1.0, 2.0, -2.0]]).unsqueeze(-1).unsqueeze(-1)
**Testing**
OSS testing is blocked by #61594. Testing was done locally in
TODO: Add OSS tests for single Tensor and Tensor List inputs.
Differential Revision: [D29726432](https://our.internmc.facebook.com/intern/diff/D29726432/)
[ghstack-poisoned]
Amyh11325
pushed a commit
that referenced
this pull request
Jul 16, 2021
…ates Pull Request resolved: #61752 Updated Android NNAPI preprocess, so that it can accept both single Tensor inputs and Tensor List inputs. - The inputs are not real data, but input parameters for shape, dtype, quantization, and dimorder that are bundled as a Tensor. Comments were updated to make this clearer. - In the future, preprocess will also accept a dedicated NnapiArg object. Compile_spec should have the following format: {"forward": {"inputs": at::Tensor}} OR {"forward": {"inputs": c10::List< at::Tensor >}} Example input Tensor: torch.tensor([[1.0, -1.0, 2.0, -2.0]]).unsqueeze(-1).unsqueeze(-1) ### Testing OSS testing is blocked by #61594. Testing was done locally in D29726948 TODO: Add OSS tests for single Tensor and Tensor List inputs. ghstack-source-id: 133683735 Differential Revision: [D29726432](https://our.internmc.facebook.com/intern/diff/D29726432/)
|
This pull request has been merged in 6349bde. |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Stack from ghstack:
Updated Android NNAPI preprocess, so that it can accept both single Tensor inputs and Tensor List inputs.
Compile_spec should have the following format:
{"forward": {"inputs": at::Tensor}} OR {"forward": {"inputs": c10::Listat::Tensor}}
Example input Tensor:
torch.tensor([[1.0, -1.0, 2.0, -2.0]]).unsqueeze(-1).unsqueeze(-1)
Testing
OSS testing is blocked by #61594. Testing was done locally in
TODO: Add OSS tests for single Tensor and Tensor List inputs.
Differential Revision: D29726432