Add opset 15 kernels for Pow, BatchNorm, and Shape #8442
Conversation
hariharans29
changed the title
hariharans29
changed the title
| .Alias(3, 1) | ||
| .Alias(4, 2) | ||
| .TypeConstraint("T", DataTypeImpl::GetTensorType<double>()) | ||
| .TypeConstraint("U", DataTypeImpl::GetTensorType<double>()), |
There was a problem hiding this comment.
Bug fix: "U" was missing for opset-14. Kept the kernel hash backwards compatible by ensuring the hash is computed only using T.
| kCudaExecutionProvider, \ | ||
| (*KernelDefBuilder::Create()) \ | ||
| .TypeConstraint("T", DataTypeImpl::GetTensorType<T>()) \ | ||
| .TypeConstraint("U", DataTypeImpl::GetTensorType<T>()), \ |
There was a problem hiding this comment.
"U" was missing for opset-14 (https://github.com/microsoft/onnxruntime/pull/7806/files#r673442347)
hariharans29
changed the title
hariharans29
requested review from
edgchen1,
guoyu-wang,
skottmckay and
YUNQIUGUO
as code owners
|
|
||
| Status ShapeToInitializer::Apply(Graph& graph, Node& node, RewriteRuleEffect& rule_effect, const logging::Logger&) const { | ||
| // Store the statically inferred shape of the input to the Shape operator. | ||
| const ONNX_NAMESPACE::TensorShapeProto* input_shape_proto = node.InputDefs()[0]->Shape(); |
There was a problem hiding this comment.
Retiring this RewriteRule as its functionality is already offered by another GraphTransformer (ConstantFolding) at the same optimization level (Level 1). Updating this would have been a copy/paste of the new logic added to the Shape processing logic in ConstantFolding
hariharans29
changed the title
| OpTester test("BatchNormalization", 15); | ||
| float epsilon = 1e-05f; | ||
| float momentum = 0.1f; | ||
| int64_t training_mode = 1; |
There was a problem hiding this comment.
Training mode is enabled. But it still tests the opset 15 kernel's availability.
| @@ -67,7 +67,6 @@ | |||
| "^test_add_uint8_cpu", | |||
| "^test_div_uint8_cpu", | |||
| // Following tests are for opset 15 ops and are not yet implemented in ORT | |||
| "^test_shape_*", | |||
There was a problem hiding this comment.
Pow and BatchNorm came with no ONNX tests. Only Shape came with tests.
|
LGTM 👍 . Can you resolve the pipelines? |
Yeah, it just needs the newer |
|
/azp run Windows GPU CI Pipeline |
|
Azure Pipelines successfully started running 1 pipeline(s). |
Fixed the pipelines. |
Description:
Clubbing some simple opset-15 implementations together-
Powhad an opset bump with the inclusion ofbfloat16in the list of supported types for the exponent input. (onnx/onnx#3412)BatchNormhad an opset bump with separate type constraints being introduced for scale and bias. (onnx/onnx#3545)Shapesupports slicing specific indices (onnx/onnx#3580)Motivation and Context
ONNX compliance