onnxruntime/js/web/docs/webgpu-operators.md at b668a6da9622a0ba91bed06affc8d4c468bc5496

mirror of https://github.com/saymrwulf/onnxruntime.git synced 2026-05-17 21:10:43 +00:00

Alexander Visheratin e6c6184fee

[JS/WebGPU] Unsqueeze operator implementation (#16138 )

### Description

This PR adds an implementation of the Squeeze operator to WebGPU JSEP.
The implementation follows the [operator
schema](https://github.com/onnx/onnx/blob/main/docs/Operators.md#Unsqueeze).

To implement the `Unsqueeze` operator in the same fashion as the
`Squeeze`, I added the `ComputeOutputShape()` method to the
`UnsqueezeBase` class and made some slight modifications. Please let me
know if it is a bad idea and if I should move this method to the JS
implementation.

I also uncommented test case lines in the `suite-test-list.jsonc` file
for both Squeeze and Unsqueeze operators following @hariharans29's
[comment](https://github.com/microsoft/onnxruntime/pull/16024#issuecomment-1565113633).

### How was it tested

1. I created a model with only one operator:

```Python
import onnx.helper

node = onnx.helper.make_node(
    "Unsqueeze",
    inputs=["T", "axes"],
    outputs=["y"],
)
graph = onnx.helper.make_graph([node], "test", [onnx.helper.make_tensor_value_info("T", 1, [3, 4, 5]), onnx.helper.make_tensor_value_info("axes", 7, [2])], [onnx.helper.make_tensor_value_info("y", 1, [3, 1, 4, 5, 1])])
onnx.save(onnx.helper.make_model(graph), "unsqueeze.onnx")
```

2. I compiled the runtime using @fs-eire's
[instructions](https://gist.github.com/fs-eire/a55b2c7e10a6864b9602c279b8b75dce).
3. I ran the test models in the browser using this minimal setup:
```HTML
<html>
    <script src=".\dist\ort.webgpu.min.js"></script>
    <script>
        async function run() {
            const session = await ort.InferenceSession.create('unsqueeze.onnx', {executionProviders: ['webgpu']});
            console.log(session);
            const input = new ort.Tensor('float32', new Float32Array(60), [3, 4, 5]);
            const dim = new ort.Tensor('int64', [1n, 4n], [2]);
            const output = await session.run({ "T": input, "axes": dim });
            console.log(output);
        }
        run();
    </script>
</html>
```

### Motivation and Context

Improve operator coverage for WebGPU JSEP.

2023-06-01 12:23:02 -07:00

2.3 KiB

Raw Blame History

Operators Support Table

The following table shows ONNX operators and the supported opset domain/versions in WebGPU EP by ONNX Runtime Web. For example, 4-6, 8+ means ONNX Runtime Web currently support opset version 4 to 6, 8 and above.

This file is automatically generated from the def files via this script. Do not modify directly.

Operator	Opset	Comments
Abs	ai.onnx(6-12,13+)
Acos	ai.onnx(7+)
Acosh	ai.onnx(9+)
Add	ai.onnx(7-12,13,14+)
Asin	ai.onnx(7+)
Asinh	ai.onnx(9+)
Atan	ai.onnx(7+)
Atanh	ai.onnx(9+)
AveragePool	ai.onnx(7-9,10,11+); com.ms.internal.nhwc(11+)	need perf optimization; need implementing activation
Ceil	ai.onnx(6-12,13+)
Clip	ai.onnx(6-10,11,12,13+)
Conv	ai.onnx(1-10,11+); com.ms.internal.nhwc(11+)	need perf optimization; conv3d not supported; need implementing activation
Cos	ai.onnx(7+)
Cosh	ai.onnx(9+)
Div	ai.onnx(7-12,13,14+)
Elu	ai.onnx(6+)
Erf	ai.onnx(9-12,13+)
Exp	ai.onnx(6-12,13+)
Floor	ai.onnx(6-12,13+)
Gemm	ai.onnx(7-8,9-10,11+)
GlobalAveragePool	ai.onnx(1+); com.ms.internal.nhwc(1+)
GlobalMaxPool	ai.onnx(1+); com.ms.internal.nhwc(1+)
LeakyRelu	ai.onnx(6-15,16+)
MatMul	ai.onnx(1-12,13+)
MaxPool	ai.onnx(1-7,8-9,10,11,12+); com.ms.internal.nhwc(11,12+)	need perf optimization; need implementing activation
MemcpyFromHost	ai.onnx(1+)
MemcpyToHost	ai.onnx(1+)
Mul	ai.onnx(7-12,13,14+)
Neg	ai.onnx(6-12,13+)
Pow	ai.onnx(7-11,12,13-14,15+)
Reciprocal	ai.onnx(6-12,13+)
Relu	ai.onnx(6-12,13,14+)
Reshape	ai.onnx(5-12,13,14+)	no GPU kernel
Shape	ai.onnx(1-12,13-14,15+)	no GPU kernel; an ORT warning is generated - need to fix
Sigmoid	ai.onnx(6-12,13+)
Sin	ai.onnx(7+)
Sinh	ai.onnx(9+)
Sqrt	ai.onnx(6-12,13+)
Squeeze	ai.onnx(1-10,11-12,13+)
Sub	ai.onnx(7-12,13,14+)
Tan	ai.onnx(7+)
ThresholdedRelu	ai.onnx(10+)
Transpose	ai.onnx(1-12,13+)	need perf optimization
Unsqueeze	ai.onnx(1-10,11-12,13+)

2.3 KiB Raw Blame History

Operators Support Table

2.3 KiB

Raw Blame History