Skip to content
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.

Sign up for GitHub

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

Jump to bottom

Add the reduction algorithms #423

Merged
merged 1 commit into from
Jun 29, 2023
Merged

Add the reduction algorithms #423

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
83 changes: 81 additions & 2 deletions index.bs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3172,7 +3172,7 @@ partial interface MLGraphBuilder {


### Reduction operations ### {#api-mlgraphbuilder-reduce}
Reduce the input along the dimensions given in *axes*.
Reduce the input tensor along all dimensions, or along the axes specified in the {{MLReduceOptions/axes}} array parameter. For each specified axis, the dimension with that index is reduced, i.e. the resulting tensor will not contain it, unless the {{MLReduceOptions/keepDimensions}} option is specified. The values of the resulting tensor are calculated using the specified reduction function that takes as parameters all the values across the reduced dimension.
<script type=idl>
dictionary MLReduceOptions {
sequence<unsigned long> axes = null;
Expand All @@ -3192,7 +3192,8 @@ partial interface MLGraphBuilder {
MLOperand reduceSumSquare(MLOperand input, optional MLReduceOptions options = {});
};
</script>
<div algorithm=reduce>

<div>
**Arguments:**
- *input*: an {{MLOperand}}. The input tensor.
- *options*: an optional {{MLReduceOptions}}. The optional parameters of the operation.
Expand All @@ -3202,7 +3203,9 @@ partial interface MLGraphBuilder {
The default value is false.

**Returns:** an {{MLOperand}}. The reduced output tensor.
</div>

<div class="note">
**Reduction types:**
- *L1*: Compute the <a href="https://mathworld.wolfram.com/L1-Norm.html">L1 norm</a> of all the input values along the axes.
- *L2*: Compute the <a href="https://mathworld.wolfram.com/L2-Norm.html">L2 norm</a> of all the input values along the axes.
Expand All @@ -3216,6 +3219,82 @@ partial interface MLGraphBuilder {
- *SumSquare*: Compute the sum of the square of all the input values along the axes.
</div>

<details open>
<summary>
To <dfn for="MLGraphBuilder" data-lt="reduce-op">create reduce operation</dfn> given |op|, |input| and |options|, run the following steps:
</summary>
<div algorithm=reduce class=algorithm-steps>
1. [=Assert=]: |op| is one of "reduceL1", "reduceL2", "reduceLogSum", "reduceLogSumExp", "reduceMax", "reduceMean", "reduceMin", "reduceProduct", "reduceSum", "reduceSumSquare".
1. If |input| is not an instance of {{MLOperand}}, then throw a "{{TypeError}}" {{DOMException}} and stop.
1. If |options| is `undefined`, let |options| be a new {{MLReduceOptions}} object with |options|.{{MLReduceOptions/keepDimensions}} set to `false` and |options|.{{MLReduceOptions/axes}} set to `null`.
1. If any of the following sub-steps fail, throw an "{{OperationError}}" {{DOMException}} and stop.
1. Let |output| be the result of invoking the <a>copy MLOperand</a> steps given |input|.
1. Make a request to the underlying platform to:
1. Let |opImpl| be an [=implementation-defined=] platform operator for the |op| reduce operation, given |options|.
1. Store a reference of |opImpl| in |output|.{{MLOperand/[[operator]]}}.
1. Create an [=implementation-defined=] platform operand |outputImpl| to represent the output, given |output| and |opImpl|.
1. Store a reference to |outputImpl| in |output|.{{MLOperand/[[operand]]}}.
1. Connect |input|.{{MLOperand/[[operand]]}} as input to |opImpl|.
1. Connect |output|.{{MLOperand/[[operand]]}} as output to |opImpl|.
1. Return |output|.
</div>
</details>

<details open>
<summary>
The following reduce algorithms are supported.
</summary>
The {{MLGraphBuilder/reduceL1(input, options)}} steps are:
1. Let |output| be the result of running the [=MLGraphBuilder/reduce-op | create reduce operation =] given "reduceL1", |input| and |options|.
1. If that throws an error, then re-throw the error and stop.
1. Return |output|.

The {{MLGraphBuilder/reduceL2(input, options)}} steps are:
1. Let |output| be the result of running the [=MLGraphBuilder/reduce-op | create reduce operation =] given "reduceL2", |input| and |options|.
1. If that throws an error, then re-throw the error and stop.
1. Return |output|.

The {{MLGraphBuilder/reduceLogSum(input, options)}} steps are:
1. Let |output| be the result of running the [=MLGraphBuilder/reduce-op | create reduce operation =] given "reduceLogSum", |input| and |options|.
1. If that throws an error, then re-throw the error and stop.
1. Return |output|.

The {{MLGraphBuilder/reduceLogSumExp(input, options)}} steps are:
1. Let |output| be the result of running the [=MLGraphBuilder/reduce-op | create reduce operation =] given "reduceLogSumExp", |input| and |options|.
1. If that throws an error, then re-throw the error and stop.
1. Return |output|.

The {{MLGraphBuilder/reduceMax(input, options)}} steps are:
1. Let |output| be the result of running the [=MLGraphBuilder/reduce-op | create reduce operation =] given "reduceMax", |input| and |options|.
1. If that throws an error, then re-throw the error and stop.
1. Return |output|.

The {{MLGraphBuilder/reduceMean(input, options)}} steps are:
1. Let |output| be the result of running the [=MLGraphBuilder/reduce-op | create reduce operation =] given "reduceMean", |input| and |options|.
1. If that throws an error, then re-throw the error and stop.
1. Return |output|.

The {{MLGraphBuilder/reduceMin(input, options)}} steps are:
1. Let |output| be the result of running the [=MLGraphBuilder/reduce-op | create reduce operation =] given "reduceMin", |input| and |options|.
1. If that throws an error, then re-throw the error and stop.
1. Return |output|.

The {{MLGraphBuilder/reduceProduct(input, options)}} steps are:
1. Let |output| be the result of running the [=MLGraphBuilder/reduce-op | create reduce operation =] given "reduceProduct", |input| and |options|.
1. If that throws an error, then re-throw the error and stop.
1. Return |output|.

The {{MLGraphBuilder/reduceSum(input, options)}} steps are:
1. Let |output| be the result of running the [=MLGraphBuilder/reduce-op | create reduce operation =] given "reduceSum", |input| and |options|.
1. If that throws an error, then re-throw the error and stop.
1. Return |output|.

The {{MLGraphBuilder/reduceSumSquare(input, options)}} steps are:
1. Let |output| be the result of running the [=MLGraphBuilder/reduce-op | create reduce operation =] given "reduceSumSquare", |input| and |options|.
1. If that throws an error, then re-throw the error and stop.
1. Return |output|.
</details>

### The relu() method ### {#api-mlgraphbuilder-relu}
Compute the <a href="https://en.wikipedia.org/wiki/Rectifier_(neural_networks)">rectified linear function</a> of the input tensor.
<script type=idl>
Expand Down