**Arguments:**
- *input*: an {{MLOperand}}. The input N-D tensor.
- *mean*: an {{MLOperand}}. Specifies the 1-D tensor of the mean values of the input features across the batch whose length is equal to the size of the input dimension denoted by {{MLBatchNormalizationOptions/axis}}.
- *variance*: an {{MLOperand}}. The 1-D tensor of the variance values of the input features across the batch whose length is equal to the size of the input dimension denoted by {{MLBatchNormalizationOptions/axis}}.
- *options*: an optional {{MLBatchNormalizationOptions}}. Specifies the optional parameters of the operation.
- - *scale*: an {{MLOperand}}. The 1-D tensor of the scaling values whose length is equal to the size of the input dimension denoted by *options.axis*.
- - *bias*: an {{MLOperand}}. The 1-D tensor of the bias values whose length is equal to the size of the input dimension denoted by *options.axis*.
- - *axis*: an {{unsigned long}} scalar. The index to the feature count dimension of the input shape for which the mean and variance values are. Its value must be in the range [0, N-1] where N is the rank of input tensor. When it's not specified, the default value is 1.
- - *epsilon*: a {{float}} scalar. A small value to prevent computational error due to divide-by-zero. The default value is 0.00001 when not specified.
- - *activation*: an {{MLActivation}}. The optional activation function that immediately follows the normalization operation.
**Returns:** an {{MLOperand}}. The batch-normalized N-D tensor of the same shape as the input tensor.
The behavior of this operation when the input tensor is 4-D of the *"nchw"* layout and the activation is of operator type *relu* can be generically emulated from the usage of other operations as follow. However, user agents typically have a more efficient implementation for it, therefore its usage is encouraged from the performance standpoint.
@@ -1517,11 +1767,14 @@ partial interface MLGraphBuilder {
+
+
The behavior of this operation can be generically emulated from the usage of
other operations as follow. However, user agents typically have a more
efficient implementation for it, therefore its usage is encouraged from the
performance standpoint.
-
+
+
if (options.minValue === undefined) {
if (options.maxValue === undefined) {
return x;
@@ -1537,17 +1790,23 @@ partial interface MLGraphBuilder {
builder.constant(options.maxValue));
}
}
-
+
-To
check clamp options given |options|, run the following steps:
- 1. If |options| is not an object that [=implements=] {{MLClampOptions}}, then return `false`.
+
+
+ To check clamp options given |options|, run the following steps:
+
+
+ 1. If |options| is not an [=object=] that [=implements=] {{MLClampOptions}}, then return `false`.
1. If |options|.{{MLClampOptions/minValue}} and |options|.{{MLClampOptions/maxValue}} are not a [=numeric type=], then then return `false`.
1. If |options|.{{MLClampOptions/minValue}} is greater than |options|.{{MLClampOptions/maxValue}}, then return `false`.
1. Return `true`.
+
+
#### The {{MLGraphBuilder/clamp(operand, options)}} method #### {#api-mlgraphbuilder-clamp-operand-options}
-
+
**Arguments:**
- *operand*: an {{MLOperand}}. The input tensor.
- *options*: an optional {{MLClampOptions}}. The optional parameters of the operation.
@@ -1556,8 +1815,12 @@ To check clamp options given |options|, run the following steps:
**Returns:**
- an {{MLOperand}}. The output tensor of the same shape as *operand*.
-
+
+
+
The {{MLGraphBuilder/clamp(operand, options)}} method steps are:
+
+
1. Let |operand| be the first argument.
1. Let |options| be the second argument.
1. If running the
check clamp options steps with |options| returns `false`, then throw a "{{TypeError}}" {{DOMException}} and abort these steps.
@@ -1571,10 +1834,11 @@ To
check clamp options given |options|, run the following steps:
1. Register the |result|.{{MLOperand/[[operand]]}} as output to |operatorImpl|.
1. Store a reference to |operatorImpl| in |result|.{{MLOperand/[[operator]]}}.
1. Return |result|.
-
+
#### The {{MLGraphBuilder/clamp(options)}} method #### {#api-mlgraphbuilder-clamp-options}
-
+
**Arguments:**
- *options*: an optional {{MLClampOptions}}. The optional parameters of the operation.
- *minValue*: a {{float}} scalar. Specifies the minimum value of the range. When it is not specified, the clamping is not performed on the lower limit of the range.
@@ -1582,8 +1846,12 @@ To check clamp options given |options|, run the following steps:
**Returns:**
- an {{MLActivation}}. The operator representing the clamp operation.
-
+
+
+
The {{MLGraphBuilder/clamp(options)}} method steps are:
+
+
1. Let |options| be the first argument.
1. If running the
check clamp options steps with |options| returns `false`, then throw a "{{TypeError}}" {{DOMException}} and abort these steps.
1. Let |op| be the result of invoking the
create MLActivation steps with `"clamp"` and |options|.
@@ -1592,7 +1860,8 @@ To
check clamp options given |options|, run the following steps:
1. Make a request to the underlying platform to connect |op| with the [=implementation-defined=] platform operator for clamp |operatorImpl|.
1. Store a reference to |operatorImpl| in |op|.{{MLActivation/[[operator]]}}.
1. Return |op|.
-
+
### The concat() method ### {#api-mlgraphbuilder-concat}
Concatenates the input tensors along a given axis.
@@ -1612,8 +1881,12 @@ partial interface MLGraphBuilder {
that all the inputs concatenated along. The size of that dimension is
computed as the sum of all the input sizes of the same dimension.
-
+
+
+
The {{MLGraphBuilder/concat(inputs, axis)}} steps are:
+
+
The permissions and context validity have been checked by [[#api-mlgraphbuilder-constructor]] steps.
@@ -1642,7 +1915,8 @@ partial interface MLGraphBuilder {
1. Make a request to the underlying platform to create an operator for this method with |inputs| connected as input and |output| connected as output and store a reference to the [=implementation-defined=] platform object to |output|.{{MLOperand/[[operand]]}}.
1. If that fails, throw a "{{DataError}}" {{DOMException}} and stop.
1. Return |output|.
-
+
+
### The conv2d() method ### {#api-mlgraphbuilder-conv2d}
Compute a 2-D convolution given 4-D input and filter tensors
@@ -3177,12 +3451,15 @@ partial interface MLGraphBuilder {
**Returns:** a sequence of {{MLOperand}}. The splitted output tensors. If *splits* is an {{unsigned long}}, the length of the output sequence equals to *splits*. The shape of each output tensor is the same as *input* except the dimension size of *axis* equals to the quotient of dividing the dimension size of *input* along *axis* by *splits*. If *splits* is a sequence of {{unsigned long}}, the length of the output sequence equals to the length of *splits*. The shape of the i-th output tensor is the same as as *input* except along *axis* where the dimension size is *splits[i]*.
-
+
+
+
The behavior of this operation can be generically emulated from the usage of
other operations as follow. However, user agents typically have a more
efficient implementation for it, therefore its usage is encouraged from the
performance standpoint.
-
+
+
// This sample shows the case that the splits parameter is an array.
const outputs = [];
let starts = Array(input_rank).fill(0);
@@ -3195,8 +3472,8 @@ partial interface MLGraphBuilder {
start += size;
}
return outputs;
-
-
+
+
### The squeeze() method ### {#api-mlgraphbuilder-squeeze}
@@ -3279,49 +3556,54 @@ const context = await navigator.ml.createContext({powerPreference: 'low-power'})
-The following code builds a graph as:
+Given the following build graph:
-constant1 ---+
- +--- Add ---> intermediateOutput1 ---+
-input1 ---+ |
- +--- Mul---> output
-constant2 ---+ |
- +--- Add ---> intermediateOutput2 ---+
-input2 ---+
+ constant1 ---+
+ +--- Add ---> intermediateOutput1 ---+
+ input1 ---+ |
+ +--- Mul---> output
+ constant2 ---+ |
+ +--- Add ---> intermediateOutput2 ---+
+ input2 ---+
-
-// Use tensors in 4 dimensions.
-const TENSOR_DIMS = [1, 2, 2, 2];
-const TENSOR_SIZE = 8;
+
+
+ The following code implements the graph:
+
+
+ // Use tensors in 4 dimensions.
+ const TENSOR_DIMS = [1, 2, 2, 2];
+ const TENSOR_SIZE = 8;
-const builder = new MLGraphBuilder(context);
+ const builder = new MLGraphBuilder(context);
-// Create MLOperandDescriptor object.
-const desc = {type: 'float32', dimensions: TENSOR_DIMS};
+ // Create MLOperandDescriptor object.
+ const desc = {type: 'float32', dimensions: TENSOR_DIMS};
-// constant1 is a constant MLOperand with the value 0.5.
-const constantBuffer1 = new Float32Array(TENSOR_SIZE).fill(0.5);
-const constant1 = builder.constant(desc, constantBuffer1);
+ // constant1 is a constant MLOperand with the value 0.5.
+ const constantBuffer1 = new Float32Array(TENSOR_SIZE).fill(0.5);
+ const constant1 = builder.constant(desc, constantBuffer1);
-// input1 is one of the input MLOperands. Its value will be set before execution.
-const input1 = builder.input('input1', desc);
+ // input1 is one of the input MLOperands. Its value will be set before execution.
+ const input1 = builder.input('input1', desc);
-// constant2 is another constant MLOperand with the value 0.5.
-const constantBuffer2 = new Float32Array(TENSOR_SIZE).fill(0.5);
-const constant2 = builder.constant(desc, constantBuffer2);
+ // constant2 is another constant MLOperand with the value 0.5.
+ const constantBuffer2 = new Float32Array(TENSOR_SIZE).fill(0.5);
+ const constant2 = builder.constant(desc, constantBuffer2);
-// input2 is another input MLOperand. Its value will be set before execution.
-const input2 = builder.input('input2', desc);
+ // input2 is another input MLOperand. Its value will be set before execution.
+ const input2 = builder.input('input2', desc);
-// intermediateOutput1 is the output of the first Add operation.
-const intermediateOutput1 = builder.add(constant1, input1);
+ // intermediateOutput1 is the output of the first Add operation.
+ const intermediateOutput1 = builder.add(constant1, input1);
-// intermediateOutput2 is the output of the second Add operation.
-const intermediateOutput2 = builder.add(constant2, input2);
+ // intermediateOutput2 is the output of the second Add operation.
+ const intermediateOutput2 = builder.add(constant2, input2);
-// output is the output MLOperand of the Mul operation.
-const output = builder.mul(intermediateOutput1, intermediateOutput2);
-
+ // output is the output MLOperand of the Mul operation.
+ const output = builder.mul(intermediateOutput1, intermediateOutput2);
+
+
@@ -3333,24 +3615,28 @@ const graph = await builder.build({'output': output});
-The following code executes the compiled graph.
-
-// Setup the input buffers with value 1.
-const inputBuffer1 = new Float32Array(TENSOR_SIZE).fill(1);
-const inputBuffer2 = new Float32Array(TENSOR_SIZE).fill(1);
-const outputBuffer = new Float32Array(TENSOR_SIZE);
-
-// Execute the compiled graph with the specified inputs.
-const inputs = {
- 'input1': inputBuffer1,
- 'input2': inputBuffer2,
-};
-const outputs = {'output': outputBuffer};
-const result = await context.compute(graph, inputs, outputs);
-
-console.log('Output value: ' + result.outputs.output);
-// Output value: 2.25,2.25,2.25,2.25,2.25,2.25,2.25,2.25
-
+
+
+ The following code executes the compiled graph.
+
+
+ // Setup the input buffers with value 1.
+ const inputBuffer1 = new Float32Array(TENSOR_SIZE).fill(1);
+ const inputBuffer2 = new Float32Array(TENSOR_SIZE).fill(1);
+ const outputBuffer = new Float32Array(TENSOR_SIZE);
+
+ // Execute the compiled graph with the specified inputs.
+ const inputs = {
+ 'input1': inputBuffer1,
+ 'input2': inputBuffer2,
+ };
+ const outputs = {'output': outputBuffer};
+ const result = await context.compute(graph, inputs, outputs);
+
+ console.log('Output value: ' + result.outputs.output);
+ // Output value: 2.25,2.25,2.25,2.25,2.25,2.25,2.25,2.25
+
+
# Appendices # {#appendices}