Remove pool2d MLRoundingType - Simplify the operand layout support of conv2d and pooling 2d operations

index.bs

@@ -871,7 +871,7 @@ dictionary MLComputeResult {
 interface MLContext {
   Promise<MLComputeResult> compute(
       MLGraph graph, MLNamedArrayBufferViews inputs, MLNamedArrayBufferViews outputs);
-  
+
   MLOpSupportLimits opSupportLimits();
 };
 </script>
@@ -5283,19 +5283,14 @@ partial dictionary MLOpSupportLimits {
 ### Pooling operations ### {#api-mlgraphbuilder-pool2d}
 Compute a pooling operation across all the elements within the moving window over the input tensor.
 <script type=idl>
-enum MLRoundingType {
-  "floor",
-  "ceil"
-};
 
 dictionary MLPool2dOptions : MLOperatorOptions {
   sequence<[EnforceRange] unsigned long> windowDimensions;
   sequence<[EnforceRange] unsigned long> padding;
   sequence<[EnforceRange] unsigned long> strides;
   sequence<[EnforceRange] unsigned long> dilations;
   MLInputOperandLayout layout = "nchw";
-  MLRoundingType roundingType = "floor";
-  sequence<[EnforceRange] unsigned long> outputSizes;
+  required sequence<[EnforceRange] unsigned long> outputSizes;
 };
 
 partial interface MLGraphBuilder {
@@ -5346,16 +5341,16 @@ partial dictionary MLOpSupportLimits {
                 - input tensor: *[batches, height, width, inputChannels]*
                 - output tensor: *[batches, height, width, outputChannels]*
 
-    : <dfn>roundingType</dfn>
-    ::
-        The rounding function used to compute the output shape.
-
     : <dfn>outputSizes</dfn>
     ::
-        A list of length 2.
-        Specifies the sizes of the two spacial dimensions of the output tensor. When the output sizes are explicitly specified, the {{MLPool2dOptions/roundingType}} is ignored.
+        A list of length 2: *[outputHeight, outputWidth]*
+        Specifies the sizes of the two spatial dimensions of the output tensor.
 
-        If not specified, the output sizes are automatically computed.
+        The spatial dimensions of the output tensor can be calculated as follows:
+
+        *output size = ((input size - filter size + beginning padding + ending padding) / stride) + 1*
+
+        Then the caller either applies a floor or ceiling depending on whether partial window results are desired.
 </dl>
 
 <div dfn-for="MLGraphBuilder/averagePool2d(input, options), MLGraphBuilder/l2Pool2d(input, options), MLGraphBuilder/maxPool2d(input, options)" dfn-type=argument>
@@ -5366,13 +5361,8 @@ partial dictionary MLOpSupportLimits {
 
     **Returns:** an {{MLOperand}}. The output 4-D tensor that contains the
     result of the reduction. The logical shape is interpreted according to the
-    value of *layout*. More specifically, if the *options.roundingType* is {{MLRoundingType/"floor"}}, the spatial dimensions of the output tensor can be calculated as follows:
-
-    `output size = floor(1 + (input size - filter size + beginning padding + ending padding) / stride)`
-
-    or if *options.roundingType* is {{MLRoundingType/"ceil"}}:
-
-    `output size = ceil(1 + (input size - filter size + beginning padding + ending padding) / stride)`
+    value of *layout*, taking the batch and channel count from the input with
+    the spatial sizes from *outputSizes*.
 </div>
 
 {{MLOpSupportLimits}} has the following members for pooling operations:
@@ -5395,7 +5385,7 @@ partial dictionary MLOpSupportLimits {
 
 <details open algorithm>
   <summary>
-    To <dfn for=MLGraphBuilder>calculate pool2d output sizes</dfn> given {{MLInputOperandLayout}} |layout|, [=/list=] of 4 unsigned integers |inputShape|, {{MLRoundingType}} |roundingType|, [=/list=] of 2 unsigned integers |windowDimensions|, [=/list=] of 4 unsigned integers |padding|, [=/list=] of 2 unsigned integers |strides|, [=/list=] of 2 unsigned integers |dilations|, and optional [=/list=] of 2 unsigned integers |outputSizes|, perform these steps. They return a [=/list=] of 4 unsigned integers.
+    To <dfn for=MLGraphBuilder>calculate pool2d output sizes</dfn> given {{MLInputOperandLayout}} |layout|, [=/list=] of 4 unsigned integers |inputShape|, [=/list=] of 2 unsigned integers <var ignore>windowDimensions</var>, [=/list=] of 4 unsigned integers <var ignore>padding</var>, [=/list=] of 2 unsigned integers <var ignore>strides</var>, [=/list=] of 2 unsigned integers <var ignore>dilations</var>, and optional [=/list=] of 2 unsigned integers |outputSizes|, perform these steps. They return a [=/list=] of 4 unsigned integers.
   </summary>
     1. Switch on |layout|:
         <dl class=switch>
@@ -5404,21 +5394,7 @@ partial dictionary MLOpSupportLimits {
             : {{MLInputOperandLayout/"nhwc"}}
             :: Let « |batches|, |inputHeight|, |inputWidth|, |channels| » be |inputShape|.
         </dl>
-    1. If |outputSizes| is given, then let « |outputHeight|, |outputWidth| » be |outputSizes|.
-    1. Otherwise:
-        1. Let |outputSizes| be the result of [=MLGraphBuilder/calculating conv2d output sizes=] given |inputHeight|, |inputWidth|, |windowDimensions|[0], |windowDimensions|[1], |padding|, |strides|, and |dilations|.
-        1. Let « |outputHeight|, |outputWidth| » be |outputSizes|.
-        1. Switch on |roundingType|:
-            <dl class=switch>
-                : {{MLRoundingType/"floor"}}
-                ::
-                    1. Set |outputWidth| to floor(|outputWidth|).
-                    1. Set |outputHeight| to floor(|outputHeight|).
-                : {{MLRoundingType/"ceil"}}
-                ::
-                    1. Set |outputWidth| to ceiling(|outputWidth|).
-                    1. Set |outputHeight| to ceiling(|outputHeight|).
-            </dl>
+    1. Let « |outputHeight|, |outputWidth| » be |outputSizes|.
     1. Switch on |layout|:
         <dl class=switch>
             : {{MLInputOperandLayout/"nchw"}}
@@ -5451,7 +5427,7 @@ partial dictionary MLOpSupportLimits {
     1. If |options|.{{MLPool2dOptions/dilations}}'s [=list/size=] is not 2, then [=exception/throw=] a {{TypeError}}.
     1. If any value in |options|.{{MLPool2dOptions/dilations}} is not greater than 0, then [=exception/throw=] a {{TypeError}}.
     1. Let |desc| be a copy of |input|.{{MLOperand/[[descriptor]]}}.
-    1. Let |outputShape| be the result of [=MLGraphBuilder/calculating pool2d output sizes=] given |options|.{{MLPool2dOptions/layout}}, |input|'s [=MLOperand/shape=], |options|.{{MLPool2dOptions/roundingType}}, |options|.{{MLPool2dOptions/windowDimensions}}, |options|.{{MLPool2dOptions/padding}}, |options|.{{MLPool2dOptions/strides}}, |options|.{{MLPool2dOptions/dilations}}, and |options|.{{MLPool2dOptions/outputSizes}} (if it [=map/exists=]).
+    1. Let |outputShape| be the result of [=MLGraphBuilder/calculating pool2d output sizes=] given |options|.{{MLPool2dOptions/layout}}, |input|'s [=MLOperand/shape=], |options|.{{MLPool2dOptions/windowDimensions}}, |options|.{{MLPool2dOptions/padding}}, |options|.{{MLPool2dOptions/strides}}, |options|.{{MLPool2dOptions/dilations}}, and |options|.{{MLPool2dOptions/outputSizes}} (if it [=map/exists=]).
     1. If any [=list/item=] in |outputShape| is not a [=valid dimension=], then [=exception/throw=] a {{TypeError}}.
     1. Set |desc|.{{MLOperandDescriptor/shape}} to |outputShape|.
     1. *Make graph connections:*