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

Introduce "valid dimension", used as needed when calculating operand shapes #641

Merged
merged 5 commits into from
Apr 16, 2024
+26 −8
Merged

Introduce "valid dimension", used as needed when calculating operand shapes #641

Changes from all commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
6563518
resample2d: Validate that dimensions are valid unsigned longs
inexorabletash Apr 8, 2024
e737dcb
Introduce 'valid dimension' term
inexorabletash Apr 9, 2024
4f30583
Validate calculated dimensions when determining output shapes
inexorabletash Apr 9, 2024
e747fbb
Update index.bs
inexorabletash Apr 15, 2024
67027f2
Update index.bs
inexorabletash Apr 16, 2024
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
34 changes: 26 additions & 8 deletions index.bs
View file
Original file line number Diff line number Diff line change
@@ -1049,11 +1049,17 @@ dictionary MLOperandDescriptor {
1. Return |elementLength| * |elementSize|.
</details>

<p>
A <dfn>valid dimension</dfn> is an integer greater than zero in the range of {{unsigned long}}. Implementations may impose a smaller upper bound.
</p>

Issue(391): Should 0-size dimensions be supported?

<details open algorithm>
<summary>
To <dfn for="MLOperandDescriptor">check dimensions</dfn> given {{MLOperandDescriptor}} |descriptor|, run the following steps:
</summary>
1. If any element of |descriptor|.{{MLOperandDescriptor/dimensions}} is too large to be supported by the implementation, return false.
1. If any element of |descriptor|.{{MLOperandDescriptor/dimensions}} is not a [=valid dimension=], return false.
1. If |descriptor|.{{MLOperandDescriptor/dimensions}}'s [=list/size=] is too large to be supported by the implementation, return false.

Issue(456): The maximum number of operand dimensions is not defined, but native ML APIs usually have a maximum supported size.
@@ -1364,6 +1370,7 @@ Data truncation will occur when the values in the range exceed the range of the
1. Let |descriptor| be a new {{MLOperandDescriptor}}.
1. Set |descriptor|.{{MLOperandDescriptor/dataType}} to |type|.
1. Let |size| be max(0, ceil((|end| - |start|)/|step|)).
1. If |size| is not a [=valid dimension=], then [=exception/throw=] a {{TypeError}}.
1. Set |descriptor|.{{MLOperandDescriptor/dimensions}} to the [=/list=] « |size| ».
1. *Make graph connections:*
1. Let |operand| be the result of [=creating an MLOperand=] given [=this=] and |descriptor|.
@@ -1771,7 +1778,10 @@ partial interface MLGraphBuilder {
If the shape of each corresponding dimension and type of the operands, except for those of the dimension given by |axis|, is not the same, fail.
</div>
1. If |dim| is not equal to |axis| and if |input|'s [=MLOperand/shape=][|dim|] is not equal to |first|'s [=MLOperand/shape=][|dim|], then [=exception/throw=] a {{TypeError}}.
1. If |dim| is equal to |axis|, add to |desc|.{{MLOperandDescriptor/dimensions}}[|axis|] the value of |input|'s [=MLOperand/shape=][|dim|].
1. If |dim| is equal to |axis|:
1. Let |size| be the sum of |desc|.{{MLOperandDescriptor/dimensions}}[|axis|] and |input|'s [=MLOperand/shape=][|dim|].
1. If |size| is not a [=valid dimension=], then [=exception/throw=] a {{TypeError}}.
1. Set |desc|.{{MLOperandDescriptor/dimensions}}[|axis|] to |size|.
1. *Make graph connections:*
1. Let |output| be the result of [=creating an MLOperand=] given [=this=] and |desc|.
1. Let |operator| be an [=operator=] for the concat operation, given |inputs| and |axis|.
@@ -1970,6 +1980,7 @@ partial interface MLGraphBuilder {
: {{MLInputOperandLayout/"nhwc"}}
:: Let |outputShape| be « |batches|, floor( |outputSizes|[0] ), floor( |outputSizes|[1] ), |outputChannels| ».
</dl>
1. If any [=list/item=] in |outputShape| is not a [=valid dimension=], then [=exception/throw=] a {{TypeError}}.
1. Let |desc| be a new {{MLOperandDescriptor}}.
1. Set |desc|.{{MLOperandDescriptor/dataType}} to |input|'s [=MLOperand/dataType=].
1. Set |desc|.{{MLOperandDescriptor/dimensions}} to |outputShape|.
@@ -2182,6 +2193,7 @@ partial interface MLGraphBuilder {
: {{MLInputOperandLayout/"nhwc"}}
:: Let |outputShape| be « |batches|, floor( |outputSizes|[0] ), floor( |outputSizes|[1] ), |outputChannels| ».
</dl>
1. If any [=list/item=] in |outputShape| is not a [=valid dimension=], then [=exception/throw=] a {{TypeError}}.
1. Let |desc| be a new {{MLOperandDescriptor}}.
1. Set |desc|.{{MLOperandDescriptor/dataType}} to |input|'s [=MLOperand/dataType=].
1. Set |desc|.{{MLOperandDescriptor/dimensions}} to |outputShape|.
@@ -4452,7 +4464,9 @@ partial interface MLGraphBuilder {
1. If [=MLGraphBuilder/validating operand=] with [=this=] and |input| returns false, then [=exception/throw=] a {{TypeError}}.
1. If |beginningPadding|'s [=list/size=] and |endingPadding|'s [=list/size=] are not both equal to |input|'s [=MLOperand/rank=], then [=exception/throw=] a "{{TypeError}}".
1. Let |desc| be a copy of |input|.{{MLOperand/[[descriptor]]}}.
1. Set |desc|.{{MLOperandDescriptor/dimensions}} to the result of [=MLGraphBuilder/calculating padding output sizes=] given |input|, |beginningPadding| and |endingPadding|.
1. Let |outputShape| be the result of [=MLGraphBuilder/calculating padding output sizes=] given |input|, |beginningPadding| and |endingPadding|.
1. If any [=list/item=] in |outputShape| is not a [=valid dimension=], then [=exception/throw=] a {{TypeError}}.
1. Set |desc|.{{MLOperandDescriptor/dimensions}} to |outputShape|.
1. *Make graph connections:*
1. Let |output| be the result of [=creating an MLOperand=] given [=this=] and |desc|.
1. Let |operator| be an [=operator=] for the padding operation, given |beginningPadding|, |endingPadding| and |options|.
@@ -4670,8 +4684,10 @@ partial interface MLGraphBuilder {
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. If any [=list/item=] in |outputShape| is not a [=valid dimension=], then [=exception/throw=] a {{TypeError}}.
1. Set |desc|.{{MLOperandDescriptor/dimensions}} to |outputShape|.
1. *Make graph connections:*
1. Set |desc|.{{MLOperandDescriptor/dimensions}} to 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 |output| be the result of [=creating an MLOperand=] given [=this=] and |desc|.
1. Let |operator| be an [=operator=] for the |op| pooling operation, given |options|.
1. Set |output|.{{MLOperand/[[operator]]}} to |operator|.
@@ -5065,8 +5081,10 @@ partial interface MLGraphBuilder {
</summary>
1. Let |desc| be a new {{MLOperandDescriptor}} initialized to |input|.{{MLOperand/[[descriptor]]}}.
1. For |index| in [=the range=] 0 to |options|.{{MLResample2dOptions/axes}}'s [=list/size=], exclusive:
1. If |options|.{{MLResample2dOptions/sizes}} [=map/exists=], set |desc|.{{MLOperandDescriptor/dimensions}}[|options|.{{MLResample2dOptions/axes}}[|index|]] to |options|.{{MLResample2dOptions/sizes}}[|index|].
1. Otherwise, set |desc|.{{MLOperandDescriptor/dimensions}}[|options|.{{MLResample2dOptions/axes}}[|index|]] to floor(|input|'s [=MLOperand/shape=][|options|.{{MLResample2dOptions/axes}}[|index|]] * |options|.{{MLResample2dOptions/scales}}[|index|]).
1. If |options|.{{MLResample2dOptions/sizes}} [=map/exists=], then let |size| be |options|.{{MLResample2dOptions/sizes}}[|index|].
1. Otherwise, let |size| be floor(|input|'s [=MLOperand/shape=][|options|.{{MLResample2dOptions/axes}}[|index|]] * |options|.{{MLResample2dOptions/scales}}[|index|]).
1. If |size| is not a [=valid dimension=], then return failure.
1. Set |desc|.{{MLOperandDescriptor/dimensions}}[|options|.{{MLResample2dOptions/axes}}[|index|]] to |size|.
1. Return |desc|.
</details>

@@ -5077,7 +5095,7 @@ partial interface MLGraphBuilder {
1. If [=MLGraphBuilder/validating operand=] with [=this=] and |input| returns false, then [=exception/throw=] a {{TypeError}}.
1. If |input|'s [=MLOperand/rank=] is not 4, then [=exception/throw=] a {{TypeError}}.
1. If [=MLGraphBuilder/checking resample options=] given |options| returns false, then [=exception/throw=] a {{TypeError}}.
1. Let |desc| be the result of [=MLGraphBuilder/calculating resample output sizes=] given |input| and |options|.
1. Let |desc| be the result of [=MLGraphBuilder/calculating resample output sizes=] given |input| and |options|. If that returns failure, then [=exception/throw=] a {{TypeError}}.
1. *Make graph connections:*
1. Let |output| be the result of [=creating an MLOperand=] given [=this=] and |desc|.
1. Let |operator| be an [=operator=] for the resample 2D operation, given |options|.
@@ -5113,7 +5131,7 @@ partial interface MLGraphBuilder {
1. If [=MLGraphBuilder/validating operand=] with [=this=] and |input| returns false, then [=exception/throw=] a {{TypeError}}.
1. Let |outputShape| be an empty array of {{unsigned long}}.
1. If |newShape|'s [=list/size=] is 0, set |outputShape| to an empty [=/list=] for a scalar.
1. If any value in |newShape| is 0, then [=exception/throw=] a {{TypeError}}.
1. If any [=list/item=] in |newShape| is not a [=valid dimension=], then [=exception/throw=] a {{TypeError}}.
1. Let |inputElementCount| be the product of all elements in |input|'s [=MLOperand/shape=]. Empty dimensions yield an |inputElementCount| of 1.
1. If product of all values in |newShape| is not equal to |inputElementCount|, then [=exception/throw=] a {{TypeError}}.
1. Let |desc| be a copy of |input|.{{MLOperand/[[descriptor]]}}.