Lines Matching full:shape

15 - A shape inference mechanism is able to compute the result shape solely based on input operand sha…
19 - The operation's result shape is compatible with —though not necessarily identical to—…
57 ## Shape inference
59 The shape inference process begins by correcting rank differences in input operands. A shape is exp…
62 ExpandRank(shape, rank):
63 	while len(shape) < rank:
64 		shape.prepend(1)
67 Given the shapes of two ranked input operands, the result's shape is inferred by equalizing input r…
77   # Infer shape
85 …shape for an operation with an arbitrary number of input operands is then inferred by discarding u…
95 	# Infer result shape
104 …shape inference process. If a failure occurs during shape inference, it is concluded that input op…
106 …ion continues by checking for a matching rank between the previously inferred shape and the result.
108 …nteed, each dimension of the inferred shape is compared with the corresponding dimension of the ac…
114 …st is convenient in certain scenarios, such as an intermediate state of a shape inference pass. Ul…
124 	# Run shape inference
152 // The shape of %arg0 is broadcast from tensor<1xi32> to tensor<4xi32>.
155 // The shape of %result is inferred as tensor<4xi32>, while the actual result
156 // type is tensor<?xi32>. The inferred shape is compatible with the actual shape.
159 // The shape of %arg0 is first expanded to tensor<1x1x4xi32> and then broadcast
167 // No result shape verification is needed when the result is unranked.
170 // No result shape verification needed when all inputs are unranked.
181 // The inferred result shape is tensor<3xi32>, but the actual result shape is
185 // The inferred result shape is tensor<?xi32>, but the actual shape is
186 // tensor<4xi32>. The inferred shape is not compatible with the actual shape.
189 // The inferred result shape is tensor<2xi32>, but the actual result shape is
193 // The inferred result shape is tensor<1xi32>, but the actual result shape is