GatherND - 12 vs 13

Next section compares an older to a newer version of the same operator after both definition are converted into markdown text. Green means an addition to the newer version, red means a deletion. Anything else is unchanged.

Files changed (1) hide show

1. GatherND12 → GatherND13 +26 -31

GatherND12 → GatherND13 RENAMED Viewed

	@@ -1 +1 @@
1 1	Given data tensor of rank r >= 1, indices tensor of rank q >= 1, and batch_dims integer b, this operator gathers
2 2	slices of data into an output tensor of rank q + r - indices_shape[-1] - 1 - b.
3 3	indices is an q-dimensional integer tensor, best thought of as a (q-1)-dimensional tensor of index-tuples into data,
4 4	where each element defines a slice of data
5 5	batch_dims (denoted as b) is an integer indicating the number of batch dimensions, i.e the leading b number of dimensions of
6 6	data tensor and indices are representing the batches, and the gather starts from the b+1 dimension.
7 7	Some salient points about the inputs' rank and shape:
8 8	1) r >= 1 and q >= 1 are to be honored. There is no dependency condition to be met between ranks r and q
9 9	2) The first b dimensions of the shape of indices tensor and data tensor must be equal.
10 10	3) b < min(q, r) is to be honored.
11 11	4) The indices_shape[-1] should have a value between 1 (inclusive) and rank r-b (inclusive)
12 12	5) All values in indices are expected to be within bounds [-s, s-1] along axis of size s (i.e.) -data_shape[i] <= indices[...,i] <= data_shape[i] - 1.
13 13	It is an error if any of the index values are out of bounds.
14 14	The output is computed as follows:
15 15	The output tensor is obtained by mapping each index-tuple in the indices tensor to the corresponding slice of the input data.
16 16	1) If indices_shape[-1] > r-b => error condition
17 17	2) If indices_shape[-1] == r-b, since the rank of indices is q, indices can be thought of as N (q-b-1)-dimensional tensors
18 18	containing 1-D tensors of dimension r-b, where N is an integer equals to the product of 1 and all the elements in the batch dimensions
19 19	of the indices_shape. Let us think of each such r-b ranked tensor as indices_slice. Each *scalar value* corresponding to data[0:b-1,indices_slice]
20 20	is filled into the corresponding location of the (q-b-1)-dimensional tensor to form the output tensor (Example 1 below)
21 21	3) If indices_shape[-1] < r-b, since the rank of indices is q, indices can be thought of as N (q-b-1)-dimensional tensor
22 22	containing 1-D tensors of dimension < r-b. Let us think of each such tensors as indices_slice. Each *tensor slice* corresponding
23 23	to data[0:b-1, indices_slice , :] is filled into the corresponding location of the (q-b-1)-dimensional tensor
24 24	to form the output tensor (Examples 2, 3, 4 and 5 below)
25 25	This operator is the inverse of ScatterND.
26	- Example 1
26	+ **Example 1**
27	- batch_dims = 0
27	+ batch_dims = 0
28	- data = [[0,1],[2,3]] # data_shape = [2, 2]
28	+ data = [[0,1],[2,3]] # data_shape = [2, 2]
29	+ indices = [[0,0],[1,1]] # indices_shape = [2, 2]
30	+ output = [0,3] # output_shape = [2]
29	- indices = [[0,0],[1,1]] # indices_shape = [2, 2]
30	- output = [0,3] # output_shape = [2]
31	+ **Example 2**
31	- Example 2
32	- batch_dims = 0
32	+ batch_dims = 0
33	+ data = [[0,1],[2,3]] # data_shape = [2, 2]
34	+ indices = [[1],[0]] # indices_shape = [2, 1]
35	+ output = [[2,3],[0,1]] # output_shape = [2, 2]
33	- data = [[0,1],[2,3]] # data_shape = [2, 2]
36	+ **Example 3**
34	- indices = [[1],[0]] # indices_shape = [2, 1]
37	+ batch_dims = 0
38	+ data = [[[0,1],[2,3]],[[4,5],[6,7]]] # data_shape = [2, 2, 2]
39	+ indices = [[0,1],[1,0]] # indices_shape = [2, 2]
35	- output = [[2,3],[0,1]] # output_shape = [2, 2]
40	+ output = [[2,3],[4,5]] # output_shape = [2, 2]
36	- Example 3
37	- batch_dims = 0
41	+ **Example 4**
38	- data = [[[0,1],[2,3]],[[4,5],[6,7]]] # data_shape = [2, 2, 2]
42	+ batch_dims = 0
43	+ data = [[[0,1],[2,3]],[[4,5],[6,7]]] # data_shape = [2, 2, 2]
39	- indices = [[0,1],[1,0]] # indices_shape = [2, 2]
44	+ indices = [[[0,1]],[[1,0]]] # indices_shape = [2, 1, 2]
40	- output = [[2,3],[4,5]] # output_shape = [2, 2]
45	+ output = [[[2,3]],[[4,5]]] # output_shape = [2, 1, 2]
41	- Example 4
46	+ **Example 5**
42	- batch_dims = 0
47	+ batch_dims = 1
43	- data = [[[0,1],[2,3]],[[4,5],[6,7]]] # data_shape = [2, 2, 2]
48	+ data = [[[0,1],[2,3]],[[4,5],[6,7]]] # data_shape = [2, 2, 2]
44	- indices = [[[0,1]],[[1,0]]] # indices_shape = [2, 1, 2]
49	+ indices = [[1],[0]] # indices_shape = [2, 1]
50	+ output = [[2,3],[4,5]] # output_shape = [2, 2]
45	- output = [[[2,3]],[[4,5]]] # output_shape = [2, 1, 2]
46	-
47	- Example 5
48	-
49	- batch_dims = 1
50	-
51	- data = [[[0,1],[2,3]],[[4,5],[6,7]]] # data_shape = [2, 2, 2]
52	-
53	- indices = [[1],[0]] # indices_shape = [2, 1]
54	-
55	- output = [[2,3],[4,5]] # output_shape = [2, 2]
56 51	### Attributes
57 52	* **batch_dims - INT** (default is '0'):
58 53	The number of batch dimensions. The gather of indexing starts from dimension of data[batch_dims:]
59 54	### Inputs
60 55	- **data** (heterogeneous) - **T**:
61 56	Tensor of rank r >= 1.
62 57	- **indices** (heterogeneous) - **tensor(int64)**:
63 58	Tensor of rank q >= 1. All index values are expected to be within bounds [-s, s-1] along axis of size s. It is an error if any of the index values are out of bounds.
64 59	### Outputs
65 60	- **output** (heterogeneous) - **T**:
66 61	Tensor of rank q + r - indices_shape[-1] - 1.
67 62	### Type Constraints
68	- * **T** in ( tensor(bool), tensor(complex128), tensor(complex64), tensor(double), tensor(float), tensor(float16), tensor(int16), tensor(int32), tensor(int64), tensor(int8), tensor(string), tensor(uint16), tensor(uint32), tensor(uint64), tensor(uint8) ):
63	+ * **T** in ( tensor(bfloat16), tensor(bool), tensor(complex128), tensor(complex64), tensor(double), tensor(float), tensor(float16), tensor(int16), tensor(int32), tensor(int64), tensor(int8), tensor(string), tensor(uint16), tensor(uint32), tensor(uint64), tensor(uint8) ):
69 64	Constrain input and output types to any tensor type.