0  0  MaxUnpool essentially computes the partial inverse of the MaxPool op.  MaxUnpool essentially computes the partial inverse of the MaxPool op. 
1  1  The input information to this op is typically the the output information from a MaxPool op. The first  The input information to this op is typically the the output information from a MaxPool op. The first 
2  2  input tensor X is the tensor that needs to be unpooled, which is typically the pooled tensor (first output)  input tensor X is the tensor that needs to be unpooled, which is typically the pooled tensor (first output) 
3  3  from MaxPool. The second input tensor, I, contains the indices to the (locally maximal) elements corrsponding  from MaxPool. The second input tensor, I, contains the indices to the (locally maximal) elements corrsponding 
4  4  to the elements in the first input tensor X. Input tensor I is typically the second output of the MaxPool op.  to the elements in the first input tensor X. Input tensor I is typically the second output of the MaxPool op. 
5  5  The third (optional) input is a tensor that specifies the output size of the unpooling operation.  The third (optional) input is a tensor that specifies the output size of the unpooling operation. 
6  6 


7  7  MaxUnpool is intended to do 'partial' inverse of the MaxPool op. 'Partial' because all the nonmaximal  MaxUnpool is intended to do 'partial' inverse of the MaxPool op. 'Partial' because all the nonmaximal 
8  8  values from the original input to MaxPool are set to zero in the output of the MaxUnpool op. Pooling  values from the original input to MaxPool are set to zero in the output of the MaxUnpool op. Pooling 
9  9  the result of an unpooling operation should give back the original input to the unpooling op.  the result of an unpooling operation should give back the original input to the unpooling op. 
10  10 


11  11  MaxUnpool can produce the same output size for several input sizes, which makes unpooling op ambiguous.  MaxUnpool can produce the same output size for several input sizes, which makes unpooling op ambiguous. 
12  12  The third input argument, output_size, is meant to disambiguate the op and produce output tensor of  The third input argument, output_size, is meant to disambiguate the op and produce output tensor of 
13  13  known/predictable size.  known/predictable size. 
14  14 


15  15  In addition to the inputs, MaxUnpool takes three attributes, namely kernel_shape, strides, and pads,  In addition to the inputs, MaxUnpool takes three attributes, namely kernel_shape, strides, and pads, 
16  16  which define the exact unpooling op. The attributes typically have the same values as the corrsponding  which define the exact unpooling op. The attributes typically have the same values as the corrsponding 
17  17  pooling op that the unpooling op is trying to invert.  pooling op that the unpooling op is trying to invert. 
18  18 


19  19  **Attributes**  **Attributes** 
20  20 


21  21  * **kernel_shape** (required):  * **kernel_shape** (required): 
22  22  The size of the kernel along each axis.  The size of the kernel along each axis. 
23  23  * **pads**:  * **pads**: 
24  24  Padding for the beginning and ending along each spatial axis, it can  Padding for the beginning and ending along each spatial axis, it can 
25  25  take any value greater than or equal to 0. The value represent the  take any value greater than or equal to 0. The value represent the 
26  26  number of pixels added to the beginning and end part of the  number of pixels added to the beginning and end part of the 
27  27  corresponding axis. pads format should be as follow [x1_begin,  corresponding axis. pads format should be as follow [x1_begin, 
28  28  x2_begin...x1_end, x2_end,...], where xi_begin the number of pixels  x2_begin...x1_end, x2_end,...], where xi_begin the number of pixels 
29  29  added at the beginning of axis i and xi_end, the number of pixels  added at the beginning of axis i and xi_end, the number of pixels 
30  30  added at the end of axis i. This attribute cannot be used  added at the end of axis i. This attribute cannot be used 
31  31  simultaneously with auto_pad attribute. If not present, the padding  simultaneously with auto_pad attribute. If not present, the padding 
32  32  defaults to 0 along start and end of each spatial axis.  defaults to 0 along start and end of each spatial axis. 
33  33  * **strides**:  * **strides**: 
34  34  Stride along each spatial axis.  Stride along each spatial axis. If not present, the stride defaults

 35   to 1 along each spatial axis. 
35  36 


36  37  **Inputs**  **Inputs** 
37  38 


38  39  Between 2 and 3 inputs.  Between 2 and 3 inputs. 
39  40 


40  41  * **X** (heterogeneous)  **T1**:  * **X** (heterogeneous)  **T1**: 
41  42  Input data tensor that has to be unpooled. This tensor is typically  Input data tensor that has to be unpooled. This tensor is typically 
42  43  the first output of the MaxPool op.Dimensions for image case are (N  the first output of the MaxPool op.Dimensions for image case are (N 
43  44  x C x H x W), where N is the batch size, C is the number of  x C x H x W), where N is the batch size, C is the number of 
44  45  channels, and H and W are the height and the width of the data. For  channels, and H and W are the height and the width of the data. For 
45  46  nonimage case, the dimensions are in the form of (N x C x D1 x D2  nonimage case, the dimensions are in the form of (N x C x D1 x D2 
46  47  ... Dn), where N is the batch size. Optionally, if dimension  ... Dn), where N is the batch size. Optionally, if dimension 
47  48  denotation is in effect, the operation expects the input data tensor  denotation is in effect, the operation expects the input data tensor 
48  49  to arrive with the dimension denotation of [DATA_BATCH,  to arrive with the dimension denotation of [DATA_BATCH, 
49  50  DATA_CHANNEL, DATA_FEATURE, DATA_FEATURE ...].  DATA_CHANNEL, DATA_FEATURE, DATA_FEATURE ...]. 
50  51  * **I** (heterogeneous)  **T2**:  * **I** (heterogeneous)  **T2**: 
51  52  Input data tensor containing the indices corresponding to elements  Input data tensor containing the indices corresponding to elements 
52  53  in the first input tensor X.This tensor is typically the second  in the first input tensor X.This tensor is typically the second 
53  54  output of the MaxPool op.Dimensions must be the same as input tensor  output of the MaxPool op.Dimensions must be the same as input tensor 
54  55  X. The indices are linear, i.e. computed considering the tensor as  X. The indices are linear, i.e. computed considering the tensor as 
55  56  flattened 1D tensor, assuming rowmajor storage. Also, the linear  flattened 1D tensor, assuming rowmajor storage. Also, the linear 
56  57  indices should not consider padding. So the values in indices are in  indices should not consider padding. So the values in indices are in 
57  58  the range [0, N x C x D1 x ... x Dn).  the range [0, N x C x D1 x ... x Dn). 
58  59  * **output_shape** (optional, heterogeneous)  **T2**:  * **output_shape** (optional, heterogeneous)  **T2**: 
59  60  The shape of the output can be explicitly set which will cause pads  The shape of the output can be explicitly set which will cause pads 
60  61  values to be auto generated. If 'output_shape' is specified, 'pads'  values to be auto generated. If 'output_shape' is specified, 'pads' 
61  62  values are ignored.  values are ignored. 
62  63 


63  64  **Outputs**  **Outputs** 
64  65 


65  66  * **output** (heterogeneous)  **T1**:  * **output** (heterogeneous)  **T1**: 
66  67  Output data tensor that contains the result of the unpooling.  Output data tensor that contains the result of the unpooling. 
67  68 


68  69  **Type Constraints**  **Type Constraints** 
69  70 


70  71  * **T1** in (  * **T1** in ( 
71  72  tensor(double),  tensor(double), 
72  73  tensor(float),  tensor(float), 
73  74  tensor(float16)  tensor(float16) 
74  75  ):  ): 
75  76  Constrain input and output types to float tensors.  Constrain input and output types to float tensors. 
76  77  * **T2** in (  * **T2** in ( 
77  78  tensor(int64)  tensor(int64) 
78  79  ):  ): 
79  80  Constrain index tensor to int64  Constrain index tensor to int64 