ConvTransposeWithDynamicPads

 Graphs in : cluster, ONNX model architecture.

X (heterogeneous) – T : object, input data tensor (e.g., image or feature map), typically in [N, C, H, W] format for 2D or [N, C, D, H, W] for 3D.
W (heterogeneous) – T : object, weight tensor representing the transposed convolution filters, typically in [C_in, C_out / group, kH, kW] format for 2D.
Pads (optional, heterogeneous) – tensor(int64) : object, integer tensor defining the padding values to be applied dynamically at runtime, e.g., [pad_top, pad_left, pad_bottom, pad_right] for 2D.
B (optional, heterogeneous) – T : object, bias tensor applied to the output, of size [C_out].

auto_pad : enum, auto_pad must be either NOTSET, SAME_UPPER, SAME_LOWER or VALID. Where default value is NOTSET, which means explicit padding is used. SAME_UPPER or SAME_LOWER mean pad the input so that output_shape = ceil(input_shape / strides) for each axis i. The padding is split between the two sides equally or almost equally (depending on whether it is even or odd). In case the padding is an odd number, the extra padding is added at the end for SAME_UPPER and at the beginning for SAME_LOWER.
Default value “NOTSET”.
dilations : array, dilation value along each spatial axis of the filter. If not present, the dilation defaults to 1 along each axis.
Default value “empty”.
group : integer, number of groups input channels and output channels are divided into.
Default value “1”.
kernel_shape : array, the shape of the convolution kernel. If not present, should be inferred from input ‘w’.
Default value “empty”.
pads : array, padding for the beginning and ending along each spatial axis, it can take any value greater than or equal to 0.The value represent the number of pixels added to the beginning and end part of the corresponding axis.pads format should be as follow [x1_begin, x2_begin…x1_end, x2_end,…], where xi_begin the number ofpixels added at the beginning of axis i and xi_end, the number of pixels added at the end of axis i.This attribute cannot be used simultaneously with auto_pad attribute. If not present, the padding defaultsto 0 along start and end of each spatial axis.
Default value “empty”.
strides : array, stride along each spatial axis. If not present, the stride defaults to 1 along each axis.
Default value “empty”.
 training? : boolean, whether the layer is in training mode (can store data for backward).
Default value “True”.
 lda coeff : float, defines the coefficient by which the loss derivative will be multiplied before being sent to the previous layer (since during the backward run we go backwards).
Default value “1”.

 name (optional) : string, name of the node.