[API] Propose to support ConvTranspose operation

[NALLEIN]

Computes the transposed 2D convolution of an image, also known as a deconvolution. The values in the output tensor are computed as:

        output[batch, row, col, channel] =
            sum_{i, j} (
                input[batch, row + i, col + j, k] *
                filter[channel, row + i, col + j, k] +
                bias[channel]
            )

• Inputs (explicit padding):
• • 0: A 4-D tensor, of shape [batches, height, width, depth_in], specifying the input. If rank 3, batch of 1 is assumed.
• • 1: A 4-D tensor, of shape [depth_out, filter_height, filter_width, depth_in],specifying the filter.
• • 2: A 1-D tensor, of shape [depth_out], specifying the bias.
• • 3: An INT32 value, specifying the padding on the left, in the ‘width’ dimension.
• • 4: An INT32 value, specifying the padding on the right,in the ‘width’ dimension.
• • 5: An INT32 value, specifying the padding on the top, in the ‘height’ dimension.
• • 6: An INT32 value, specifying the padding on the bottom, in the ‘height’ dimension.
• • 7: An INT32 value, specifying the stride when walking through input in the ‘width’ dimension.
• • 8: An INT32 value, specifying the stride when walking through input in the ‘height’ dimension.
• Outputs:
• • 0: The output 4-D tensor, of shape [batches, out_height, out_width, depth_out].

Model Format	API reference
Tensorflow.lite	https://www.tensorflow.org/lite/guide/ops_compatibility TRANSPOSE_CONV
ONNX	https://github.com/onnx/onnx/blob/master/docs/Operators.md#ConvTranspose
OpenVINO	None

backend	support
WASM	No
WebGL	Yes
NNAPI
MPS
BNNS
clDNN
MKLDNN
DirectML
IE-clDNN
IE-MKLDNN