Conv2dTranspose 中 Output_padding 的作用是什么？请帮助我理解这一点？
Conv2dTranspose(1024, 512, kernel_size=3, stride=2, padding=1, output_padding=1)
convolution conv-neural-network deconvolution pytorch
conv-neural-network ×1
convolution ×1
deconvolution ×1
pytorch ×1