[ICLR'23 Spotlight🔥] The first successful BERT/MAE-style pretraining on any convolutional network; Pytorch impl. of "Designing BERT for Convolutional Networks: Sparse and Hierarchical Masked Modeling"
Hello! In the function sp_conv_forward, the input x first goes through a normal convolution forward, so why can the sp_conv_forward improve training efficiency compared to the normal conv_forward?
Hello! In the function sp_conv_forward, the input x first goes through a normal convolution forward, so why can the sp_conv_forward improve training efficiency compared to the normal conv_forward?