inline void conv_col2im_cpu(const Dtype* col_buff, Dtype* data) {
if (!force_nd_im2col_ && num_spatial_axes_ == 2) {
col2im_cpu(col_buff, conv_in_channels_,
conv_input_shape_.cpu_data()[1], conv_input_shape_.cpu_data()[2],
kernel_shape_.cpu_data()[0], kernel_shape_.cpu_data()[1],
pad_.cpu_data()[0], pad_.cpu_data()[1],
stride_.cpu_data()[0], stride_.cpu_data()[1], data);
} else {
col2im_nd_cpu(col_buff, num_spatial_axes_, conv_input_shape_.cpu_data(),
col_buffer_shape_.data(), kernel_shape_.cpu_data(),
pad_.cpu_data(), stride_.cpu_data(), data);
}
}
void Im2colLayer<Dtype>::Backward_cpu(const vector<Blob<Dtype>*>& top,
const vector<bool>& propagate_down, const vector<Blob<Dtype>*>& bottom) {
const Dtype* top_diff = top[0]->cpu_diff();
Dtype* bottom_diff = bottom[0]->mutable_cpu_diff();
for (int n = 0; n < num_; ++n) {
if (!force_nd_im2col_ && num_spatial_axes_ == 2) {
col2im_cpu(top_diff + n * top_dim_, channels_,
bottom[0]->shape(channel_axis_ + 1),
bottom[0]->shape(channel_axis_ + 2),
kernel_shape_.cpu_data()[0], kernel_shape_.cpu_data()[1],
pad_.cpu_data()[0], pad_.cpu_data()[1],
stride_.cpu_data()[0], stride_.cpu_data()[1],
bottom_diff + n * bottom_dim_);
} else {
col2im_nd_cpu(top_diff + n * top_dim_, num_spatial_axes_,
bottom[0]->shape().data() + channel_axis_,
top[0]->shape().data() + channel_axis_,
kernel_shape_.cpu_data(), pad_.cpu_data(), stride_.cpu_data(),
bottom_diff + n * bottom_dim_);
}
}
}