void Im2colLayer<Dtype>::Forward_cpu(const vector<Blob<Dtype>*>& bottom,
const vector<Blob<Dtype>*>& top) {
const Dtype* bottom_data = bottom[0]->cpu_data();
Dtype* top_data = top[0]->mutable_cpu_data();
for (int n = 0; n < num_; ++n) {
DCHECK_EQ(bottom[0]->shape().size() - channel_axis_, num_spatial_axes_ + 1);
DCHECK_EQ(top[0]->shape().size() - channel_axis_, num_spatial_axes_ + 1);
DCHECK_EQ(kernel_shape_.count(), num_spatial_axes_);
DCHECK_EQ(pad_.count(), num_spatial_axes_);
DCHECK_EQ(stride_.count(), num_spatial_axes_);
if (!force_nd_im2col_ && num_spatial_axes_ == 2) {
im2col_cpu(bottom_data + n * bottom_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],
top_data + n * top_dim_);
} else {
im2col_nd_cpu(bottom_data + n * bottom_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(),
top_data + n * top_dim_);
}
}
}
// wrap im2col/col2im so we don't have to remember the (long) argument lists
inline void conv_im2col_cpu(const Dtype* data, Dtype* col_buff) {
if (!force_nd_im2col_ && num_spatial_axes_ == 2) {
im2col_cpu(data, 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], col_buff);
} else {
im2col_nd_cpu(data, num_spatial_axes_, conv_input_shape_.cpu_data(),
col_buffer_shape_.data(), kernel_shape_.cpu_data(),
pad_.cpu_data(), stride_.cpu_data(), col_buff);
}
}
