Open vinbhaskara opened 5 years ago
DLA consists of groups of HDA. It is mainly used for classification tasks. IDA is used for upsampling DLA to get high-resolution output, so it is called IDAUp in the code. DLAUp is the final structure after putting DLA and IDAUp together.
Hi @fyu, I am interested in the segmentation network and I want to know the number of features maps (ouput_dim) that you use during the up-sampling branch
The paper mentions DLA, IDA and HDA.
But how are DLAUp and IDAUp in your code different? Can you provide some reference please?
Thanks.