search

mattmacy / vnet.pytorch

A PyTorch implementation for V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation
https://mattmacy.github.io/vnet.pytorch
BSD 3-Clause "New" or "Revised" License
688 stars 201 forks source link

Concatenation operation in InputTransition causing confusion and memory abuse #21

Open tongdaxu opened 5 years ago

tongdaxu commented 5 years ago

As described in #01, the Concatenation operation in InputTransition has not been fix. Note that this could cause confusion in training, as the data should be of size() [Batchsize, Channel, Xsize, Ysize, Zsize] and the output to softmax should be of size() [Batchsize, Classnum, Xsize, Ysize, Zsize].

But as the broadcasting between [Batchsize16, XChannel, Xsize, Ysize, Zsize], [Batchsize, XChannel16, Xsize, Ysize, Zsize] bring [Batchsize16, XChannel16, Xsize, Ysize, Zsize], all the following layers would have 16 times more batchsize.

Mathematically this could be offset by running a lot of epochs, but could also make device suffers from memory issue. And each batch is equivalent to 16 un-shuffled batch.

Mrdeer3935 commented 11 months ago

Thanks #1 ! I was confused for this problem! Now, my thoughts is right!