Hengshuang Zhao
Hengshuang Zhao
Hi, for the training, the issues are mainly related to bn layer: 1. Whether to update the parameters (mean,variance,slope,bias) of 'bn'? -If you are working on the same (or similar)...
It's hard to make the training code compatible with the official Caffe version. May be we can release the testing model and prototxt first. Sorry for the delay and the...
Dear all, thanks for the patience, the evaluation code is ready now.
Hi, fabianboth Please clone the newest version of PSPNet which has been tested successfully on Ubuntu 14.04 and 12.04 with CUDA 7.0. Thanks.
Hi, when training, the gt labels [0-150] are mapped into 0-149 and 255 for void labels are ignored.
Yeah, will be available no later than the end of May, possibly after nips ddl. Thanks.
Dear all, thanks for the patience, the evaluation code is ready now.
Yes, for the original design is trained with a square input(like 473*473), so in the ppm the pooled ones are all squared maps. 1. Let's say your crop size of...
Can you help provide the detailed config you are using?
Hi, We assume that number of images can be divided by number of GPUs; if not, you can just pad your image list or switch to single GPU evaluation by...