This repository was a fork of BVLC/caffe and includes the upsample, bn, dense_image_data and softmax_with_loss (with class weighting) layers of caffe-segnet (https://github.com/alexgkendall/caffe-segnet) to run SegNet with cuDNN version 5.
When I run the compute_bn_statistics.py, I get the following error:
I realize that the MaxTopBlobs() is set to 1 and it has to be increased to 3 to accommodate mean and variance blobs.
@TimoSaemann Can you please help me with this problem?
When I run the compute_bn_statistics.py, I get the following error:
I realize that the MaxTopBlobs() is set to 1 and it has to be increased to 3 to accommodate mean and variance blobs.
@TimoSaemann Can you please help me with this problem?