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 used "ImageData" layer in this version of Caffe to read an image and a label, I received the error of "Segmentation fault (core dumped)". There is no such an error for the original official version of Caffe. I doubt maybe when you added the denseImageData layer, you ruined the original ImageData layer. Could you check this issue? Thanks!
When I used "ImageData" layer in this version of Caffe to read an image and a label, I received the error of "Segmentation fault (core dumped)". There is no such an error for the original official version of Caffe. I doubt maybe when you added the denseImageData layer, you ruined the original ImageData layer. Could you check this issue? Thanks!