search

IBBM / Cascaded-FCN

Source code for the MICCAI 2016 Paper "Automatic Liver and Lesion Segmentation in CT Using Cascaded Fully Convolutional NeuralNetworks and 3D Conditional Random Fields"
Other
304 stars 127 forks source link

Incorrect output after step 1. #5

Closed XiaonanZang closed 7 years ago

XiaonanZang commented 7 years ago

Hi, I have run the notebook and seemed to obtain an incorrect prediction after step1.

For comparison, I have used the same example from https://github.com/cjayanth95/liverseg/blob/master/custom_outs_updated.ipynb.

This is my output: https://github.com/XiaonanZang/liverseg/blob/master/cascaded_unet_inference-Copy1.ipynb.

I have followed your instruction and built the caffe from the provided git.

Could you help me on this issue?

Thank you very much.

Xiaonan Zang

XiaonanZang commented 7 years ago

Hi,

After further reviewed the issue regarding the offset. I found that even with the caffe at: https://github.com/mohamed-ezz/caffe/tree/jonlong, I still have to specifically set up the offsets.

I set the offsets based on the answer you provided at: https://groups.google.com/forum/#!topic/caffe-users/YSRYy7Nd9J8

And now my output perfectly matched the output from: https://github.com/cjayanth95/liverseg/blob/master/custom_outs_updated.ipynb.

Thanks, Xiaonan

dk67604 commented 7 years ago

How did you set up the crop offset for caffe?