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

training data format #36

Closed idinsmore1 closed 3 years ago

idinsmore1 commented 3 years ago

Hi there,

I was wondering what the format of the data was for you when you did the training of this model? I understand the preprocessing steps for the example, but when the training happened was it loaded in through .npy files? I was trying to figure it out by looking through https://github.com/mohamed-ezz/saratan/blob/master/notebooks/realtime_train.ipynb but was having issues. Thanks for your help.

mohamed-ezz commented 3 years ago

It's been a long while since I touched this code but I think you're correct...seems that data during training was in .npy format.

This first layer here https://github.com/mohamed-ezz/saratan/blob/master/notebooks/unet-overfit-python.prototxt#L11 has type numpy_data_layer. It's a custom layer defined here https://github.com/mohamed-ezz/saratan/blob/master/data/layers/numpy_data_layer.py

idinsmore1 commented 3 years ago

Ah I see, missed this before. Thanks!