Some questions about the train_2ddense.py

xmengli / H-DenseUNet

TMI 2018. H-DenseUNet: Hybrid Densely Connected UNet for Liver and Tumor Segmentation from CT Volumes

526 stars 161 forks source link

Some questions about the train_2ddense.py #16

Open WdBlink opened 5 years ago

WdBlink commented 5 years ago

Hello, please ask line 62 in the train_2ddense.py code:

crop_img = img[a - deps / 2:a + deps / 2, b - rows / 2:b + rows / 2,
                c - cols / 2: c + cols / 2 + 1].copy()
cropp_tumor = tumor[a - deps / 2:a + deps / 2, b - rows / 2:b + rows / 2,
                  c - cols / 2:c + cols / 2 + 1].copy()

What function does this code play? The colon here in python: What kind of arithmetic operation is it?

Apple-zly commented 5 years ago

Hello, I run "train_2ddenseunet.py", The program is killed as soon as it runs. I don't know this is why?

xmengli commented 5 years ago

check if the CPU memory is full when running the program.(CPU memory on my server is 46G. ) At the beginning, the program load all data at once.

Excelsiorwu commented 5 years ago

Hello,I can not find 'long skip' in the Up-sampling process ,which your paper has mentioned. i wonder that the Up-sampling process only take the output of dense encoder without long skip from the front layers.

xmengli commented 5 years ago

Yes, there are two version, One is densenet and the other is the densenet with u net connections. Two versions are available. Both of it can be used in the hybrid architecture.