Testing

[cyiheng]

Hi,

Motion :
I wanted to try the testing of the motion field but I have an issue with the variable index_list, it's not defined in your test_motion.py

Interpolation :

1. Your ````eval_data.py has an emptymain```, is it the same as the one in the motion-net ?
2. The data to use is the original testing set ? Or the deformed image produced by the test of motion-net ?

data = pd.read_csv(\
        'test data')
testdata_l = data['']
testlabel_l = data['']

3. What .pth I should put in dir_deform = '.pth' of the test.py ?

Thank you !

[yyguo0536]

Hi,
The index_list is defined in "niidata.py"
1 - yes, its same as the motion-net.
2 - It's original 4D sequence, not produced by the motion-net. For example, if your 4D data include 5 time-points, then you just need to input the beginning time-point and ending time-point, and using the interpolation network to generate three intermediate time-points. After that, your can evaluate the interpolation network by comparing the generated intermediate images with your ground-truth.
3 - '.pth' is your well-trained motion net.

[cyiheng]

Ok thank you.

I saw that you change a little bit the niidata.py so I updated it as yours.
But it failed to run again when I tried again.

Because I have 6 time points, I have a higher length of index_list.
And I finally noticed the self.loss_weight.

Therefore can you tell me what does it represent ? And how do you choose the numbers ?

Thank you