s-mostafa-a / luna16 Goto Github PK

Hello Sir
I used your code to validate the dataset size as data_loader=373 and got an error while validating as follows.
When
for i, (data, target, coord) in enumerate(data_loader):

The following error message appears when the loop reaches the 66th time.

IndexError: index 32 is out of bounds for axis 2 with size 32

Can you help me please? Thank you.

Hi,

In the following snippet from the loss.py file:
''classify_loss = 0.5 * self.classify_loss(
pos_prob, pos_labels[:, 0]) + 0.5 * self.classify_loss(
neg_prob, neg_labels + 1) ''

why is the target label for sigmoid loss of negative samples given as ' neg_labels + 1' ?
Shouldn't it be just 'neg_labels'? (as the value of 'neg_labels' is initilaized as 0 in itself)

Dear Mostafa, Thank you very much for your efforts. You provided information about a small sample, however the data on the link is unavailable. Could you please provide a new link?

Dear author,

I'm using your google colab
I followed your instruction from 'How to use' but I got "IndexError: too many indices for array: array is 1-dimensional, but 2 were indexed" while running train.py.
May I ask you how to solve this?

Thanks

Hello Sir
Could you help me please, when am trying to run the pre-process step am facing the errors below...

IndexError Traceback (most recent call last)
in
57
58 if name == 'main':
---> 59 save_preprocessed_data()

in save_preprocessed_data()
48 tp_co = tp_co[:max_numbers_to_use]
49 radii = radii[:max_numbers_to_use]
---> 50 ct = CTScan(seriesuid=series_id, centers=tp_co, radii=radii, clazz=0)
51 ct.preprocess()
52 ct.save_preprocessed_image()

in init(self, seriesuid, centers, radii, clazz)
15 self._centers = centers
16 paths = glob(f'''{RESOURCES_PATH}/*/{self._seriesuid}.mhd''')
---> 17 path = paths[0]
18 self._ds = sitk.ReadImage(path)
19 self._spacing = np.array(list(reversed(self._ds.GetSpacing())))

IndexError: list index out of range