search

frankkramer-lab / MIScnn

A framework for Medical Image Segmentation with Convolutional Neural Networks and Deep Learning
GNU General Public License v3.0
402 stars 116 forks source link

how to prepare data(kits) #35

Closed Iamyourbaba closed 4 years ago

Iamyourbaba commented 4 years ago

model = miscnn.Neural_Network(preprocessor=pp, architecture=unet_standard) Traceback (most recent call last): File "", line 1, in File "/home/damu/MIScnn/miscnn/neural_network/model.py", line 73, in init n_labels=self.classes) File "/home/damu/MIScnn/miscnn/neural_network/architecture/unet/standard.py", line 132, in create_model_3D self.ba_norm_momentum) File "/home/damu/MIScnn/miscnn/neural_network/architecture/unet/standard.py", line 197, in expanding_layer_3D padding='same')(input), concatenate_link], axis=4) File "/home/damu/anaconda3/envs/temp/lib/python3.7/site-packages/tensorflow/python/keras/engine/base_layer.py", line 554, in call outputs = self.call(inputs, *args, *kwargs) File "/home/damu/anaconda3/envs/temp/lib/python3.7/site-packages/tensorflow/python/keras/layers/convolutional.py", line 1140, in call outputs_shape[0], outputs_shape[1] outputs_shape[2], TypeError: unsupported operand type(s) for *: 'NoneType' and 'NoneType'

muellerdo commented 4 years ago

Hey @Iamyourbaba,

sounds like your are providing a sample with None as image/segmentation?

It is hard to say anything without any question/problem description or reproducible code. Nearly impossible ;)

I would recommend open up a new issue with a clear description of what you want to do and the problem.

Cheers, Dominik