search

IAmSuyogJadhav / 3d-mri-brain-tumor-segmentation-using-autoencoder-regularization

Keras implementation of the paper "3D MRI brain tumor segmentation using autoencoder regularization" by Myronenko A. (https://arxiv.org/abs/1810.11654).
MIT License
369 stars 113 forks source link

InvalidArgumentError on build_model #26

Open linaouro opened 4 years ago

linaouro commented 4 years ago

I am running the example notebook locally. In the "build model" step, I get the following error:

InvalidArgumentError: Duplicate node name in graph: 'Dec_VAE_VDraw_Sampling/random_normal/shape'

Do you know what is causing it and how to fix it?

vijayannepu commented 4 years ago

Even I got the same issue first, Change your tensor flow version to 1.14 or 1.8. It worked fine for me for the same error.

675492062 commented 4 years ago

@vijayannepu,I installed tensorflow 1.8.0 and run this code,but some errors as blow. Is the problem of tf version? Traceback (most recent call last): File "Example_on_BRATS2018.py", line 109, in model.fit(data, labels, batch_size=1, epochs=1) File "/home/xxx/anaconda3/envs/tf108/lib/python3.6/site-packages/keras/engine/training.py", line 1630, in fit batch_size=batch_size) File "/home/xxx/anaconda3/envs/tf108/lib/python3.6/site-packages/keras/engine/training.py", line 1480, in _standardize_user_data exception_prefix='target') File "/home/xxx/anaconda3/envs/tf108/lib/python3.6/site-packages/keras/engine/training.py", line 86, in _standardize_input_data str(len(data)) + ' arrays: ' + str(data)[:200] + '...') ValueError: Error when checking model target: the list of Numpy arrays that you are passing to your model is not the size the model expected. Expected to see 2 array(s), but instead got the following list of 1 arrays: [array([[[[[0, 0, 0, ..., 0, 0, 0], [0, 0, 0, ..., 0, 0, 0], [0, 0, 0, ..., 0, 0, 0], ..., [0, 0, 0, ..., 0, 0, 0], [0, 0, 0, ..., 0, 0, 0],

akezhanmussa commented 4 years ago

@675492062 , I got the same problem. It is related to the way how you feed data to the model. In the Example_on_BRATS2018.ipynb, it was like model.fit(x, [x, y]) instead of usual model.fit(x, y)

@vijayannepu,I installed tensorflow 1.8.0 and run this code,but some errors as blow. Is the problem of tf version? Traceback (most recent call last): File "Example_on_BRATS2018.py", line 109, in model.fit(data, labels, batch_size=1, epochs=1) File "/home/xxx/anaconda3/envs/tf108/lib/python3.6/site-packages/keras/engine/training.py", line 1630, in fit batch_size=batch_size) File "/home/xxx/anaconda3/envs/tf108/lib/python3.6/site-packages/keras/engine/training.py", line 1480, in _standardize_user_data exception_prefix='target') File "/home/xxx/anaconda3/envs/tf108/lib/python3.6/site-packages/keras/engine/training.py", line 86, in _standardize_input_data str(len(data)) + ' arrays: ' + str(data)[:200] + '...') ValueError: Error when checking model target: the list of Numpy arrays that you are passing to your model is not the size the model expected. Expected to see 2 array(s), but instead got the following list of 1 arrays: [array([[[[[0, 0, 0, ..., 0, 0, 0], [0, 0, 0, ..., 0, 0, 0], [0, 0, 0, ..., 0, 0, 0], ..., [0, 0, 0, ..., 0, 0, 0], [0, 0, 0, ..., 0, 0, 0],