jack-etheredge / brain-tumor-segmentation-3d-unet-cnn Goto Github PK

Hi Jack,

Thank you for sharing.

I was wondering if you can tell me what 'y2' should be in the DataGenerator part(this may be a seemingly silly question.). I saw you marked 'list of survival days' next to it, but I failed to make the model work after trying several different methods.

Thanks a lot!

Liam

why the code in Write images to .tif has an error?
in firts imsave I have an error that says 'list' object has no attribute 'dtype'
Thanks

hi
thanks for your code, i have one question
I use brats 2019, why do I have this error while my path adress is correct?
No such file or directory: '/content/drive/My Drive/brats2019/HGG/BraTS19_TCIA08_436_1_images.pkl

do you put the classification label and the mask together into the model? I can not understand how you do it. do you try to write a one-hot code?

hello, i want to ask in your presentation how do you show the ground truth, prediction, and the 3D slices ,rotation are you using matlab?
thank you

Hi,

Thanks for sharing your code.

I was wondering if you could explain how you arrange the data. It seems like the generator is looking in ./data/ for all of the files. Is there another file or function that moves the data from the original location (./HGG or ./LGG) into ./data ?

Thanks

Rony

Hello Jack !
Thank you for your sharing !
But I found I can't make it, because I have no './weights/1pred_weights.25--0.08.hdf5 ', './data/', which really made me distressed.
So how can I figure it out? Could you please share these whole things? Thank you very much !

hi
thanks for your codes, but in train it needs more than 25g RAM, it gave me an error that need more RAM. how can I solve it?

hi sir,
I really thank you, sir, for sharing a wonderful work.
I am trying this code on google colaboratory.
I got the following error,
even if I did !pip install git+https://www.github.com/farizrahman4u/keras-contrib.git

ImportError Traceback (most recent call last)
in create_convolution_block(input_layer, n_filters, batch_normalization, kernel, activation, padding, strides, instance_normalization)
17 try:
---> 18 from keras_contrib.layers.normalization import InstanceNormalization
19 except ImportError:

ImportError: cannot import name 'InstanceNormalization'

During handling of the above exception, another exception occurred:

ImportError Traceback (most recent call last)
in ()
40
41 if current_layer is inputs:
---> 42 in_conv = create_convolution_block(current_layer, n_level_filters)
43 else:
44 in_conv = create_convolution_block(current_layer, n_level_filters, strides=(2, 2, 2))

in create_convolution_block(input_layer, n_filters, batch_normalization, kernel, activation, padding, strides, instance_normalization)
18 from keras_contrib.layers.normalization import InstanceNormalization
19 except ImportError:
---> 20 raise ImportError("Install keras_contrib in order to use instance normalization."
21 "\nTry: pip install git+https://www.github.com/farizrahman4u/keras-contrib.git")
22 layer = InstanceNormalization(axis=1)(layer)

ImportError: Install keras_contrib in order to use instance normalization.
Try: pip install git+https://www.github.com/farizrahman4u/keras-contrib.git