search

liziyu0929 / DeepAnat

Keras implementation of DeepAnat: Diffusion MRI data analysis assisted by deep learning synthesized anatomical images
MIT License
8 stars 1 forks source link

Is this the bug in your code ？ I cannot find te block_size[0] in s_DeepAnat_trainGAN.py #1

Open NoraHit opened 1 year ago

NoraHit commented 1 year ago

gtrain_output_tag = np.ones((batch_size_train, block_size[0] 3, 1)) label_smoothing_factor gtest_output_tag = np.ones((batch_size_test, block_size[0] 3, 1)) label_smoothing_factor

NoraHit commented 1 year ago

where does this block_size[0] come from??

liziyu0929 commented 1 year ago

Hi, we split the image volume into smaller blocks to comply with the GPU memory limit. In our study block_size = [64,64,64].