Using the SynDiff_Sample_Data and using the pretrained network to output T2 from T1

[carlouic]

Hello,
Thanks for your amazing work and for sharing it with all of us.
I have a couple questions:
first thing, when i try to load the T1.mat and T2.mat file, i get an error like this in matlab:

Error using load
Unknown text on line number 1 of ASCII file path/to/T2/T2.mat
"HDF
".
Error in uiimport/runImportdata (line 470)
datastruct = load('-ascii', fileAbsolutePath);
Error in uiimport/gatherFilePreviewData (line 438)
[datastruct, textDelimiter, headerLines]= runImportdata(fileAbsolutePath, type);
Error in uiimport (line 260)
gatherFilePreviewData(fileAbsolutePath);

this is using the very basic load function in matlab. should i try to load it in a different way?

second thing, i downloaded the pretrained network to perform the synthesis of T2 starting from T1. i run this line of code:

python test.py --image_size 256 --exp exp_syndiff --num_channels 2 --num_channels_dae 64 --ch_mult 1 1 2 2 4 4 --num_timesteps 4 --num_res_blocks 2 --batch_size 1 --embedding_type positional --z_emb_dim 256 --contrast1 T1 --contrast2 T2 --which_epoch 50 --gpu_chose 0 --input_path /input/path/for/data --output_path /output/for/results

and the result is amazing. how can i try the pretrained model on some of my data? I am trying to convert my nifti file to mat in this way:

import nibabel as nib
nii = nib.load('filename.nii')
slices = data.reshape((1, data.shape[0], data.shape[1], data.shape[2]))
sio.savemat('slices.mat', {'slices': slices})

but then when i try to use it in the testing stage, this is the error i get, when trying to load it using the LoadDataset() function:

OSError: Unable to open file (file signature not found)

However, when I try to open this file in matlab, this works and i can see the image.

Thanks!

thanks in advance!!
best regards.

[zhang-bin1999]

Because the T1.mat and T2.mat in the sample_data isn't the ascii file, but the HDF5 file. If you want to open the 'mat' file in MATLAB, you should use the command 'data = h5read('T1.mat', '/data_fs')' , and then you will see the result. Absolutely, if you want to use you own data, you should save your mat file also in the HDF5 file.