About Saving Unet The Results in .h5 format

[zaccharieramzi]

About Saving Unet The Results in .h5 format

[zaccharieramzi]

Hi @fharman ,

I did not provide a script to perform the inference using the functional models (the old ones).

Can you show me the code you used so that I can help you debug it?

I just tested to see whether the sequences in 'testing' mode indeed contained the expected number of test files, and it's the case, see:

from fastmri_recon.data.sequences.fastmri_sequences import ZeroFilled2DSequence
test_path = ...  # your test path here
seq_4 = ZeroFilled2DSequence(
    test_path,
    mode='testing',
    af=4,
    contrast=None,
    norm=True,
)
seq_8 = ZeroFilled2DSequence(
    test_path,
    mode='testing',
    af=8,
    contrast=None,
    norm=True,
)
print(len(seq_4.filenames), len(seq_8.filenames))

Which returns 50, 58, and there are 108 files for the test set.

[zaccharieramzi]

In the colab you linked, I didn't see where you performed the inference to predict the test images.

Also please note that since #113 you no longer need to switch to an older commit for correct results using the U-net, I corrected the error.

[zaccharieramzi]

Ok I see now, let me see.

[zaccharieramzi]

So your function save_figure (consider changing the name for greater readability) is the one that I guess you wanted to use to save your results (I am rewriting it here for clarity).

def save_figure(im_recos, name):
    global img_index
    with h5py.File(test_gen_scaled.filenames[img_index],'r') as f:
    
        for slice_index in range(f.get('kspace').shape[0]):
            im_reco = im_recos[ slice_index ]
            image_name=test_gen_scaled.filenames[img_index][78:len(test_gen_scaled.filenames[img_index])-6]
            # im_gt = img_batch[slice_index]
            # im_res = np.abs(im_gt - im_reco)
            fig, ax = plt.subplots ( 1, frameon=False )
            ax.imshow ( np.abs ( np.squeeze ( im_reco ) ), aspect='auto' )
            ax.axis ( 'off' )
            fig.savefig (f'/content/drive/My Drive/fastmri-reproducible-benchmark-bcd3fddb48ad324566a44b23c4439ff7a50a316e/TestFigures2/AF8/{image_name}_{slice_index}_{name}_recon_af{AF}.png' )
            
            # fig, ax = plt.subplots(1, frameon=False)
            # ax.imshow(np.abs(np.squeeze(im_res)), aspect='auto')
            # ax.axis('off')
            # fig.savefig(f'/content/drive/My Drive/UNET_Colab/fastmri_reproducible_benchmark_master/TestFigures/trivial_{name}_residu_af{AF}.png')
    
    img_index += 1

However, you didn't open the correct file, you opened the original test file rather than a newly created output file with the correct naming (see the guidelines here).
Also, in this function, you never write to that file but instead save a matplotlib figure, you should save to the newly created h5 file instead.

Also, I think in Python it's recommended to not use global variables in the general case, you should try rewriting this function also without a global variable.

[fharman]

Hi, I did not understand your correction. But i gave a link about a reconstructed folder for an old unet commit bcd3fdd.(with AF4 and AF8) https://drive.google.com/drive/folders/1J3_3t-VmosMR0-vQhVZN7WdZX8QHLpQg?usp=sharing With the latest version, the reconstructed folder is like this. https://drive.google.com/drive/folders/1StJVuOLI-FT0qRGhgwjhqRkaWo0GCSpx?usp=sharing Thank you Zaccharie Ramzi <[email protected]>, 26 Kas 2020 Per, 20:57 tarihinde şunu yazdı:

…

In the colab you linked <https://colab.research.google.com/drive/1S3Xzn9UXG6Zrz1Q0jlTMqsHluTmCjvt5>, I didn't see where you performed the inference to predict the test images. Also please note that since #113 <#113> you no longer need to switch to an older commit for correct results using the U-net, I corrected the error. — You are receiving this because you were mentioned. Reply to this email directly, view it on GitHub <#115 (comment)>, or unsubscribe <https://github.com/notifications/unsubscribe-auth/AO4IQ2UJFTWIUQ25EFBPXYLSR2JIHANCNFSM4UDU2VIA> .

[zaccharieramzi]

@fharman I did not do any correction in the function, I just rewrote it in the issue for logging's sake.

The folders you are showing me are full of png images. For this challenge you need to submit h5 files: please read the guidelines on how to submit.

Alternatively, you can also take inspiration from this function or the one of the official repo.

[fharman]

Thank you for your recommendation. But i still don't understand what you mean just saying However, you didn't open the correct file, you opened the original test file rather than a newly created output file with the correct naming (see the guidelines here <https://fastmri.org/submission_guidelines/#leaderboard> ). Also, in this function, you never write to that file but instead save a matplotlib figure, you should save to the newly created h5 file instead. Please let me know the information about details and my faults in reconstruction. Thank you again, Zaccharie Ramzi <[email protected]>, 26 Kas 2020 Per, 21:05 tarihinde şunu yazdı:

…

So your function save_figure (consider changing the name for greater readability) is the one that I guess you wanted to use to save your results (I am rewriting it here for clarity). def save_figure(im_recos, name): global img_index with h5py.File(test_gen_scaled.filenames[img_index],'r') as f: for slice_index in range(f.get('kspace').shape[0]): im_reco = im_recos[ slice_index ] image_name=test_gen_scaled.filenames[img_index][78:len(test_gen_scaled.filenames[img_index])-6] # im_gt = img_batch[slice_index] # im_res = np.abs(im_gt - im_reco) fig, ax = plt.subplots ( 1, frameon=False ) ax.imshow ( np.abs ( np.squeeze ( im_reco ) ), aspect='auto' ) ax.axis ( 'off' ) fig.savefig (f'/content/drive/My Drive/fastmri-reproducible-benchmark-bcd3fddb48ad324566a44b23c4439ff7a50a316e/TestFigures2/AF8/{image_name}_{slice_index}_{name}_recon_af{AF}.png' ) # fig, ax = plt.subplots(1, frameon=False) # ax.imshow(np.abs(np.squeeze(im_res)), aspect='auto') # ax.axis('off') # fig.savefig(f'/content/drive/My Drive/UNET_Colab/fastmri_reproducible_benchmark_master/TestFigures/trivial_{name}_residu_af{AF}.png') img_index += 1 However, you didn't open the correct file, you opened the original test file rather than a newly created output file with the correct naming (see the guidelines here <https://fastmri.org/submission_guidelines/#leaderboard>). Also, in this function, you never write to that file but instead save a matplotlib figure, you should save to the newly created h5 file instead. Also, I think in Python it's recommended to not use global variables in the general case, you should try rewriting this function also without a global variable. — You are receiving this because you were mentioned. Reply to this email directly, view it on GitHub <#115 (comment)>, or unsubscribe <https://github.com/notifications/unsubscribe-auth/AO4IQ2UQYMNL7RPYUF5BMM3SR2KF7ANCNFSM4UDU2VIA> .

[fharman]

Thank you for the clarification. 26 Kas 2020 Per 21:16 tarihinde Zaccharie Ramzi <[email protected]> şunu yazdı:

…

@fharman <https://github.com/fharman> I did not do any correction in the function, I just rewrote it in the issue for logging's sake. The folders you are showing me are full of png images. For this challenge you need to submit h5 files: please read the guidelines <https://fastmri.org/submission_guidelines/#leaderboard> on how to submit. Alternatively, you can also take inspiration from this function <https://github.com/zaccharieramzi/fastmri-reproducible-benchmark/blob/master/fastmri_recon/evaluate/utils/write_results.py> or the one of the official repo <https://github.com/facebookresearch/fastMRI/blob/master/fastmri/utils.py> . — You are receiving this because you were mentioned. Reply to this email directly, view it on GitHub <#115 (comment)>, or unsubscribe <https://github.com/notifications/unsubscribe-auth/AO4IQ2VVXDPY5GUHIAXLXG3SR2LO7ANCNFSM4UDU2VIA> .

[fharman]

Hi,

Sorry for my faults and misunderstanding. But I try to learn and revise myself according to your reply. I want to ask you about fastmri-reproducible-benchmark/fastmri_recon/evaluate/utils/write_results.py /

write_result(exp_id, result, filename, coiltype='multicoil', scale_factor=1e6, brain=False, challenge=False) in this line, what is exp_id?

Thank you for your patience and reply,

Best,

[zaccharieramzi]

I added a Pull Request (PR) where I specify the docs of this function. Please take a look.

[fharman]

Thanks, I'll check it out. Zaccharie Ramzi <[email protected]>, 27 Kas 2020 Cum, 16:20 tarihinde şunu yazdı:

…

I added a Pull Request (PR) where I specify the docs of this function. Please take a look <https://github.com/zaccharieramzi/fastmri-reproducible-benchmark/pull/118/files#diff-f117a68dfd3fedc5e30ed3f1d2ce827f82e0e2973d06bb44812712f59a618525R22> . — You are receiving this because you were mentioned. Reply to this email directly, view it on GitHub <#115 (comment)>, or unsubscribe <https://github.com/notifications/unsubscribe-auth/AO4IQ2TQ35AMQ3JMRA2RPZDSR6RRZANCNFSM4UDU2VIA> .

[zaccharieramzi]

@fharman it's because the exp_id should be a string. Here you just put Unet without specifying that it was a string.

[zaccharieramzi]

Hi @fharman ,

Can we close this?

[fharman]

Hi, Thank you for your help. I sent it and finally reached a result for improvement. Thanks, 19 Ara 2020 Cmt 21:35 tarihinde Zaccharie Ramzi <[email protected]> şunu yazdı:

…

Hi @fharman <https://github.com/fharman> , Can we close this? — You are receiving this because you were mentioned. Reply to this email directly, view it on GitHub <#115 (comment)>, or unsubscribe <https://github.com/notifications/unsubscribe-auth/AO4IQ2XVFAJWQX6LDDWXL6DSVTW5NANCNFSM4UDU2VIA> .