Then, I use the following code to get the header, and the fdata:

        header_bytes = cp.asnumpy(image[:348])\n        header = nib.Nifti1Header.from_fileobj(io.BytesIO(header_bytes))\n        data_offset = header.get_data_offset()\n        data_shape = header.get_data_shape()\n        data_dtype = header.get_data_dtype()\n        affine = header.get_best_affine()\n        data = image[data_offset:].view(data_dtype).reshape(data_shape, order=\"F\")\n\n

I have some questions on the above implementation:

\n
1. Does Nibabel already have GDS related feature? If so, I can use it directly
\n
2. Does my way of loading header and using offset, dtype and shape have any issues in some cases?
\n

It would be very appreciate if you can help to answer them, thanks very much!

\n
1. No.
\n
2. I don't know if kvikio.CuFile handles compression, but many NIfTI files are gzipped. You will need to account for that if it's not done automatically. The construction of the header, affine and data seem reasonable. However, if there are scale factors, you will not get the same data. Also, nibabel lazily loads data, so you can get the header and your parameters like:
\n

img = nb.load(filename)\nshape = img.shape\noffset = img.dataobj.offset\ndata_dtype = img.dataobj.dtype\nslope = img.dataobj.slope\ninter = img.dataobj.inter\n\nraw = ...  # Do what's needed to get your cupy array.\nif (slope, inter) != (1, 0):\n    data = slope * raw + inter\nelse:\n    data = raw

Questions on nifti data loading with GPU #1385

Answered by effigies

yiheng-wang-nv asked this question in Q&A

Questions on nifti data loading with GPU #1385

yiheng-wang-nv

Nov 5, 2024 · 1 comments · 2 replies

Answered by effigies Return to top

Discussion options

yiheng-wang-nv

Nov 5, 2024

Hi Nibabel experts, recently I did some research on how to use GPU Direct Storage (GDS) for NIFTI data loading, and I have some successful trials on Decathlon datasets. My draft implementation is in: Project-MONAI/MONAI#8188 and it uses Nibabel + kvikio + cupy for the loading. Generally, I use cupy to create an empty array , and use kvikio to read the data into it: file_size = os.path.getsize(filename) image = cp.empty(file_size, dtype=cp.uint8) with kvikio.CuFile(filename, "r") as f: f.read(image) Then, I use the following code to get the header, and the fdata: header_bytes = cp.asnumpy(image[:348]) header = nib.Nifti1Header.from_fileobj(io.BytesIO(header_bytes)) data_offset = header.get_data_offset() data_shape = header.get_data_shape() data_dtype = header.get_data_dtype() affine = header.get_best_affine() data = image[data_offset:].view(data_dtype).reshape(data_shape, order="F") I have some questions on the above implementation: Does Nibabel already have GDS related feature? If so, I can use it directly Does my way of loading header and using offset, dtype and shape have any issues in some cases? It would be very appreciate if you can help to answer them, thanks very much!

1 You must be logged in to vote

Answered by effigies Nov 5, 2024

1. No.
2. I don't know if kvikio.CuFile handles compression, but many NIfTI files are gzipped. You will need to account for that if it's not done automatically. The construction of the header, affine and data seem reasonable. However, if there are scale factors, you will not get the same data. Also, nibabel lazily loads data, so you can get the header and your parameters like:

img = nb.load(filename)
shape = img.shape
offset = img.dataobj.offset
data_dtype = img.dataobj.dtype
slope = img.dataobj.slope
inter = img.dataobj.inter

raw = ...  # Do what's needed to get your cupy array.
if (slope, inter) != (1, 0):
    data = slope * raw + inter
else:
    data = raw

View full answer

Replies: 1 comment · 2 replies

Comment options

edited

effigies

Nov 5, 2024

Maintainer

No. I don't know if kvikio.CuFile handles compression, but many NIfTI files are gzipped. You will need to account for that if it's not done automatically. The construction of the header, affine and data seem reasonable. However, if there are scale factors, you will not get the same data. Also, nibabel lazily loads data, so you can get the header and your parameters like: img = nb.load(filename) shape = img.shape offset = img.dataobj.offset data_dtype = img.dataobj.dtype slope = img.dataobj.slope inter = img.dataobj.inter raw = ... # Do what's needed to get your cupy array. if (slope, inter) != (1, 0): data = slope * raw + inter else: data = raw

Marked as answer

1 You must be logged in to vote

2 replies

Comment options

edited

yiheng-wang-nv Nov 7, 2024

Author

Thanks @effigies for the answer. You are correct, for .nii.gz files, I did not figure out a fully GPU way to handle it. Thanks for the explain of lazily loading, I will enhance it accordingly! Thanks for the explain of scale factors, will include it in my formal implementation

Comment options

effigies Nov 7, 2024

Maintainer

Sorry, just a note that the slope and inter are also attributes on the dataobj. Will edit...

👍 1

Answer selected by yiheng-wang-nv

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Category

🙏

Q&A

Labels

None yet

2 participants