Dataloader that serves MRI images from a mogodb
Project description
# mindfultensors Dataloader that serves MRI images from a mogodb.
The main idea is to keep MRI images and corresponding training labels for segmentation tasks in a mongo database. However, each <img src=”https://render.githubusercontent.com/render/math?math=256^3”> 3D MRI tensor even in 8 bit precision is 16Mb. mongo’s records cannot be larger than this limit and we need to also store the labels of the same dimensions. mindfultensors fetches and aggregates each <img src=”https://render.githubusercontent.com/render/math?math=256^3”> tensor stored across multiple records, together with corresponding labels either for gray and white matter, 104 regions atlas, volume of each of 104 ROIs, or a 50 region atlas.
# installation
Eventually, the package will be placed on pypy, but for now, first clone the repo: ` git clone git@github.com:neuroneural/mindfultensors.git ` Then change directory to the newly cloned repository: ` cd mindfultensors ` And install locally by ` pip intall -e . ` # usage A detailed example of how to create a dataloader using provided dataset class and the corresponding tools is in scripts/usage_example.py
Do not forget to move the batches to the GPU once obtained.
Project details
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Hashes for mindfultensors-0.0.3-py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | f5367d40107ef6b8630438da2f36782b34e15e85868416d7300f87d3ad8e1edb |
|
MD5 | b93002dc46d626a6b7788bc479c9f085 |
|
BLAKE2b-256 | 4257e15f12c0517caf7a9578a6aca8fc358eefe78c19530b862f282017a39b27 |