Comments (5)
Hi @atbenmurray ,
I committed a PR #25 for this task, could you please help review it?
Glad to see your feedback.
If I misunderstand anything, please feel free to contact me.
Thanks in advance.
from monai.
Currently we have the functionality to rescale arrays to [0,1] range, this suffices for the segmentation example so we feel it's beyond the MVP scope.
from monai.
Hi @ericspod @atbenmurray @wyli @yanchengnv ,
Thanks for the discussion of the design principle on transforms.
I think we are on the same page to use basic PyTorch only. Then I have several questions about ShapeFormat, could you please help make them clear before we start to develop?
- torchvision supposes the 2D input images are PIL image which is "channel last", and converts to torch.Tensor which is "channel first" in "toTensor()" transform. Can we also suppose all 3D input images are "channel last"?
- If not all input images are "channel last", how does every transform know the input image is "channel last" or "channel first"? In previous design, we defined a MediaImage object to record ShapeFormat information with image data together, then we can support 12 kinds of ShapeFormats in transforms.
- Should the transform support to process both numpy data and torch.Tensor data? If only support numpy data, I think we need to define an implicit transform "toTensor()" at the end of chain.
Welcome your discussion and please feel free to correct me if I misunderstand anything.
Thanks in advance.
from monai.
@Nic-Ma as I understand it, for the current sprint we assume the input image is in NifTI format, which uses 'channel last'. Before feeding it to the network we add another 'ToTensor' transform to convert it into a 'channel first' torch tensor. Let's keep the implementation "minimal", for example, following torch vision's implementation.
from monai.
#25 #28 jointly resolve this issue.
from monai.
Related Issues (20)
- No space left on device when test with conda
- Define categories for the MONAI bundle properties HOT 5
- Deprecating tests for python3.8
- AutoencoderKlMaisi input num_splits default value may cause unexpected error
- determinism (seeding) not working for transform RandSimulateLowResolutiond
- LoadImage default reader improper affine handling on nrrd files with non-standard ijk_to_ras HOT 1
- Update doc to drop support Python 3.8 when it meets its the end of life HOT 2
- Mismatch result in `test_wsireader` HOT 1
- Cannot use monai-deploy package by following offical tutorial
- No randomness for threading=True HOT 1
- Pretrained weights incompatibility for resnet10 HOT 2
- Incorrect repo name during bundle download
- Auto-select bundle version based on the version of MONAI HOT 2
- Option to Disable `Compose` list/tuple Expansion HOT 1
- Failed building wheel in python 3.11
- Metatensor can modify values? HOT 4
- Module 'SABlock' has no attribute 'causal_mask' HOT 1
- RuntimeError: Can't redefine method: forward on class in test_unetr
- New issue introduced in mypy 1.11.0
- Consideration of Flash Attention in Generative Components HOT 6
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from monai.