Comments (1)
Hi All,
To start this discussion, I have a proposal of "Refactor input ‘transform’ interfaces":
- Keep current 'vanilla' implementation of transforms, it's similar to torchvision and user can use it if they don't have "dict" input data.
- Add another higher level adapter or proxy class to handle "dict" based input data. Take "random window croping" for example, this proxy layer will:
(1) generate a random window.
(2) call our crop_transform twice to crop the same window on 2 apply keys('image', 'label').
Welcome your discussion and please feel free to correct me if I misunderstand anything.
Thanks in advance.
from monai.
Related Issues (20)
- Add Code Coverage to PR Checks
- Why is there a significant difference in the maximum number of epochs required for different segmentation tasks?
- Layer norm not working in densenet
- Implement the ability to use layernorm with resnet models HOT 3
- Update the schema for MONAI Bundle HOT 7
- `RuntimeError` in `DataAnalyzer`
- Save and load parameters of a pre-processing or augmentation (transforms) pipeline
- Inquiry Regarding Functionality of CropForeground in MONAI Library HOT 2
- `lazy` ignored in `SpatialPadd` HOT 1
- Support specified filenames in `Saveimage`
- RuntimeError with SpatialPad when input is MetaTensor and padding size is the same as tensor size HOT 6
- SwinUNETR's PatchMerging Layer has bug? HOT 3
- Insufficient error message when interrupted in `DataAnalyzer`
- collate/stack a list of tensors > E: expected Tensor as element 1 in argument 0, but got int, type ['MetaTensor', 'int', 'MetaTensor', 'int', 'MetaTensor', 'int', 'MetaTensor', 'int', 'MetaTensor', 'int', 'MetaTensor', 'int', 'MetaTensor', 'int', 'MetaTensor', 'int'] in collate([metatensor([[[[-0.5960, -0.5960, -0.5960, ..., -0.5960, -0.5960, -0.5960], HOT 1
- Batch support for saliency maps
- Support newer openslide-python version that has available whls for newer python versions HOT 1
- Track any fixes made to MONAI Generative during porting
- Security vulnerability caused by pinned versions of transformers
- Remove all absolute paths in the Auto3DSeg templates generation (BundleGen) process HOT 1
- Can monai increase research related to cancer
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.