Comments (3)
Hello
I am curious about the cases where it happen.
I work with full brain MRI segmentation and there the probability map are often very large. (ie number of possible patche center << NUM_SAMPLE
but let's imagine I want to focus on a small region with only five (connected) voxels. If I choose large enough patch size it seems to me that event the five possible distinct patches (each center on the five voxel of my cdf) will already be very similar. So taking only five patches will not solve the issue to have almost identical patches ... no ?
may be your proposition makes sense if the five voxel are spatially distinct ... but it looks weird to me to have single voxel regions ...
from torchio.
Hi,
The reason this came up is because I am using torchio for 2D samples, with each slice representing a patch in the classical sense. As a result, I sometimes have less available slices than the patches_per_subj set upfront. I am aware that this case is not usually encountered but it raises then the question: Why have that mechanism in place if it is not checked anyways? Why not remove the entire NUM_SAMPLES attribute alltogether if it is not set at all or at the wrong time?
For my application it makes sense to set the attribute but I understand this is not always the case. However, if the check and system is already there, why not use it in the way it was intended. I am happy to utilise my own classes that overwrite this functionality but the question still remains why the mechanism is there but not being used.
from torchio.
I was just questioning the use case, but I now better understand your's so it makes senses
from torchio.
Related Issues (20)
- Suggestions the modifying default value of prefetch_factor and the argument to set it for minimize the blocking-bottleneck between fetch subject and generate patch in Queue HOT 1
- Different transforms applied to CT and label HOT 11
- The Affine matrix does not change after applying the augmentations HOT 3
- Custom loader not used when loading data lazily HOT 2
- Seed is not working HOT 2
- Silenced exception makes it harder to debug custom Transforms HOT 5
- Resample
- tio.Resample does not work with custom image class HOT 2
- RescaleIntensity - multiple calls HOT 9
- Return sampled parameters upon request HOT 3
- Halve queue length when using DDP HOT 2
- bug in rotation part of tio.transforms.RandomAffine HOT 4
- get_subjects_from_batch has a hick-up with int metadata HOT 5
- masking_method in Mask class is not saved as argument (preventing applying the inverse transform)
- RandomAffine raises an error when isotropic=True and 3 elements are given for scales HOT 10
- Queue is not respecting the batch size HOT 1
- Resample an image by providing only the target affine HOT 1
- Supporting PyTorch 2.3 HOT 10
- Cannot copy subclass of Subject with keyword arguments HOT 1
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 torchio.