Comments (5)
Hi @nguyenhg,
Why image_size should be divisible by 8 and >89?
so that we could handle multiple layers of "2×2×2 downsampling/upsampling with strides of two" conveniently.
The parameter spatial_window_size of [label] should be same with the one of [images] or not?
Not for the 3D-Unet, please check out the original release for more info: https://lmb.informatik.uni-freiburg.de/resources/opensource/unet.en.html
and the script for image/feature dims: https://lmb.informatik.uni-freiburg.de/resources/opensource/findsize.m
from niftynet.
Hi @nguyenhg thanks for the feedback. This is using the 3D U-net (https://arxiv.org/abs/1606.06650) and by the original design, it takes 132×132×116
-voxel inputs and predicts 44×44×28
-voxel outputs. Both of your Q1 and Q2 are due to this "cropping" effect of the network (also please note there's another spatial_window_size
parameter in the [inference]
section of the config).
You could also remove the cropping layer by deleting this line https://github.com/NifTK/NiftyNet/blob/dev/niftynet/network/unet.py#L122
the result is a network taking NxNxN
inputs and predicting NxNxN
outputs. Hope this helps!
from niftynet.
Hi @wyli, thank you for your comment. I did the interpolation for my data to original design: 132×132×116 for both images and labels, voxel size is 1.76×1.76×2.04 . And re-run the training step, but the dimension is not compatible.
Could you explain me:
Why image_size should be divisible by 8 and >89?
The parameter spatial_window_size of [label] should be same with the one of [images] or not?
from niftynet.
Hi@wyli, with the cropped version, the border has to be specified to 44, which makes the inference too long and results in bad performance. Do you have any suggestion on this? Thank you.
from niftynet.
Does it mean the maximum size of input volumetric images is no larger than [132 132 116]? If so, it makes the NiftyNet is not so flexiable.
from niftynet.
Related Issues (20)
- Expected size of adding custom dataset for classification task on MR dataset?
- Provided indices are out-of-bounds w.r.t. dense side with broadcasted shape. Histogram error? HOT 1
- Using GANs without conditioning
- upgrade to support tensorflow 1.15
- If Niftynet supports Xavier initialization?
- Remove unconnected islands
- Default values for the bias field layer might be too large
- Float comparison in histogram normalisation layer
- Handle SimpleITK's lack of thread safety
- Sections containing `csv_data_file` are not loaded
- AdamW optimizer
- TensorRT frozen graphs - integration with NiftyNet
- Feature: Rewrite NiftyNet to use TensorFlow 2.0 HOT 1
- Using NiftyNet to do segmentation of MRI scans(in .nii extension) to grey matter,white matter and csf
- NiftiNet Roadmap HOT 2
- Niftynet window aggregator function for inferens - explaination needed
- using other DL framework
- How to train a model with one input and multi-output?
- dense-vnet to Monai HOT 1
- Segmentation classes description not available
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 niftynet.