Comments (4)
Hi, yes, it is. The main reason is that it is much faster.
I doubt that it would hinder the result. In fact, it may improve them as this is training data and the extra noise may help regularising. The amount of deformation is also fairly small. However, I never tested this properly (other than noticing that the performance of the trained networks is good), so it is possible that a different interpolation in training may slightly change the results.
On 13 Oct 2015, at 11:33, Amir Rosenfeld [email protected] wrote:
In get batch, the images seem to be re-sized using a nearest-neighbor interpolation,
look at line 77:
ims(oky,okx,:,si) = bsxfun(@minus https://github.com/minus, rgb(sy(oky),sx(okx),:), opts.rgbMean) ;Is this on purpose ? Seems that it may hinder the results.
—
Reply to this email directly or view it on GitHub #1.
from matconvnet-fcn.
Well, I'm dealing with images which may be quite small to begin with, e.g, 60x60 pixels, so nearest neighbor interpolation may be quite detrimental in this case.
from matconvnet-fcn.
I've also noticed that while the getBatch function resizes all images to a common size, the fcnTest function does not.
from matconvnet-fcn.
Hi, yes, that’s because in training it is more efficient to stack multiple images together, which is only possible if the size is the same. For segmentation, this may be ok.
If your images are particularly small, you could e.g. resize them beforehand, or upsample them 2 times using bilinear interpolation before using the nearest neighbour warping. However, I am not sure that there would be an advantage in making the images smaller.
To be clear, with these networks, the input image size is arbitrary (within limits) as they are fully convolutional.
On 13 Oct 2015, at 11:40, Amir Rosenfeld [email protected] wrote:
I've also noticed that while the getBatch function resizes all images to a common size, the fcnTest function does not.
—
Reply to this email directly or view it on GitHub #1 (comment).
from matconvnet-fcn.
Related Issues (20)
- Image input that is not a multiple of 32
- image segmentation implementation HOT 1
- how to train fcn on my own data on the matconvnet
- CUDA error when trying to use multiple GPUs: nnconv_forward_blas: CUDA error [cuda: forward: pointer does not correspond to a registered memory region] HOT 5
- Does any contributor accept payed contract for specific code ?
- out of memory gpu
- bopts.useGpu = numel(opts.train.gpus) > 0 ; issue HOT 1
- Can't download the "benchmark.tgz" HOT 12
- when use GTX1070 and beta23, report error: CUDA_ERROR_ILLEGAL_ADDRESS
- How to train my dataset using FCN HOT 3
- Warning: Escaped character '\S' is not valid. See 'doc sprintf' for supported special characters.
- Transpose on ND array is not defined. Use PERMUTE instead.
- Segmentation accuracy is better during training than testing for validation (val) images HOT 1
- No variable of name 'label' could be found in the DAG.
- vl_nnloss.m function error
- FCN model initialization for other networks rather than VGG-16
- pre-trained model lacking fields lead to error
- In FcnTest.m my predicted image does not get displayed
- vl_imreadjpeg.m error HOT 1
- Not format GZIP
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 matconvnet-fcn.