Comments (3)
Hi Jiangm18:
According to the page 5 of the paper states: "As a method of regularization, we extend the idea of reconstructing the input to promote a better embedding of our input space.", it is a regularization technique to prevent over-fitting.
Kr,
Cheng-Lin
from segcaps.
Hi Cheng
I tried to fit my data with segcaps but it converged too slow and the loss value stuck in -0.58(Dice Coeff), how many epochs you use?
Best
Jiang
from segcaps.
Hi Jiang:
According to my experiments, the model is sensitive on data. You may need to try different loss functions and --recon_wei on your data set. I found the margin loss also works for COCO dataset. I can get a converge result with overfit on single image by 20 epochs (1000 iterations, lr=0.01, recon_wei=20). But I cannot make the model even starting to converge after 20 epochs with 80 color images and enable data augmentation option. Due to the limit GPU resource I have and I believe parameters may need to be adjusted, I stop the experiment so far. According to the url: https://www.kaggle.com/c/data-science-bowl-2018/discussion/54500, author responsed via twitter: SegCaps converged in ~ 232k iters.
Kr,
Cheng-Lin
from segcaps.
Related Issues (20)
- Creating MSCOCO dataset HOT 2
- What does num_atom mean?
- Instruction for running the code from .jpg files HOT 3
- TypeError: deconv_length() missing 1 required positional argument: 'output_padding' HOT 13
- bad mask HOT 1
- RuntimeError: Exception thrown in SimpleITK ReadImage: /opt/miniconda2/conda-bld/simpleitk_1546539363356/work/Code/IO/src/sitkImageReaderBase.cxx:107: sitk::ERROR: Unable to determine ImageIO reader for "data/imgs/train470.png"
- Can not load images and masks HOT 3
- Final output and raw output are always same no matter what input images are given HOT 1
- Why transformation matrix shared by different child capsule types?
- Training image and mask error HOT 4
- Did you realize the Experiments Results stated in paper of Capsules for Object Segmentation?
- RGB images with binary masks
- dependencies version
- Value Error
- ValueError: No gradients provided for any variable HOT 1
- ValueError: Dimension 0 in both shapes must be equal, but are 3 and 16.
- Proplem with deconv_length from keras.utils.conv_utils
- Iteration Time Issue
- Training Performance Do Not Improve HOT 4
- expected out_recon shape (512, 512, 1) HOT 2
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 segcaps.