Comments (9)
from segmentation_keras.
Yes, the dataset was corrupt somehow. Just re-downloaded and it is fine.
from segmentation_keras.
@Barfknecht Could you, please, tell what exactly was wrong with your dataset, because I have this problem on my own dataset. But it doesn't look corrupted
from segmentation_keras.
@dimaxano Can you give an example of an image?
The issue with mine was that the pixel values of the masks were not valid, so instead of them indicating the class, it had corrupted it and changed it to random ASCII characters.
from segmentation_keras.
from segmentation_keras.
@dimaxano Well I can see your problem. So the issue is that the image mask has not been correctly formatted. So if you look in the benchmark_RELEASE/dataset/pngs folder you will see how the masks have been formatted. For example, 2008_000026.png is a mask of a person. That is class 15 of this altered pascal_voc dataset. When you open the png as a matrix, every pixel where the person is located has a pixel value of 15. So the input image is grayscale where the pixel values represent the class associated with it. So I have added one more class to this set, namely tyres. I have then made this my 21st class and when I created the mask, every pixel which is a tyre I set that pixel value to 21.
I hope this helps
from segmentation_keras.
@Barfknecht Thanks for advice! Now it works
from segmentation_keras.
@dimaxano No problem, can you give me some advice on how you trained on your own dataset?
from segmentation_keras.
@Barfknecht For now, I have some troubles with predicting (#33), but training was quite easy (except this problem with labels ). It is more important to prepare data in a right way
from segmentation_keras.
Related Issues (20)
- Problems with CuDNN library HOT 4
- Black image after segmentation HOT 7
- Modifying number of class HOT 7
- How do you determine the width and height of the input, and the size of the label_margin? HOT 1
- convert to mask looks bad HOT 1
- The pascal_mean in image_reader.py HOT 1
- About the pretrain model HOT 1
- What is the reason behind the removal of padding?
- How to handle high resolution images HOT 2
- When the mask image is converted to array, is there a value of <21 in it? HOT 1
- Why sparse_categorical_crossentropy is used? HOT 1
- How to deal with unbalanced classes? HOT 1
- Failure running conversion through provided Docker container HOT 2
- vgg_conv.npy HOT 1
- Weights Conversion Error: wget: unable to resolve host address 'vobj.cs.princeton.edu' HOT 3
- AtrousConvolution2D vs.Conv2DTranspose
- AttributeError: module 'keras.utils.generic_utils' has no attribute 'populate_dict_with_module_objects' HOT 2
- No module named '_pywrap_tensorflow_internal' HOT 1
- how to add one more category in dataset
- Training freezes 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 segmentation_keras.