skokec/segdec-net-jim2019
Surface Defect Detection with Segmentation-Decision Network on KolektorSDD
PythonNOASSERTION
Issues
- 0
the segment network precise
#26 opened by jjqcat - 3
License of the dataset and code
#25 opened by jnhwkim - 0
Rotation option is not working
#24 opened - 1
notebook and access to dataset from Ftp
#5 opened by JulienMaille - 2
Training strategy of deeplabv3 on the dataset
#23 opened by Gavinwxy - 1
Run the truning in my own data
#22 opened - 2
running in parallel with CUDA
#17 opened by xinlong-image - 1
Training with low number of samples
#20 opened by sinangokce - 6
Have question about the decision network
#21 opened by bill2239 - 2
- 0
tensorflow.python.framework.errors_impl.NotFoundError: KolektorSDD-dilate=5/fold_0
#19 opened by HuitMahoon - 0
How does calculate the positive sample number 33 in"With 33 defective images per training set in one fold"
#16 opened by lasmiles - 1
No valid saved model
#15 opened by Sodininkas - 1
- 1
Compatibility with tensorflow 1.14
#13 opened by sinangokce - 1
Output nodes name
#12 opened by JiatianWu - 5
Dilation for label images in 3D
#11 opened by sinangokce - 0
This is a great job! I'm working on a dataset with multiple defects on the same object. Thus I'm annotating the defects with different colors which makes my label images be in 3D contrarily to your case in which you are working with 2D labels. I tried to adapt your dilation code by changing the dimensions of structure but as expected it doesn't dilate as I want. Have you ever tested your code with colored labels? Best!
#10 opened by sinangokce - 0
This is a great job,
#9 opened by sinangokce - 0
It's a great job!
#8 opened by sinangokce - 5
Data Preprocessing
#7 opened by Tiamo666 - 2
About the dilation
#6 opened by leon0n - 3
prepare my own data
#2 opened by strongteck - 2
- 1
实际工厂生产产品外观缺陷检测
#3 opened by cylvzj - 2
KolektorSDD is not available
#1 opened