Almost everything is seen as OK with default settings

[JulienMaille]

Almost everything is seen as OK with default settings

[elepp]

try to use sigmoid but not rule in the last which is named layer 5

[eric-tc]

Hi,
i have the same behaviour. Did you find an answer?

[JulienMaille]

Not really, I tried to setup a Google Colab notebook.
https://colab.research.google.com/drive/101HUaOo3PskWp7h6DucR50pIGxO_SX2m
The loss during training doesn't look good to me

[eric-tc]

Hi,

i got it working. When you train the segmentation network please use only the defect inside Train_NG with lr 0.001. Train it for 100 epochs as default. When you train the decision network change the lr=0.1 with Adam or add some lr_scheduler like cycle learning. With these parameters i got both defect and good classification. Let me know if it is working also for you. Thanks

[JulienMaille]

Ok I will try that. Have you tried training it on your own dataset?

[eric-tc]

Yes i have tried but with no good results

[SampleW]

when i using defualt settings in training, the output mask in "testResultSeg" is completely black, no defect was detected,same In all pictures of all epoch (100 epoch ).
How can i fix it.
thanks.

[ShaneYS]

when i using defualt settings in training, the output mask in "testResultSeg" is completely black, no defect was detected,same In all pictures of all epoch (100 epoch ).
How can i fix it.
thanks.

hi, I have the same problem(the output mask in "testResultDec" is completely black), have you sovled it?

[eric-tc]

Hi @SampleW ,

have you tried with the images provided or with your own dataset?

[LoveIsAGame]

ValueError: num_samples should be a positive integer value, but got num_samples=0
how can i fix it?

[LoveIsAGame]

@eric-tc
@Nefast

[molyswu]

@LoveIsAGame
The same problem, how do you solve it？

[molyswu]

Tried to python train_segment.py
ValueError: num_samples should be a positive integer value, but got num_samples=0

THANKS

[molyswu]

Changed ".jpg" to ".bmp" at dataset.py .

ok

[1ylwang]

oh,Tried to python train_segment.py is ok, but tried to python train_decision.py is ValueError: num_samples should be a positive integer value, but got num_samples=0, why? how do you solve it?
thanks.

try to use sigmoid but not rule in the last which is named layer 5

Still not working. I doubt the implementation can work tbh

[DCC-lzhy]

try to use sigmoid but not rule in the last which is named layer 5

Still not working. I doubt the implementation can work tbh
just no act function，because loss function has the act.