Closed bemoregt closed 6 years ago
Hey @bemoregt, Can you please attach a screenshot of the same?
What is the classification label for this image? @bemoregt
@sar-gupta, label is "line".
in lables, 0:"normal", 1:"line", 2:"hole"
@bemoregt Can you check running gradcam with an image that has just one line, instead of multiple lines, and share the result?
@sar-gupta
Those Horizontal lines are just background. Diagonal line is a only defect object which I want to find.
Is that background lines are critical obstacle for real object heat mapping?
@sar-gupta
I using target layer 4.2 or 4.1:
CONFIG = {
'resnet34': {
'target_layer': 'layer4.2',
'input_size': 224
},
# Add your model
}.get(arch)
@bemoregt Can you tell me the prediction acore for an image with just the horizontal lines (background) without any diagonal line?
@bemoregt Can you tell me the prediction score for an image with just the horizontal lines (background) without any diagonal line?
@sar-gupta
Normal class Classification Accuray Score may be 99.8% .. line or hole classes Accuarcys are same.
GuidedBackpropagation mapping method is more capable than grad-CAM for my image data?
@bemoregt "line or hole classes Accuarcys are same." I don't understand what you mean by this
Can you answer a few questions:
@sar-gupta,
Yes,
Can you answer a few questions:
1.Have you changed the architecture of resnet to have only three output units?
- I have using transfer learning with resnet(3-outpou FC layer) + pretrained imagenet.
2.Have you trained the changed resnet with your own training data? If so, how many samples did you train it on?
- About 5000 images per classes. Data augmented.
3.The sum of all predictions should be 100%. Are you passing the output prediction scores through a softmax?
- Yes, of course. all prediction sum is 100%. AUC of (line correct)/total is about 99.8%, I mean.
@bemoregt Okay
I need two more things for now to help you with troubleshooting.
Softmax scores of all three classes for the following:
Both of these should have the horizontal lines as background.
Thanks
@sar-gupta
1.Image with diagonal line in it. >> Line Class
2.Image without diagonal line. >> Nomal class
Both scores are nearly 0.998 (softmax).
Thanks.
@bemoregt Kindly provide the softmax scores for all three classes in both the cases.
To clarify, by softmax score, I mean the three outputs from softmax layer.
Closing because the issue is not related to this project. However, discussion can be continued here.
Hi, @sar-gupta
As a result of classifying with Resnet, Accuarcy is over 99%. If you hit map the object area with gradCAM with that model file, it does not match exactly. Why? it does not match exactly. Why?
It seems to be a problem of GradCAM rather than Resnet classification learning. The objects to be hit-mapped are not as local or blob like dogs or cats, but close to a long straight line. In this case, GradCAM seems to miss the object area. Have you experienced this?
For a well-trainedd Resnet34 model, how do you optimize GradCAM?
Thanks, in advance.
from @bemoregt.