GradCAM does not match exactly. Why? about gradcam-pytorch HOT 17 CLOSED

Hey @bemoregt,
Can you please attach a screenshot of the same?

from gradcam-pytorch.

@bemoregt
Can you tell me the prediction score for an image with just the horizontal lines (background) without any diagonal line?

from gradcam-pytorch.

@bemoregt
"line or hole classes Accuarcys are same."
I don't understand what you mean by this

Can you answer a few questions:

1. Have you changed the architecture of resnet to have only three output units?
2. Have you trained the changed resnet with your own training data? If so, how many samples did you train it on?
3. The sum of all predictions should be 100%. Are you passing the output prediction scores through a softmax?

from gradcam-pytorch.

from gradcam-pytorch.

from gradcam-pytorch.

What is the classification label for this image? @bemoregt

from gradcam-pytorch.

@sar-gupta, label is "line".

in lables, 0:"normal", 1:"line", 2:"hole"

from gradcam-pytorch.

@bemoregt
Can you check running gradcam with an image that has just one line, instead of multiple lines, and share the result?

from gradcam-pytorch.

@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?

from gradcam-pytorch.

@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)

from gradcam-pytorch.

@bemoregt
Can you tell me the prediction acore for an image with just the horizontal lines (background) without any diagonal line?

from gradcam-pytorch.

@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?

from gradcam-pytorch.

@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.

from gradcam-pytorch.

@bemoregt
Okay

I need two more things for now to help you with troubleshooting.

Softmax scores of all three classes for the following:

1. Image with diagonal line in it.
2. Image without diagonal line.

Both of these should have the horizontal lines as background.

Thanks

from gradcam-pytorch.

@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.

from gradcam-pytorch.

@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.

from gradcam-pytorch.

Closing because the issue is not related to this project. However, discussion can be continued here.

from gradcam-pytorch.