-
Notifications
You must be signed in to change notification settings - Fork 110
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
[Any Hints?] - TF-explain for YOLOv3 #133
Comments
@Meywether Which implementation of yolov3 do you use and which error message do you currently receive? I am also working on this question and maybe we can benefit from each other. |
Hello @johnny-mueller, |
@Meywether If I understand you correctly, you are currently trying to create the model using keras.model(input_layer, output_layer)? if this is the case, then we are currently in the same spot. Unfortunately, I can't really get any further, but maybe you have an approach at the moment? |
@johnny-mueller Yes, we are at the same spot. The main problem, out of my perspective is, that we are loosing the connection between the class props after the nms of yolo, before the yolo head. |
@Meywether I am also of the opinion that it is a connection problem. I permanently get a message that he cannot find input_07. But if you take a closer look at the model you see that there is an input_06 layer and only then an input_09 again. I can't find input_07 and input08 myself. |
@johnny-mueller Maybe I can help you: Maybe this information can help you more than me XD |
@Meywether inputs= [model.layers[0].input] + [model.layers[2].layers[0].input] + [model.layers[6].layers[0].input]
last_conv_layer = model.get_layer('yolo_output_1')
last_conv_layer_model = keras.model(inputs, last_conv_layer.output) But my next problem that I could not solve so far lies in this line. So if anyone has a suggestion, I would be happy to hear about it. with tf.GradientTape() as tape:
# Compute activations of the last conv layer and make the tape watch it
last_conv_layer_output = last_conv_layer_model(img_array) The error message that appears is: |
Congrats! @johnny-mueller |
@Meywether And yes, it must be "keras.Model()" |
Fine! same starting repo! |
@Meywether No it does not. It was just a copy&paste error. In my code it was right |
perfect. mmh whats your input shape of the image? or the layer before? |
Input processing is the same as in the detect.py file from the original yolov3 repo |
mmh ok, can you try to get the output shape of the previous layer before the error occurs? |
shape = (None, None, None, 256) |
@Meywether here the file is uploaded. the code is still very unorganized and chaotic. https://www.file-upload.net/download-14080821/grad-cam.py.html |
(None, None, None, 3, 85) -> from your code above, it seems that, whyever, there is a shape issue, need to check you code, when i am back at my pc :) |
@Meywether any suggestions to solve the current issue? |
No, I did not come any further sorry -.- Need to improve my understanding of these things in more detail ... |
Hello everyone :)
Does anyone has experience by using tf-explain or any other explainability lib for using it with YOLOv3?
I am looking pretty long for it, but only found this one: feature vis yolo v3 https://github.com/jennalau/feature-vis-yolov3
But it is not working, because a lot of files are missing and the author is not responding ...
Many thanks in advance!
Meywether
The text was updated successfully, but these errors were encountered: