-
Thanks for the GREAT repo! I noticed, there is only one small difference between the algorithms of this 2 visualization methods:
For Guided BP we use: **return (F.relu(grad_in[0]),)**
For Deconvne…
-
@gbaydin This is a question about something I thought might "just work". Don't spend time on it, I'm just curious if there's something obvious I'm doing wrong.
I took a tentative attempt at hyper-p…
dsyme updated
3 years ago
-
Atm, guided backpropagation is included in Grad CAM automatically (see [here](https://github.com/sicara/tf-explain/blob/1a75841762985e55abe19107d09279f68f5731c8/tf_explain/core/grad_cam.py#L89)). The …
-
Hi @kazuto1011 , Thanks a lot for your great work! I have a small question when I try to use GuidedBackPropagation in my own model. In my model, I use 'PReLU' layer instead of 'ReLU' module. So how do…
-
In grad-cam paper,the authors use the gradient of the score for class c namely y^c partial derivative of feature maps A^k of a convolutional layer to obtain the neuron importance weights.But how to c…
-
I find the "target_layer_names" of these two models, but when I run the modified code, I get the following error:
**RuntimeError: size mismatch, m1: [1 x 277248], m2: [768 x 1000] at /opt/conda/con…
-
Hi, Thank you very much for this awesome repo!
In Guided Backprop implementation ( in guided_backprop.py ) I don't see why it is necessary to block the gradients where the neuron didn't activate ( th…
-
Hi,
I was using the guided backpropagation to visualize my own pretrained models and found out the resultant gradient maps did not have the same dimension as the input image, but the ouput shape of…
-
Good day! I use fine-tuning loaded model ResnetXt-101 from .pth file. GradCam works good with my model, but when I try to use GuidedBackprop I get the error:
-> 80 gradients_as_arr = self.g…
-
arXiv论文跟踪