-
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…
-
excuse me, can you tell me how to get gradcam with my own networks?
-
L81: cam=np.ones(target.shape[1:], dtype=np.float32) # Why not np.zeros()?
-
Hi, @mingloo @jacobgil @flyingpot
In your code:
grad_cam = GradCam(model = models.resnet50(pretrained=True), \
target_layer_names = ["35"], use_cuda=args.use_cuda)
What's the meaning o…
-
I am trying your code and getting this error:
>> python3 yolov2_darknet_parser.py yolo.weights
yolov2.conv21.W.data = dat[38718432:67029984].reshape(1024, 3072, 3, 3)
Traceback (most recent call la…
-
Hi all, I have recently met with trouble when migrating from captum 0.1.0 to 0.2.0. When I am using the attribution function, I am passing a sparse tensor as additional forward arguments.
However …
-
- Hi. I am trying to import from tf_explain.core.gradients_inputs but facing an error
…
-
Hi,
It appears the opacity parameter settings in heatmap_display are causing gradCAM to not properly superimpose on original images. This is specifically being seen when using CIFAR10 and small siz…
ksasi updated
4 years ago
-
TF 2.1, tf-explain 0.2.0
------
Hello,
I'm using tf-explain (callbacks) on about 70.000 images, 56*56*3, and two labels (0: 13%, 1: 87%), in order to explain class 0 classification. Whereas Gr…
-
I came back to this and realized the notebooks don't run with tensorflow 2. Sad!