-
Hi Hovinh,
Thank you so much for your wonderful DeconvNet code. I am wondering how can I take a look on deconvolution image from different layers other than the prediction layer? For example, de…
-
Hello.
I've tried to build a similar network to **DeconvNet** for the image segmentation, but I stacked on defining the fully connected layers in the middle of the net.
: 2.5
Are you willing to contribute it (Yes/No) : Yes
**Describe the feature and the current behavior/state**.
Some segmentation mo…
-
Evaluate the PatternNet and PatternAttribution methods based on the evaluation criteria from issue #9 and fill in the results in the table created in issue #23.
- [Paper](https://arxiv.org/pdf/1705…
-
**❔Question**
Hello,
I think it's a very interestring work! But I want to konw where I can get the dataset in "reproducing results on ViT", for example, "gtsegs_ijcv.mat".
I hope for your help. Tha…
-
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…
-
**System information**
- Windows 10 (64-bit):
- TensorFlow version: 2.1.0
- Python version: 3.6
- CPU
**Describe the current behavior**
I have implemented the custom layer described [here](ht…
-
Hi,
I have a network which outputs a tuple containing two elements. one of them is a scalar which is the one I want to use for multiple methods in captum.
Is there any way to handle multiple outputs…