-
Actually, the following code is used for the CapsNet implementation: [here](https://github.com/bojone/Capsule).
Thus, this repository should be added as a git submodule to get the latest fixes for …
-
I am trying to train this network on a dataset with different dimensions. My images are 16*16 large and I have only 2 categories. In CapsNet, input_shape is (16, 16, 1) and n_class is 2. I get the fol…
-
My server has two 1080ti, however, I almost spent 10 hours or more to run your code. What should I modify in your code?
-
In the main README.md, there is a line as:
`A CNTK implementation of CapsNet based on Geoffrey Hinton's paper Dynamic Routing Between Capsules`
The paper has two more authors: _Sara Sabour_ and _N…
-
Hello, @ageron
First, thanks your excellent work about CapsNet it is very helpful.
I have a suggestion about squash function (not very big deal),
The squash function can change to t…
-
[Train] Batch ID = 0, loss = 4.22318, acc = 0.0
[Validation] Batch ID = 0, loss = 1.2876, acc = 0.02
Evaluate full validation dataset ...
Current loss: 1.4351 Best loss: None
[TOTAL Validation] Ba…
-
Hi there,
while testing the script, I found that the utils module was not installed, So, I installed that through `pip install utils` (version = 0.9.0) after that, it couldn't import `combine_images`…
-
- **PDF**: https://openreview.net/pdf?id=HJWLfGWRb
- **Code**: https://github.com/www0wwwjs1/Matrix-Capsules-EM-Tensorflow/ (open-source-impl)
- **Reason**:
+ ICLR 2018 accepted paper, Hinton's p…
-
https://github.com/naturomics/CapsNet-Tensorflow/blob/4be551a1069e62ba8a5e7c12537c6672e3f11c6f/capsLayer.py#L78
I think this line is not preserving the following in the paper:
"Each primary caps…
-
Hi,
I am training Full Yolo to detect two classes. I have about 13k images for training where 70% of them are of class 1 and 30% of class 0.
As you can see below I am getting very good results for c…