-
I think, reconstruction/decoder is not much helpful in learning the model, but creating an extra computation overhead. So, in order to prove this hypothesis/thought (or whatever you call it), is it po…
-
If I want to apply this model to a multi-class multi-label classification, what changes would be required for me to make on the `Mask()` layer? Can you give me any hint?
Will there be any other chang…
-
1. for the loss funtion in 'class CapsNet' (train.py)
you use mask = u.ge(0).float() to complete the max operation. but after a check about this function(tensor.ge) i think we should not us thi…
-
Hi,
I would like to use a capsule model for the regression problem in which I have an input image with a shape similar to MNIST but with a label (vector length 40). which part of the code I should …
-
@XifengGuo ,
I was going through your program. I did not understand the purpose of the manipulate_latent function. Can you please give some explanation over this?
Thank you so much.
Regards,
B…
-
The following operations do not work as I expected.
```
a = np.random.rand(3,10, 8)
b = np.random.rand(3, 8, 1)
c = cntk.times(a, b)
c.eval().shape # Expected (3, 10, 1)
```
but this code…
-
Hi @XifengGuo ,
The given model is really good for MNIST dataset. I would like to train the model on PASCAL VOC/ MS COCO. Could you please let me know where and how do I the necessary changes to th…
-
I trained the model in my PC with the GTX-1060, I interrupt the training use Ctrl+c
I get 4 files in checkpoints, they are:
1.checkpoint
2.c2n_64_c1s_5_c1vl_16_c1s_9_c2d_0.7_c1nf_16_lr_0.0001_rs_1…
-
Hi,
In the paper you mention that you use Locally-Constrained Dynamic Routing, which means children
are only routed to parents within a defined spatially-local window.
But I cannot find this part i…
-
I was trying to implement `CapsuleNet` for classifying the Native digits. All the images are RGB images and resize to **`32 X 32`** and dataset has **10** classification output.
> **X_train_all.sha…
innat updated
5 years ago