-
Here is a question we found when writing models using DGL. Let's first look at a following GCN example:
```python
import torch.nn as nn
from dgl import DGLGraph
# Node update module
class NodeMod…
-
In v2.15, when you have 2 inputs that are exactly the same but for some reason have different outputs, you get an unhandled exception:
``` c#
double[][] inputs = new double[][] {
new double[] { 0…
-
We can hopefully get backward propagation using
newtype F a b = F (a -> ( b :* (b -> a) ))
We can add that to the two existing ADs. I'm not sure how to make it `Closed` though; it seems that…
-
In term 1 lesson 4 section 20 backpropagation algorithm there is some notation that causes me some confusion, especially when coming from section 19. At least it was so for me :)
You see, in the hidd…
-
**Problem**
The NN.py program does not train properly when using 2 or more hidden layers.
**Possible Errors**
*The cause of this problem is currently unknown.*
1. Most likely a problem with the …
-
In current form (without minus sign in front of _trust_region_loss), reward obtained just sits at ~9 on cartpole; it might take off after more steps but haven't tried it.
With minus sign in front, re…
-
I would like to develop a scalable Finetune class, need some suggestions, following are the suggestion api
```
/**
* Fine tune deep network like StackAutoencoder
*
*@tparam OutputLayerType ty…
-
Hi,
As this repo has no license I'm not sure what is allowed here, I want to port this lib to Crystal (https://crystal-lang.org/) Is that ok with you ?
-
I am trying to extend the example from your book with those things, but I can't get them to work. Can you maybe show how that would be done in python?
Thanks!
-
http://karpathy.github.io/2015/05/21/rnn-effectiveness/