Conversation
|
Thanks for opening your first pull request in this repository! Someone will review it when they have a chance. In the mean time, please be sure that you've handled the following things, to make the review process quicker and easier:
Thank you again for your contributions! 👍 |
|
Hi @ojhalakshya, could you rebase your repo, It will fix python error that might occur (It's unrelated to your PR). |
0e5347e to
70fd586
Compare
|
This code touches the ANN code, and there was recently a big refactoring of the ANN code in #2259, so be sure to merge the master branch into your branch here to make sure that nothing will fail if this PR is merged. 👍 (I'm pasting this message into all possibly relevant PRs.) |
kartikdutt18
left a comment
There was a problem hiding this comment.
Thanks @ojhalakshya, for working on this, just one minor comment. Thanks.
| * noise level sigma of the input(noisy image) and a | ||
| * coefficient 'a' which is one of the training parameters. | ||
| * Default value of lambda is 0.5. |
There was a problem hiding this comment.
Hey @ojhalakshya, could you please fix the indentation here. Thanks.
| * \end{array} | ||
| * \right. | ||
| * @f} | ||
| * lambda is set to 0.5 by default. |
There was a problem hiding this comment.
I think we can put this with the constructor
There was a problem hiding this comment.
Hi @favre49
I am afraid I have included this there also, line no 61 - 63.
Also these are important here because here I have defined the formula.
Thanks.
There was a problem hiding this comment.
The reason I said this is because this seemed like an implementation detail that would belong with the constructor, not with the overview of the class, and putting it in both places would be redundant
There was a problem hiding this comment.
Hi @favre49
I have implemented the changes.
Kindly see the same if they are satisfactory.
Thanks.
8b87115 to
2858662
Compare
favre49
left a comment
There was a problem hiding this comment.
I think everything is alright. Thanks for the good work!
|
I am very happy to be of help! |
I have added the soft shrink activation function.
It can be referred from link.
I have also tried to do the same according to the mlpack standards, any other improvements are appreciated and would be happy to work more.