Saksham comments

Results 27 comments of


                                            Saksham

Added Model for Time Series Classification

> You'd likely have to rebase #256 after merging this PR if you've made changes to the same functions/types in that one. If that doesn't sound like a problem, we...

Timeseries learning usecase

Hey @lorenzoh, So i was working on this issue. For starting i was creating a `TimeSeries` `Block` type, According to me each struct should just contain an array of values,...

Feature Request: Better Indexing for ModeResult object

Hey is the issue open ? Also can i take it up ?

feat: Add support for JavaScript

Hi @emilwallner is someone working on this issue ?

Addition of all Activation Functions.

Hi, @kartikdutt18, I would like to work on the implementation of Inverse Square Root Linear. Can I work on it ?

Addition of all Activation Functions.

@kartikdutt18 Thanks please do that. Is any activation function still unoccupied ? I recently about swish activation function, has someone implemented that previously?

Addition of all Activation Functions.

@kartikdutt18 Thanks a lot. Please add some more issues to work on

Addition of all Activation Functions.

Hi, @birm can I work on adding bipolar sigmoid activation function. I've seen it in a paper and some class slides on neural networks??

Adding a new transposed convolution function (similar to `torch.nn.ConvTranspose2d()`)

Hey is this an active issue that is being worked on ?

Adding a new transposed convolution function (similar to `torch.nn.ConvTranspose2d()`)

According to the docs :- `torch.nn.ConvTranspose2d` and `nn.ConvTranspose` are not compatible. `nn.ConvTranspose` is a wrapper around `jax.lax.conv_transpose` which computes a fractionally strided convolution, while `torch.nn.ConvTranspose2d` computes a gradient based transposed...