Hyeon-Seo Yun

keras tf layer Dot operation not supported?

3

I am trying to make a GCN model that is compatible to this package. I trying to use tf.keras.layers.Dot(axes=-1) as the Adjacency matrix for my GCN model, and I have...

Hello; I just wanted to notify that I noticed that HLS version of torch.nn.LeakyReLU() doesn't actually mutiply the negative input by 0.01, like it is done normally in pytorch. The...

I have been using pytorch a lot more than tensorflow, so writing in pytorch and converting to hls4ml would be more convenient. I tried to simply convert some of the...

This is my first time submitting a pull request, let alone for work, so corrections are appreciated. ## Description - I have added a custom block called residualBlock on top...

Unexpected output shape value for BatchNorm1dToQuantScaleBias

3

Hey, I have been trying to implement brevitas' version of nn.BatchNorm1d(), and I receive this error: `ValueError: Using a target size (torch.Size([64, 1])) that is different to the input size...

Fixed issue where the output shape of `class BatchNorm1dToQuantScaleBias` was giving an unexpected shape of `[1, input_dim, batch_dim, input_dim]` instead of `[batch_dim, input_dim]`. The issue came from the fact that...

Feature request for typetracers handler for `np.interp`

8

Hello, I originally made a QA question on implementing dask_awkward equivalent of `np.interp` in this [QA discussion](https://github.com/dask-contrib/dask-awkward/discussions/492#discussion-6435930). @lgray suggested wrapping `np.interp` with `dak.map_partitions`, but doing so gave `TypeError("cannot compare unknown...

support for dask_awkward.mean() needed

6

Dear Developers. Hello, I am one of the graduate students working with dask_awkward within coffea 2023 pacakage, and it seems like support for `dask_awkward,mean() ` function is missing. What I...