-
Recently, we introduced [Tied-Augment](https://arxiv.org/abs/2305.13520), a simple framework that combines self-supervised learning learning and supervised learning by making forward passes on two aug…
-
It is a great package that improves my efficiency , When I test cifar10, for the one-hot label , I can use
```python
label = torch.argmax(label,dim=1)
```
to transform one-hot label but When I te…
-
Brendon and Daniela to find beliefs about β
-
It was mentioned in the paper "Our model resembles WaveNet (Oord et al., 2016a) in the use of tree-structured dilated convolutions. However, our principle-guided design has distinct skip-connection st…
-
### Go version
```
$ ~/sdk/go1.23/bin/go version
go version go1.23rc2 darwin/arm64
```
### Output of `go env` in your module/workspace:
```shell
$ ~/sdk/go1.23/bin/go env -changed
$
```…
rhysh updated
3 months ago
-
## Bug report
### Describe the bug
Here is a clear and concise description of what the problem is:
Whenever I play some specific 1080p hev1 encoded HEVC movies I've been noticing that mos…
-
Hello,
I'm using v2.0.0 dataset and successfully followed the example on loading Waymo data using dask.
This is all fine for quick testing, but when I use the same method on my data loader things d…
-
During training the forward method casts to FP16 but during sampling no
```python
@torch.no_grad()
@cast_torch_tensor
def sample(self, *args, **kwargs):
self.print_untrain…
-
Currently, the inputs for OpenScPCA-nf modules are channels that contain the following tuple:
`[project_id, project_dir]`
This makes for a pretty nice compact and universal input, and for modules …
-
Hi,
I have PacBIO Hifi reads (~4kb) with very 200-300x coverage, as well as 30x PCR-free WGS data for around 30 normal human samples. I'm particularly interested in one region around 400kb long, th…