-
Hi!
It is possibile to add support for macro, meso and micro cycle training?
An example of structure is this:
Macro
Meso 1
Micro 1
Micro 2
Meso 2
Micro 1
…
-
from the `ScatteringBase1D` frontend to `compute_meta_scattering`, `precompute_size_scattering`, and `scattering_filter_factory`
This `dict` could be named `filterbank_kwargs` and eventually also c…
-
I have noticed that DWT always applies padding, even in the case of perfect powers …
-
Set up an API that, like Queryset definitions, makes it possible to define models through a simple API.
-
Good day!
Thanks a lot for your efforts with this lib!
Recently I encountered some problems with preserving spatial dimensions of tensor.
```
j = 3
wave = 'db1'
mode = 'symmetric'
layer0 …
-
Source: [Masader Project](https://arbml.github.io/masader/)
- uid: openiti_proc
- entry: https://arbml.github.io/masader/card.html?202
- Link: https://zenodo.org/record/2535593#.YWh7FS8RozU
- Lice…
-
```
test = np.arange(16).reshape(2,8)
wav = pywt.wavedec(test, 'haar', mode='periodization', level=None, axis=-1)
#wav = pywt.threshold(wav, 3, mode='hard')
recon = pywt.waverec(wav, 'haar', mode=…
-
I've tried your implementations using multi-GPU and failed.
the code is as follows
```
device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
xfm = DWTForward(J=3, wave='db3',…
-
https://github.com/srophe/caesarea/issues/6
-
### Description
Currently direct access and cache access to OCLC FAST are labeled the same, such that they appear to be the same authority. At the minimum, the labels need to be updated to make it…