-
In some cases we may wish to rechunk our data prior to execution. This can help to balance between high scheduling overheads (too many tasks) and poor load balancing (too few tasks).
It appears …
-
After a bit of profiling, this is what I found out for Dask-GLM with Dask array:
```
14339 0.139 0.000 0.814 0.000 /home/pentschev/.local/lib/python3.5/site-packages/dask/local.py:…
-
I know it's common in ADMM (a similar Lagrangian decomposition method) to have an adaptive / dynamic penalty parameter and it would be nice to have this here as well. This could be very easy using cal…
-
I have a large-scale problem where I use the L1-regularized least square for compressed sensing by [ Stephen Boyd ](https://web.stanford.edu/~boyd/l1_ls/). However, the computation takes something lik…
-
I'm attacking the imageNet image. I used the Inceptionv3 pre-training model provided by Pytorch.
The following parameters are used for normalization:
`mean = torch.Tensor([0.485, 0.456, 0.406]).…
-
We aim at integrating ExaTron in the ProxAL decomposition solver. That would require to define a new `AbstractBlockModel` in ProxAL, named for instance `ExaTronBlockModel`. The generic interface of bl…
-
Compressed sensing is now really fast with FISTA : https://github.com/MagneticResonanceImaging/MRIReco.jl/discussions/102#discussioncomment-3655548
But there is still an issue with accuracy (https:…
-
@jackweiwang 您好,想问下为啥RFB-320.mnn测不出人脸呢??请教下如果我想用RFB-320.mnn而不是量化模型RFB-320-quant-ADMM-32.mnn来进行检测的话需要怎么修改呢?麻烦作者帮我解答下啦
-
**Is your feature request related to a problem? Please describe.**
Recently, there have been two papers that have demonstrated that Griffin-Lim ADMM has a higher quality than Fast Griffin Lim (the cu…
-
The optimization method is inconsistent with the original paper, could you please provide the source of the paper for this method? Thank you