-
I have the following script:
`import random
import cutlass
import torch
print_module = False
batch = 256
feature_dim_in = 4098
feature_dim_out = 10
type_A = torch.int8
type_B = to…
-
when i use a simple net for testing
```
class simpleNet(nn.Module):
def __init__(self) -> None:
super(simpleNet,self).__init__()
self.linear_input = nn.Linear(64,100)
self.relu = n…
-
We've known about this for a while now, I think it's time to at least make it an official feature-request. A solution is not urgent, though.
Matrices which are used in `ODEPrior` are, more often th…
-
I implemented several linear operators related to solve control problems. An example is the Lyapunov operator L: X -> AX+XA', where A is a squre matrix. This operator acts usually on symmetric/hermiti…
-
- Add a boolean member called `symmetric` that defines is the operator is symmetric or not. This will be always False if the operator is not square, while it can be fixed for a square operator or depe…
-
This is kind of a note/Todo:
https://docs.python.org/3/reference/datamodel.html#object.__init_subclass__
We can use it for the Autograd mechanic of linear operators.
For endomorph operator we would …
-
Once we have #737 it would make a lot of sense to decide on a similar base class for non-linear operators. We could have
`Operator -> DifferentiableOperator -> LinearOperator`.
- `Operator` would h…
-
As discussed, adding and dropping columns from the active-set matrix `S` is especially inefficient. Because `S` is only used through products with vectors, it seems plausible that we could replace the…
-
We are refactoring the regression tests under the [fix/tests](https://github.com/DeepWok/mase/tree/fix/tests) branch. On the hardware side, we observed the following errors. Due to the large number of…
-
At the moment we have the following setup for linear operators / functionals that are not built out of elementary operations, where `f isa AbstractQuasiVector` and `T isa AbstractQuasiMatrix`:
1. `De…