-
I mean is the same idea but not same implementation?
please refer: https://github.com/yiskw713/boundary_loss_for_remote_sensing.
```python
class BDLoss(nn.Module):
"""Boundary Loss proposed…
-
#### Issue description
Description of the issue - include code snippets and screenshots here
if relevant. You may use the following template below
* *Expected behavior:* (What you expect to hap…
-
The main motivation to use sinc function is its nice and smooth behavior around zero. However, the current implementation can produce results greater than 1 close to zero, and the results are not even…
-
I have been thinking about @dellaert's comments during our last chat that CGLS is particularly suited to SwiftFusion because CGLS only needs the JVP and VJP. CGLS does not need to know anything about …
-
I would like to implement a formula that involve eigen values and eigen vectors of the gram matrix. Do you think its possible to compute it with keops (e.g. using the KernelSolve) or not?
-
I have a question regarding the material estimation experiment. Did you obtain the observation from the original ArcSim simulator or this differentiable simulator?
In addition, I realize there is s…
-
## 🐛 Bug
On master,
```
import torch
import torch.nn.functional as F
x = torch.randn(3, 3)
y = torch.randn(9)
F.logsigmoid(x, out=y) # crashes
```
The crash does not occur on CUDA on mast…
-
Dear jax team,
I implemented `np.unwrap` by looking at the numpy source and changing the inplace-modification bits to `np.where` and `np.concatenate`.
While the values are correct, the runtime e…
-
I suggest to improve the English used for the documentation in the following:
> copy_initial_weights – if true, the weights of the patched module are copied to form the initial weights of the patch…
-
Hello,
I was wondering whether there's a more efficient way of sending additional input parameters to ODEfunc in the forward pass, than appending the additional parameter as part of the tuple-state…
ghost updated
4 years ago