-
Allowing training on MSP device besides CUDA and CPU.
**Motivation**
Since the introduction of PyTorch Nightly, it is now possible to use tell PyTorch to use the embedded GPU of the new M1 chips o…
-
`What would you like changed/added and why?`
Currently, all blocks are included in training. We should remove dropping blocks which are all zeros as training on them is redundant.
`What would be t…
-
{
"name": "IndexError",
"message": "index 3000 is out of bounds for axis 0 with size 3000",
"stack": "---------------------------------------------------------------------------
IndexError …
-
While looking at the debugging output dumped via the web interface, it kind of seemed like all the entity hashes ended with two or more zeros. Not yet sure whether this is really a bug or what's goin…
-
Hi ^_^
Thanks for your contribution. I am trying to apply SHAP to analysis the feature importance of my regression model. I have trained a vanilla LSTM model and it seems to be good enought to make…
-
The following code snippet was adopted from function DoB1Scaling:
`function rfGain=DoB1Scaling(PulSeg,dt,ActFA)
global VObj;
flag=zeros(size(PulSeg));
ind=diff(abs(PulSeg));
flag(find(ind=0)=…
-
### Describe the bug
warp_image_tps is returning a black image, both if tested with reasonable keypoints obtained with image registration frameworks and with random points. The warp_points_tps() is …
-
https://github.com/oasisprotocol/oasis-core/blob/18da8bc49d92a543795246b8bb7fb574df070eec/secret-sharing/src/poly/univariate.rs#L89
because we don't trim high degree zeros, `size` does not return o…
-
**Issue Description**
I tried to train the network on another private dataset. I started with overfitting on a single image. I noticed that a lot of optimizer steps are skipped, because of invalid gr…
-
Given an integer array nums, move all 0's to the end of it while maintaining the relative order of the non-zero elements.
Note that you must do this in-place without making a copy of the array.
Ex…