-
### Title
ME-mppca: Building a tensor-based thermal denoising method
### Leaders
Marco Antonio Flores-Coronado @MarcoFloresCoro
### Collaborators
SPiN lab (BCBL)
### Brainhack Global 2024 Even…
-
I use tons of torch.Tensor.to methods in my model for moving tensor between cpu/cuda, but the method is not supported in torch2trt currently. Will it ever be supported in the future release?
torch.Te…
-
When we decorate a class with a function registry (e.g. `export.public_api()`) we should apply it to all methods of that class. This allows us to support features like type checking and overloading fo…
-
I am adding two new tensor methods related to NaN (is_nan and contains_nan). My unit tests are failing for burn-wgpu backend. See https://github.com/tracel-ai/burn/pull/2088 PR
**Describe the bug…
-
## Feature
Support for Custom Bin Width in `EntropyBottleneck`
## Motivation
So far only bin width equal to 1 is considered, but would be good to have this as tunable option.
## Additional context…
ghost updated
3 weeks ago
-
The Scaladoc should be similar to [numpy's API reference](https://docs.scipy.org/doc/numpy-1.13.0/reference/)
-
``` r
library(torch)
f = function(device) {
nn_spiral_net
#> [[2]]
#> torch_tensor
#> 0 0
#> [ CPUFloatType{1,2} ]
f("mps")
#> [[1]]
#> torch_tensor
#> 0 0
#> [ MPSFloatType{1,2}…
-
### Search before asking
- [X] I have searched the Ultralytics YOLO [issues](https://github.com/ultralytics/ultralytics/issues) and [discussions](https://github.com/ultralytics/ultralytics/discussion…
-
## 🚨🚨 Feature Request
- [ ] Related to an existing [Issue](../issues)
- [x] A new implementation (Improvement, Extension)
### If your feature will improve `HUB`
Currently, only Datasets can…
-
The current plan methods appear to include unnecessary device-to-CPU copies, as seen in the following links:
https://github.com/flashinfer-ai/flashinfer/blob/d30667b0a23c1cc9135f7557404409ca1a9b9f0…