-
- [x] #23
- [ ] #24
- [x] #25
- [x] #26
- [ ] #27
-
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…
-
Here's a complete list of tensor method we need to implement:
- [x] `$abs`
- [x] `$abs_`
- [x] `$acos`
- [x] `$acos_`
- [x] `$add`
- [x] `$add_`
- [x] `$addbmm`
- [x] `$addbmm_`
- [x] `$add…
-
**Describe the bug**
Convolution configuration, ("batch_size, output_channels,input_channels, input_height, input_width, filter_height, filter_width, stride_h, stride_w, pad_h, pad_w, use_1d_systolic…
-
We unify the use of the methods `tensor` vs. `tensor_product` in parent classes.
Current situation:
Category `ModulesWithBasis` provides a parent method `tensor` to construct a tensor product of m…
-
- [x] bool
- [x] element_size
- [ ] get_device
- [ ] imag
- [ ] is_shared
- [ ] map_
- [ ] new_ones
- [ ] new_tensor
- [ ] real
-
I am trying to export a custom GeoCalib model to ONNX.
The model uses LMOptimizer, which accepts a custom class Pinhole (inherited from BaseCamera) as input. When I attempt to export the model, I en…
-
### 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…
-
When users get the ort values and do stuff to them, what the experience will be: Currently they will call .numpy() and ortvalue_from_numpy() and some io binding if the tensor is on cuda. With `__dlpac…
-
## 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…