-
**To Reproduce**
Steps to reproduce the behaviour:
Use AMD ROCm and try and inference on standalone mode.
Might be an issue at driver level / ROCm level with HIP. Looks like some parameter isn'…
-
`(1, 21, 12) - predict.shape `
```
import shap
e = shap.DeepExplainer(loaded_model, X_data)
shap_values = e.shap_values(X_data)
```
```
AssertionError Traceback…
-
After following https://www.kaggle.com/learn/deep-learning with Tensor Flow and Keras (and Kaggle data and pretrained models) is pretty easy today to offer a service for detecting "things" inside imag…
-
We’re looking to extend the TensorBoard user interface to display interesting GPU details for each node in a neural network. The GPU Details that we plan to display focus on the usage of tensor cores…
-
We require a function that expands and collapses sidpy.dataset objects. For instance, the need to collapse spatial dimensions and/or spectral dimensions when undertaking matrix or tensor factorization…
-
## 🚀 Feature
Kornia already has a set of exciting deep learning based models implemented.
I would like to add to Kornia the first stereo model: PSMNet. PSMNet is used in many stereo research pape…
-
The following code for the contiguous check in **shape.rs** will trigger problems for the squeezed tensor (n-dim to 1-dim) because of the " if dim > 1" condition (recently added ).
``` rust
//…
-
In order to write a multiple view geometry and make it easy to used in deep learning, I think the input and output tensor should have a batch dimension. And I need a few batched versions of the linear…
-
[Physics Informed Neural Networks by NVIDIA](https://docs.nvidia.com/deeplearning/modulus/user_guide/theory/recommended_practices.html#physics-informed-neural-networks) ... more generally, [Physics-In…
-
I tried to run this file https://github.com/fchollet/deep-learning-with-python-notebooks/blob/master/chapter11_part02_sequence-models.ipynb and this section as the below:
import tensorflow as tf
i…