Michael A. Alcorn comments

Results 16 comments of


                                            Michael A. Alcorn

🐛 [Bug] RuntimeError: [Error thrown at core/runtime/execute_engine.cpp:132] Expected inputs[i].is_cuda() to be true but got false Expected input tensors to have device cuda, found device cpu

Interestingly, this code, which just uses normal boolean indexing, seems to work with the Dynamo path: ```python3 import torch import torch_tensorrt from torch import nn DEVICE = "cuda:0" class Indexer(nn.Module):...

🐛 [Bug] RuntimeError: [Error thrown at core/runtime/execute_engine.cpp:132] Expected inputs[i].is_cuda() to be true but got false Expected input tensors to have device cuda, found device cpu

When using PyTorch 2.3.1 and Torch-TensorRT 2.3.0, I still get the same error for the original code (i.e., with `ir="torchscript"`), but when using the Dynamo backend or `output_format="torchscript"`, I don't...

A question regarding the variable ray_directions

`ray_directions` is eventually normalized in [`run_one_iter_of_nerf`](https://github.com/krrish94/nerf-pytorch/blob/a14357da6cada433d28bf11a45c7bcaace76c06e/nerf/train_utils.py#L147).

number of views used for training

Can you provide more information?

number of views used for training

My implementation only conditions on a single view, but it should be straightforward to extend the code to condition on multiple views using Section 4.2 and Figure 18 as a...

gr.Model3D does not display valid 3D models (PLY/GLB/OBJ) — only shows a blank canvas

[I also reported this](https://github.com/gradio-app/gradio/issues/12120#issue-3557511299) and my issue was prematurely closed.