-
Can’t import 'ConvBNReLU' from 'torchvision.models.mobilenet' while using GPU
Problem I’m following this tutorial to train an object detection model for Lens Studio. I want to use a GPU to train the model, either Google Colab’s cloud GPU or my local through Jupyter. When I try to import: import torchvisionfrom torchvision.models.mobilenet import ConvBNReLUfrom torchvision.ops import box_iou, nms I'm…
-
How to fix the drawPath script in "Spectacles Path" template
Hi there! I'd like to create an experience of spawning numerous objects along the generated forward path. I came across this Spectacles Path template and guide and provide a good starting point. I downloaded the finished project and when I run it to check it out, it seems like the elements are not reacting and following…
-
Template with pre-built ML model to detect TV objects
Hey folks! According to this doc, "Multi-Object Detection" should come with a model that allows detecting TV objects. I downloaded the template, but the only model there is the one to detect berries. I'm wondering if I'm missing anything or do I have to create my own model to detect TV screens.