-
Hi @Peize-Liu
When I tried to execute your program on my Jetson Orin NX's Docker, following your [guide](https://github.com/HKUST-Aerial-Robotics/OmniNxt?tab=readme-ov-file#runtime-setup), the err…
-
I followed the repository's guidelines but encountered the error shown below.
I am using only the Realsense camera because I currently don't have a 4-camera setup ready. It's indicated that the Omn…
-
Thank you for this wonderful repository.
To minimize dependency errors, I decided to try using Docker.
My PC:
Ubuntu 22.04, with CUDA enabled
I have attached my laptop specs for your review.
…
-
Hello, what is the formula to calculate the loss in mobilenetvlad with distillation? I saw in loss function there is descriptor_n and descriptor_p, where are they come from? I am sorry about i don’t …
-
Please make sure that this is a bug. As per our [GitHub Policy](https://github.com/tensorflow/tensorflow/blob/master/ISSUES.md), we only address code/doc bugs, performance issues, feature requests and…
-
Hi everyone,
in my quest of converting a tensorflow saved model to a coreml model, I'm facing some issues.
So far, I have a TF saved model, I opened it and froze to graph to a single .pb file
Th…
-
I am not clearly about which place the descriptor dimension reduction is located in training process of MobileNetVLAD. Is it applied to global descriptor computed by teacher network, and then use the …
-
I get "yes" in chapter 3.1. But in chapter 4.1, distillation uses NCLT dataset which located in The University of Michigan North Campus, while pose estimation dataset uses Google Tango in Zurich.