LukeAI
LukeAI
I want to retrain csmobilenet-v2.cfg for a different task starting with the provided weights. How many layers should I extract from the provided weights? There are 59 [convolutional] layers and...
Hi, I'm interested in your project! It'd be great to get a high level description of how it works - both the one-stage and two-stage process?
I see there are [8 books](https://www.google.com/search?q=where%27s+waldo%3F+books) in total - so I guess this isn't the full set?
I've been trying to parse the camera calibration .yaml file via the ROS parameter server ([my ROS answers question here]( https://answers.ros.org/question/352519/how-to-retrieve-list-from-ros-parameter-server-that-is-not-comma-separated/) and I found that the output of camera_calibrator in...
This fixes [a bug](https://github.com/WongKinYiu/yolov7/issues/676) which happens if you run with `--evolve` After the first iteration, (because then `evolve.txt` can be found) ``` Traceback (most recent call last): File "train.py", line...
### My actions before raising this issue - [X ] Read/searched [the docs](https://github.com/cvat-ai/cvat/tree/master#documentation) - [ X] Searched [past issues](/issues) I have many tasks, unassociated with a project, created on an...
I have a couple of bfly-pge-31s4c-c cameras (set to bgr8 and 2x2 binning. So each image should be 1024 x 768 x 24 / (8*10**6) = 2.36MB) I've increased Ubuntu's...
I have a Blackfly BFLY-PGE-31S4C, Sensor: Sony IMX265 (1/1.8" Color CMOS), Resolution: 2048x1536, Color: true, Firmware Version: 1.61.3.0, ubuntu 16.04 This works well with: the pointgrey ros drivers. https://github.com/ros-drivers/pointgrey_camera_driver and...
There is currently a `DetectionHorizontalFlip` but no `DetectionVerticalFlip`. This PR adds DetectionVerticalFlip which is a common, useful augmentation, (which I want to use for my application with yoloNAS) Resolves: https://github.com/Deci-AI/super-gradients/issues/1161...
### 🚀 Feature Request If I export yoloNAS as an onnx and inspect with netron, I see the inputs/outputs are like this:  Which means, to use with TensorRT, I...