-
Done computations are a bit complicated by the fact that communication between CPU and GPU is mostly write-forward. It may make more sense to have a simple envelope calculated on CPU side, then upload…
-
Hi, I want to know how can I run yolo detection with your model provided? I don't understand the given examples in your bashfile track1.sh
`./darknet procimgflr cfg/aicity.data cfg/yolo-voc.cfg yolo-…
-
What is the top-level directory of the model you are using:**models/research/object_detection/**
Have I written custom code (as opposed to using a stock example script provided in TensorFlow):**NO**
…
-
Hi,
i tried to run this code in tensorflow-gpu, but i am facing this issue while execute train command,
(tensor_gpu) C:\Users\admin\Downloads\models\research\object_detection>python train.py -…
-
### Search before asking
- [X] I have searched the YOLOv8 [issues](https://github.com/ultralytics/ultralytics/issues) and [discussions](https://github.com/ultralytics/ultralytics/discussions) and fou…
-
### System information
- **What is the top-level directory of the model you are using**: Object Detection
- **Have I written custom code (as opposed to using a stock example script provided in Tenso…
-
Hello,
thank you very much for the nice work.
I found the GPU utilization ratio is very low, around 10%.
![image](https://github.com/jhb86253817/PIPNet/assets/28244700/f5d6ef24-d0fd-420a-918…
-
My training pipeline is consuming a lot memory when I switch to just different dataset which doesn't make sense. GPU usage should only be impacted by parameters like batch size. On dataset1 it takes …
-
There is a need to be able to compare components that generate the same type of detections. For example, if two components generate `FACE` tracks we need to determine which one is better in terms of p…
-
**Describe the bug**
Detect and inform user about unmet system requirements for running a model, like the 200GB+ RAM for LLama 3.1 405B
`level=WARN source=server.go:136 msg="model request too la…