A rookie here. CodeProject AI used to work for me sending MQTT messages about objects and lic. plates. Doesn't work as good as it used to. Misses objects and never recognizes lic plates anymore. I just installed the latest version with the default settings. I noticed that the default installs both YOLO5 and YOLO5.NET. I also have the option to run one of them or both. What should I do? Should I try YOLO8? Do I install and run them both or just one? Which one to choose? Albeit I do run it on quite powerful Intel machine with 12 cores and 16 threads and 64G memory, I do not have GPU. Thanks.
YOLO5 vs YOLO5.NET
- Thread starter risquare
- Start date
MikeLud1
IPCT Contributor
I recommend using just YOLO5.NET, this module will use your iGPU
OakleyFreak
Getting the hang of it
- Joined
- Jun 2, 2016
- Messages
- 56
- Reaction score
- 41
depends on the GPU
From the website
Object Detection (YOLOv5 .NET)
2024-04-01
Installed
MITProvides Object Detection using YOLOv5 ONNX models with DirectML. This module is best for those on Windows and Linux without CUDA enabled GPUs
Project by Matthew Dennis, based on yolov5-net. Uses C#, ONNX, DirectML, YOLO.
So this is for GPU that dosent use CUDA (Cuda Is on most Nviia GPU)
Object Detection (YOLOv5 3.1)
2024-04-01
Installed
GPL-3.0Provides Object Detection using YOLOv5 3.1 targeting CUDA 10 or 11 for older GPUs.
Project by Chris Maunder, Matthew Dennis, based on Deepstack. Uses Python, PyTorch, YOLO.
Object Detection (YOLOv5 6.2)
2024-02-08
Installed
GPL-3.0Provides Object Detection using YOLOv5 6.2 targeting CUDA 11.5+, PyTorch < 2.0 for newer GPUs.
Project by Matthew Dennis, based on Ultralytics YOLOv5.
My latest Upgrade installed all three
Im Looking into what needs uninstalled
Im running a Nvidia GTX 1650
From the website
Object Detection (YOLOv5 .NET)
2024-04-01
Installed
MITProvides Object Detection using YOLOv5 ONNX models with DirectML. This module is best for those on Windows and Linux without CUDA enabled GPUs
Project by Matthew Dennis, based on yolov5-net. Uses C#, ONNX, DirectML, YOLO.
So this is for GPU that dosent use CUDA (Cuda Is on most Nviia GPU)
Object Detection (YOLOv5 3.1)
2024-04-01
Installed
GPL-3.0Provides Object Detection using YOLOv5 3.1 targeting CUDA 10 or 11 for older GPUs.
Project by Chris Maunder, Matthew Dennis, based on Deepstack. Uses Python, PyTorch, YOLO.
Object Detection (YOLOv5 6.2)
2024-02-08
Installed
GPL-3.0Provides Object Detection using YOLOv5 6.2 targeting CUDA 11.5+, PyTorch < 2.0 for newer GPUs.
Project by Matthew Dennis, based on Ultralytics YOLOv5.
My latest Upgrade installed all three
Im Looking into what needs uninstalled
Im running a Nvidia GTX 1650