FPS measurement.

[hiiksu]

❔Question

Hello, I am a student who is conducting research using your model. I'm curious about how to measure my custom data FPS regarding the study.
Is there a separate program? Or is there a way to measure it right away in "frompt"? I'll be waiting for the reply. Thank you.

Additional context

[glenn-jocher]

@hiiksu good news 😃! Your original issue may now be fixed ✅ in PR #4741. This PR updates detect.py timing to allow for simpler FPS. Simply divide 1000ms by the inference speed shown to arrive at a mean FPS for all images/frames run. Below for example 1000ms / 215ms = 4.7 FPS.

$ python detect.py
YOLOv5 🚀 v5.0-419-gc5360f6 torch 1.9.0 CPU

Fusing layers... 
Model Summary: 224 layers, 7266973 parameters, 0 gradients
image 1/2 /Users/glennjocher/PycharmProjects/yolov5/data/images/bus.jpg: 640x480 4 persons, 1 bus, 1 fire hydrant, Done. (0.240s)
image 2/2 /Users/glennjocher/PycharmProjects/yolov5/data/images/zidane.jpg: 384x640 2 persons, 2 ties, Done. (0.191s)
Speed: 1.1ms pre-process, 215.5ms inference, 1.1ms NMS per image at shape (1, 3, 640, 640)  <------- NEW
Results saved to runs/detect/exp12

To receive this update:

• Git – git pull from within your yolov5/ directory or git clone https://github.com/ultralytics/yolov5 again
• PyTorch Hub – Force-reload with model = torch.hub.load('ultralytics/yolov5', 'yolov5s', force_reload=True)
• Notebooks – View updated notebooks
• Docker – sudo docker pull ultralytics/yolov5:latest to update your image

Thank you for spotting this issue and informing us of the problem. Please let us know if this update resolves the issue for you, and feel free to inform us of any other issues you discover or feature requests that come to mind. Happy trainings with YOLOv5 🚀!