datitran / object_detector_app

Real-Time Object Recognition App with Tensorflow and OpenCV

Home Page:https://medium.com/towards-data-science/building-a-real-time-object-recognition-app-with-tensorflow-and-opencv-b7a2b4ebdc32

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Why the fps isn't improve

Wangzishenz opened this issue · comments

Hi:
I have download your project in June,and then run it in my computer and get the fps of 2.2. Today I have find that you update it in Aug 17 and note with "Change folder structure, finish the multithreading example to improve fps on low performance machines ". So I run the new project ,but the fps is also 2.2. Is there something else I could do to improve fps or something wrong what I do? I run this command: $ python object_detection_multithreading.py --source=0

Hi,
I have run the new project ,and the fps has improved 2.2 to 9.41.
I have studing how is the multithreading working.
We can communicate with each other.@Wangzishenz

Hi,
Could you tell me what have you do with this project? Have you changed something? And how can I contact with you @liuqy1994

Hello @Wangzishenz , @liuqy1994 and @datitran

What was the outcome of your exchange regarding fps performance?

@Wangzishenz, what is your setup?
I see from what you have shared that you are achieving ~9fps

Did you conclude on a way to improve the fps?

For my part, I'm running in the following environment:

Windows 10
Python 3.6
OPENCV 3.4 (compiled from source) with CUDA enabled
Tensorflow 1.5 compiled from source with CUDA 9 
NVIDIA 1030 GTX GPU
Lenovo i5 laptop T410 with eGPU as above

I'm seeing the following fps

object_detection_multithreading.py
source 1
width 640
height 480

2018-02-05 18:30:18.754829: I C:\tf_jenkins\workspace\rel-win\M\windows-gpu\PY\36\tensorflow\core\common_runtime\gpu\gpu_device.cc:1105] Found device 0 with properties: 
name: GeForce GT 1030 major: 6 minor: 1 memoryClockRate(GHz): 1.468
pciBusID: 0000:05:00.0
totalMemory: 2.00GiB freeMemory: 1.63GiB
2018-02-05 18:30:18.755763: I C:\tf_jenkins\workspace\rel-win\M\windows-gpu\PY\36\tensorflow\core\common_runtime\gpu\gpu_device.cc:1195] Creating TensorFlow device (/device:GPU:0) -> (device: 0, name: GeForce GT 1030, pci bus id: 0000:05:00.0, compute capability: 6.1)

[INFO] elapsed time (total): 597.08
[INFO] approx. FPS: 2.16 

Is this to be expected with my particular GPU compute?