pinto0309 / mobilenet-ssd Goto Github PK

Hi my friend
I used to tested a model using somebody's trained prototxt and caffemodel caffe model files.. but it skip the detection of the object and even sometimes it does not detect at all. but it worked for the person who provide it with the same video file....
do you think i should have trained (fine tune it)..
so could you show me how should I train the caffe model for a my dataset.
i need to detect a person.....

Traceback (most recent call last):
File "MultiStickSSD.py", line 12, in
import cv2
File "/home/pi/.local/lib/python3.5/site-packages/cv2/init.py", line 3, in
from .cv2 import *
ImportError: libQtGui.so.4: cannot open shared object file: No such file or directory

import cv2 works with python 2 but it doesn't work with python 3.

when i run make install i meet the error of Installation failed: Command 'sudo -H -E pip3 install --trusted-host files.pythonhosted.org Cython graphviz scikit-image' return code=2. Error on line 308 in ./install-utilities.sh. Will exit
i want to know how to solve it

I get my movidius ncs from amazon right now and i need to use it for fast computing ability.
model : ssd mobilenet
framework: caffe

please show me how to get the ncs work with my pi...
I have installed the NCS SDK on my raspberry pi before I received my movidius from amazon carrier using the below link:
dependencies like opencv and tensorflow are also installed by default based on the link:
https://github.com/movidius/ncsdk

What's the speed (FPS) on RaspberryPi3?
Have some Speedup?

Hi Pinto,

Great work!
Looks like Movidius has released a latest NVSDK v2.08.01. I found this version of SDK does not support the graph file included in your repo,
Error messages:

W: [         0] checkGraphMonitorResponse:931	Graph monitor request returned error
W: [         0] ncGraphAllocate:1125	The device didn't accept the graph

W: [         0] ncGraphAllocate:1128	graph file version is incompatible

Traceback (most recent call last):
  File "MultiStickSSD.py", line 44, in <module>
    graphHandle.append(graph[devnum].allocate_with_fifos(devHandle[devnum], graph_buffer))
  File "/home/pi/.local/lib/python3.5/site-packages/mvnc/mvncapi.py", line 613, in allocate_with_fifos
    raise Exception(Status(status))
Exception: Status.UNSUPPORTED_GRAPH_FILE

I tried using the graph file compiled localy from /home/pi/Desktop/ncappzoo/caffe/SSD_MobileNet, however, the detection result is always 1 result with class name tvmonitor and a bounding box of whole frame size.

As you have successfully run the SSD model before, would you please try the latest NVSDK and update this repo if possible?

Thanks!

I think you will be my helper ... please share it to me.....
I transferred a file ( SSD mobilenet model for classification) from my computer to raspberry pi (connected via VNC viewer) and try to execute the model on the RPi python 3 IDE ... but it give nothing like the image below... please let me understand your steps ....