- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
Hi,
I'm trying stream_infer.py in ncappzoo/apps/stream_infer directory.
It was from https://github.com/movidius/ncappzoo.
After "make run" command, a window came up, but the window with blank had no response and no stream.
Any helpful advices are appreciated.
The message are blow
making squeezenet
...
making prereqs
...
making prototxt
...
making caffemodel
...
making compile
...
making run
python3 stream_infer.py
** (stream_infer.py:2994): WARNING **: Error retrieving accessibility bus address: org.freedesktop.DBus.Error.ServiceUnknown: The name org.a11y.Bus w
as not provided by any .service files
Found stale device, resetting
Device 0 Address: 1.4 - VID/PID 03e7:2150
stream_infer.py:335: DeprecationWarning: Gtk.Widget.set_double_buffered is deprecated
gDrawAreaSink.set_double_buffered(True)
Starting wait for connect with 2000ms timeout
Found Address: 1.4 - VID/PID 03e7:2150
Found EP 0x81 : max packet size is 512 bytes
Found EP 0x01 : max packet size is 512 bytes
Found and opened device
Performing bulk write of 830212 bytes...
Successfully sent 830212 bytes of data in 108.030159 ms (7.328989 MB/s)
Boot successful, device address 1.4
Found Address: 1.4 - VID/PID 03e7:f63b
done
Booted 1.4 -> VSC
My Environment
Raspberry PI3, Raspbian stretch with desktop
Movidius NC SDK version: 1.10.01.00
Raspberry PI Camera
I already checked that camera was working by raspivid and omxplayer command.
And I refered that plugin information
https://github.com/movidius/ncappzoo/blob/master/apps/stream_infer/readme.md
Followings are dpkg results.
ii gstreamer1.0-libav:armhf 1.10.4-1 armhf
ii gstreamer1.0-plugins-bad:armhf 1.10.4-1 armhf GStreamer plugins from the "bad" set
ii gstreamer1.0-plugins-base:armhf 1.10.4-1 armhf GStreamer plugins from the "base" set
ii gstreamer1.0-plugins-good:armhf 1.10.4-1 armhf GStreamer plugins from the "good" set
Thanks,
Link Copied
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
Hi,
Additional information in my environment,
In stream_infer.py, I edited the below from original code for raspberry pi3.
Commented out the 1st line, removed # at the 2nd line.
#SINK_NAME="xvimagesink" # use for x86-64 platforms
SINK_NAME="glimagesink" # use for Raspian Jessie platforms
And I added "bcm2835-v4l2" to /etc/modules with reference to
https://medium.com/@hsheil/movidius-neural-compute-stick-and-raspberry-3-quick-start-guide-a89ff5e1d7ca.
$ more /etc/modules
i2c-dev
bcm2835-v4l2
After reboot, still I have the same situation.
Thank you,
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
You need to use a USB camera. (Very slow on the RPi)
I can't get a USB camera to work with stream_infer.py ether.
I don't think any demos are written for the Raspberry PI Camera.
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
Hi, pkrush
Ok, I'll try to use a USB camera and I'll post the result.
Thank you for your comment.
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
Hi, ps55,
Did you solve the problem? I also meet the same issue.
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
Hi, davidwu0709
I am still having the same problem.
And when I tried the USB camera, I encountered another problem that raspberry pi didn't detected it.
I have two problem now.
Thank you.
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
Dear all,
I just tested stream_infer.py on Raspberry Pi B3+ via ssh and it works really good. Just use
SINK_NAME="ximagesink" # use for Raspian Jessie platforms
instead #SINK_NAME="glimagesink" # use for Raspian Jessie platforms
- Subscribe to RSS Feed
- Mark Topic as New
- Mark Topic as Read
- Float this Topic for Current User
- Bookmark
- Subscribe
- Printer Friendly Page