Do you have a class list that this project is capable of processing?

Traceback (most recent call last):
File "eval.py", line 123, in
tf.flags.DEFINE_string('video', 0, 'Path to the video file.')
File "/home/abhayjeet/.local/lib/python2.7/site-packages/tensorflow/python/platform/flags.py", line 58, in wrapper
return original_function(*args, **kwargs)
File "/home/abhayjeet/.local/lib/python2.7/site-packages/absl/flags/_defines.py", line 241, in DEFINE_string
DEFINE(parser, name, default, help, flag_values, serializer, **args)
File "/home/abhayjeet/.local/lib/python2.7/site-packages/absl/flags/_defines.py", line 81, in DEFINE
DEFINE_flag(_flag.Flag(parser, serializer, name, default, help, **args),
File "/home/abhayjeet/.local/lib/python2.7/site-packages/absl/flags/_flag.py", line 107, in init
self._set_default(default)
File "/home/abhayjeet/.local/lib/python2.7/site-packages/absl/flags/_flag.py", line 196, in _set_default
self.default = self._parse(value)
File "/home/abhayjeet/.local/lib/python2.7/site-packages/absl/flags/_flag.py", line 169, in _parse
'flag --%s=%s: %s' % (self.name, argument, e))
absl.flags._exceptions.IllegalFlagValueError: flag --video=0: flag value must be a string, found "<type 'int'>"

Installed all the requirements.
Using tensorflow-gpu 1.7.0
cuda 9.0

Hi
And thanks for this repo.

I got it to work "OUT OF THE BOX" with tensorflow cpu 1.4.0 in the requirements.txt.
But it does not work with any other cpu version of tensorflow nor 1.4.0-gpu or any other gpu version.
Tried hard in the last couple days (even installed ubuntu more than 10 times breaking and starting all over again) but no success so far. only TF1.4.0 cpu.
Other examples i use works flawlessly with my GPU. GTX1080.

Any idea why and how to fix this excellent example code to work with gpu even newer version of tensorflow?

10X
--{-@

$ python3 eval.py --video="aab.mp4"

** (Detector:2966): WARNING **: Error retrieving accessibility bus address: org.freedesktop.DBus.Error.ServiceUnknown: The name org.a11y.Bus was not provided by any .service files
terminate called after throwing an instance of 'std::bad_alloc'
what(): std::bad_alloc
Aborted

$python3 daemon.py
[INFO] 2018-05-13 17:50:24,420: Start camera loop
terminate called after throwing an instance of 'std::bad_alloc'
what(): std::bad_alloc
Aborted

$python3
Python 3.5.3
[GCC 6.3.0 20170124] on linux

import tensorflow
import cv2
tensorflow.version
'1.4.0'
cv2.version
'3.4.0'

It runs well in most part, but it fails at this part.
When I run the command below,
$ pip install -e git://github.com/devicehive/devicehive-python-webconfig.git@a792db1babcedb5baa68ec6ba6ebcf0041f20469#egg=devicehive_webconfig

I get

Obtaining devicehive_webconfig from git+git://github.com/devicehive/devicehive-python-webconfig.git@a792db1babcedb5baa68ec6ba6ebcf0041f20469#egg=devicehive_webconfig
Updating /home/david/.virtualenvs/tf-yolo-demo/src/devicehive-webconfig clone (to revision a792db1babcedb5baa68ec6ba6ebcf0041f20469)
fatal: Could not parse object 'a792db1babcedb5baa68ec6ba6ebcf0041f20469'.
Command "git reset --hard -q a792db1babcedb5baa68ec6ba6ebcf0041f20469" failed with error code 128 in /home/david/.virtualenvs/tf-yolo-demo/src/devicehive-webconfig

$ git reset --hard -q a792db1babcedb5baa68ec6ba6ebcf0041f20469

fatal: Could not parse object 'a792db1babcedb5baa68ec6ba6ebcf0041f20469'.

When running the code in TF1.5+ there is an error in eval.py in line 123 caused by the function DEFINE_string.

Hello,

Thank you very much for the wonderful work. I have a question: If I run this demo inside docker container, can I get the output in with web interface outside with http://127.0.0.1:8000/events/

I tried, but does not work. I am not sure what to do to make it work.

Best,
Fayzur

I have managed to run the eval.py with YouTube video, but it is quite slow. The video is not playing at the same speed like in YouTube.

I'm using Google Cloud Platform with 2 GPUs

How can I make it faster?

What changes are needed in code to use Yolo3 ?
Yolo3 weight url - https://pjreddie.com/media/files/yolov3.weights

When trying to evaluate any local video saved in my Downloads, I get this error:

OpenCV: Couldn't read video stream from file "~/Downloads/tf_traffic.mp4" Traceback (most recent call last): File "eval.py", line 126, in <module> tf.app.run(main=evaluate) File "/Users/ruhi/anaconda3/lib/python3.6/site-packages/tensorflow/python/platform/app.py", line 48, in run: _sys.exit(main(_sys.argv[:1] + flags_passthrough)) File "eval.py", line 44, in evaluate: raise IOError('Can\'t open "{}"'.format(FLAGS.video)) OSError: Can't open "~/Downloads/tf_traffic.mp4 "

I have ensure all dependencies are correctly installed and my file path is correct.

Firstly, thanks a lot for your tutorial and code. It works perfectly!

And when reading your code, I found your comment in models/yolo.py:

We can merge normalization with other OPs, but we need to redefine input tensor for this.

So I would like to know whether you have any idea on how to do that?

I am now trying to export your version of YOLO from TF to TF-Serving, and if I chose self._raw_inp as input to export, then it will report Invalid argument: You must feed a value for placeholder tensor 'evaluation/input' with dtype float and shape [1,608,608,3] error. So instead, I exported self._eval_inp, and re-wrote the normalization part in numpy. It worked, but as you mentioned, it will be faster if we use tf's API to do the normalization. So I wonder whether you have any idea on how to merge normalization and postprocess in your _evaluate() in models/yolo.py.

Thanks! :-)

Hi,
thanks for the tutorial!

When I start python daemon.py I get the following error:
Traceback (most recent call last):
File "daemon.py", line 25, in
from web.routes import routes
ImportError: No module named web.routes

Do you have an idea what the problem is? Which package shall I install?

Of course, there are still many videos I haven't tried yet, but I couldn't get any successful result so far.
I ran
pip install -r requirements.txt
with modified requirements.txt (due to this issue)

-e git://github.com/devicehive/devicehive-python-webconfig.git#egg=devicehive_webconfig

then,
python eval.py --video="https://youtube_url"

Traceback (most recent call last):
File "eval.py", line 129, in
tf.app.run(main=evaluate)
File "~/.virtualenvs/tf-yolo-demo/lib/python3.6/site-packages/tensorflow/python/platform/app.py", line 48, in run
_sys.exit(main(_sys.argv[:1] + flags_passthrough))
File "eval.py", line 47, in evaluate
raise IOError('Can't open "{}"'.format(FLAGS.video))
OSError: Can't open "https://youtube_url"

Hello,

i get a Problem when i run the Code on an Ubuntu Server 18.04.
When i use: python eval.py –video="https://www.youtube.com/watch?v=hfeNyZV6Dsk"

i get this Error: : cannot connect to X server

Whats the Problem for it?

Can we use this to train model to identify custom objects from images or video?