Why it's so slow in real time and I'm using GPU to run the software?
Can you improve the speed of the model

f=tf.gfile.GFile(graph_path, 'rb') #graph_path 我已经修改为我本机上该文件的路径
f.read()

f= tf.gfile.GFile(graph_path, 'rb')
f.read()
Traceback (most recent call last):

File "D:\ProgramData\Anaconda3\lib\site-packages\IPython\core\interactiveshell.py", line 2927, in run_code
self.showtraceback(running_compiled_code=True)

File "D:\ProgramData\Anaconda3\lib\site-packages\IPython\core\interactiveshell.py", line 1833, in showtraceback
self._showtraceback(etype, value, stb)

File "D:\ProgramData\Anaconda3\lib\site-packages\ipykernel\zmqshell.py", line 558, in _showtraceback
dh.parent_header, ident=topic)

File "D:\ProgramData\Anaconda3\lib\site-packages\jupyter_client\session.py", line 737, in send
to_send = self.serialize(msg, ident)

File "D:\ProgramData\Anaconda3\lib\site-packages\jupyter_client\session.py", line 625, in serialize
content = self.pack(content)

File "D:\ProgramData\Anaconda3\lib\site-packages\jupyter_client\session.py", line 103, in
ensure_ascii=False, allow_nan=False,

File "D:\ProgramData\Anaconda3\lib\site-packages\zmq\utils\jsonapi.py", line 43, in dumps
s = s.encode('utf8')

UnicodeEncodeError: 'utf-8' codec can't encode character '\udcd5' in position 1402: surrogates not allowed

Hello, nice work, thanks for sharing.

May I ask how can I train a new action recognition model that can recognize somebody is smoking?somebody is writing on the blackboard and so on.
Could you provide your training code and annotated video sample to have look at the input format.
Thanks a lot. :)

John

Hi, 非常好的项目， 我正在尝试着做一个坐姿头朝前或向左向右三种姿势判断的项目， 目前用三种姿势的骨骼图像训练出来的模型测试效果并不是太理想， 单纯的只想完成上半身头部的一些姿势判断， 现在有些摸不着方向， 能不能给我一些建议，谢谢啦。

这是什么错误啊

您好，我看了您写的代码，我本人也在研究人体异常行为的检测问题。在您写的代码中，我运行了estimator.py这个文件，但是系统却报错了，提示scipy模块导入错误，显示为ImportError: No module named 'numpy.core._multiarray_umath'，所以我想知道您编写代码的时候，用的是scipy的哪一个版本？或者您知道这样的错误应该从哪儿解决吗？十分感谢您的帮助！

Dear author, when I am reproducing your model, after executing run.py, click on the camera, and then set the human body motion recognition. There is no text appearing, only the frame of the line. I would like to ask you if you have any solutions

Hi, thank you for your work it is really interesting! I have a small problem with running the code. Everything works fine but when i press the "Multiple Object Tracking" button to "ON", the program quits with the error:
File "run.py", line 171, in show_camera
show, joints, bboxes, xcenter = TfPoseEstimator.get_skeleton(show, humans, imgcopy=False)
ValueError: too many values to unpack (expected 4)
Abort trap: 6
Any way to resolve this issue?
Thanks!

python main.py
/home/sarthak/anaconda3/lib/python3.7/site-packages/tensorflow/python/framework/dtypes.py:516: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
_np_qint8 = np.dtype([("qint8", np.int8, 1)])
/home/sarthak/anaconda3/lib/python3.7/site-packages/tensorflow/python/framework/dtypes.py:517: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
_np_quint8 = np.dtype([("quint8", np.uint8, 1)])
/home/sarthak/anaconda3/lib/python3.7/site-packages/tensorflow/python/framework/dtypes.py:518: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
_np_qint16 = np.dtype([("qint16", np.int16, 1)])
/home/sarthak/anaconda3/lib/python3.7/site-packages/tensorflow/python/framework/dtypes.py:519: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
_np_quint16 = np.dtype([("quint16", np.uint16, 1)])
/home/sarthak/anaconda3/lib/python3.7/site-packages/tensorflow/python/framework/dtypes.py:520: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
_np_qint32 = np.dtype([("qint32", np.int32, 1)])
/home/sarthak/anaconda3/lib/python3.7/site-packages/tensorflow/python/framework/dtypes.py:525: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
np_resource = np.dtype([("resource", np.ubyte, 1)])
/home/sarthak/anaconda3/lib/python3.7/site-packages/tensorboard/compat/tensorflow_stub/dtypes.py:541: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
_np_qint8 = np.dtype([("qint8", np.int8, 1)])
/home/sarthak/anaconda3/lib/python3.7/site-packages/tensorboard/compat/tensorflow_stub/dtypes.py:542: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
_np_quint8 = np.dtype([("quint8", np.uint8, 1)])
/home/sarthak/anaconda3/lib/python3.7/site-packages/tensorboard/compat/tensorflow_stub/dtypes.py:543: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
_np_qint16 = np.dtype([("qint16", np.int16, 1)])
/home/sarthak/anaconda3/lib/python3.7/site-packages/tensorboard/compat/tensorflow_stub/dtypes.py:544: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
_np_quint16 = np.dtype([("quint16", np.uint16, 1)])
/home/sarthak/anaconda3/lib/python3.7/site-packages/tensorboard/compat/tensorflow_stub/dtypes.py:545: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
_np_qint32 = np.dtype([("qint32", np.int32, 1)])
/home/sarthak/anaconda3/lib/python3.7/site-packages/tensorboard/compat/tensorflow_stub/dtypes.py:550: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
np_resource = np.dtype([("resource", np.ubyte, 1)])
Traceback (most recent call last):
File "main.py", line 6, in
from utils import choose_run_mode, load_pretrain_model, set_video_writer
File "/home/sarthak/Major Project/Online-Realtime-Action-Recognition-based-on-OpenPose/utils.py", line 6, in
from Pose.pose_visualizer import TfPoseVisualizer
File "/home/sarthak/Major Project/Online-Realtime-Action-Recognition-based-on-OpenPose/Pose/pose_visualizer.py", line 6, in
from .pose_estimator import estimate
File "/home/sarthak/Major Project/Online-Realtime-Action-Recognition-based-on-OpenPose/Pose/pose_estimator.py", line 21, in
'coord1', 'coord2', 'score1', 'score2'], verbose=False)
TypeError: namedtuple() got an unexpected keyword argument 'verbose'

你好，

请问在 move_status( action.py) 里的h1,h2,ty 等等代表着什么意思？？ （比如 xc 和 yc 是代表格子的长和宽？？h1 是人的高度/ ratio？？ 如何得到那些比较大小的数字？ ）
如果能明白这些，那就可以用来辨别更多动作。（比如我需要辨别倒下的动作。）

另外， 如果说我想辨别 举手的动作， 请问我可不可以用手肘的点高于肩膀（或和头的点并行）来进行判断？？ (看了其他回复，但还是不明白， 对不起）

真心希望你能帮忙， 谢谢。

请问一下每个数据集您采集了多少张图片？

Hi

Can you please tell me how to fetch the coordinates of each joint especially the coordinates of Right Wrist and Left Wrist of our hands.

Regards
Akhil

Hi Without modifying your code I just compiled it but getting this error.
Any help will be appreciated.(tensorflow_p36) ubuntu@ip-172-31-62-23:~/Real-Time-Action-Recognition$ python run.py
/home/ubuntu/anaconda3/envs/tensorflow_p36/lib/python3.6/site-packages/h5py/init.py:36: FutureWarning: Conversion of the second argument of issubdtype from float to np.floating is deprecated. In future, it will be treated as np.float64 == np.dtype(float).type.
from ._conv import register_converters as _register_converters
Traceback (most recent call last):
File "run.py", line 5, in
from utils.sort import Sort
File "/home/ubuntu/Real-Time-Action-Recognition/utils/init.py", line 1, in
from . import processing
ImportError: cannot import name 'processing'

Hi

While compiling the program I am facing this below issue:

Traceback (most recent call last):
File "run.py", line 3, in
from PyQt5 import QtCore, QtGui, QtWidgets
ImportError: /usr/local/lib/python3.5/dist-packages/PyQt5/QtCore.so: undefined symbol: PySlice_AdjustIndices

This issue is also reproducible with the simple QT application as well.
Can you please guide me here

Thanks in Advance !!!!!

Regards
Akhil

你好，感谢您的分享，我在实验中发现您使用的tf_pose中的thin模型，不知道有没有常识cmu原来的模型进行行为识别，如果我需要改成那个的话，不知道需要在您的基础上怎么修改，希望得到您的指教 @TianzhongSong

@TianzhongSong
你好，我想问一下身体那18个点对应关系是什么样的？谢谢了！

你好，action部分的代码原理能解释一下吗，还有根据关键点做动作识别方面有没有什么简单，效果还说得过去的模型，想做个这方面的简单应用~

Can you please share weights_c3d_mask.h5 and weights_SSD300.h5?

Dears, can you please share the way or source of the dataset

你好，之前价格Issues你说是通过动作模板来匹配识别是哪个动作，那请问下这个动作模板是如何设计的？可以自定义模板让系统识别更多的动作吗？

Hi

I am trying few things for the action recognition for my academic purpose and my area of study is 3DCNN and in your old branch code you have used the 3DCNN as well.

I have one Query which file I should run to execute the source code (There is no run.py file)

Thanks in Advance !!!!!

Regards
Akhil

Traceback (most recent call last):
File "/usr/local/lib/python3.6/dist-packages/tensorflow/python/pywrap_tensorflow.py", line 41, in
from tensorflow.python.pywrap_tensorflow_internal import *
File "/usr/local/lib/python3.6/dist-packages/tensorflow/python/pywrap_tensorflow_internal.py", line 28, in
_pywrap_tensorflow_internal = swig_import_helper()
File "/usr/local/lib/python3.6/dist-packages/tensorflow/python/pywrap_tensorflow_internal.py", line 24, in swig_import_helper
_mod = imp.load_module('_pywrap_tensorflow_internal', fp, pathname, description)
File "/usr/lib/python3.6/imp.py", line 243, in load_module
return load_dynamic(name, filename, file)
File "/usr/lib/python3.6/imp.py", line 343, in load_dynamic
return _load(spec)
ImportError: libcusolver.so.8.0: cannot open shared object file: No such file or directory

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File "run.py", line 3, in
from pose.estimator import TfPoseEstimator
File "/content/Real-Time-Action-Recognition/pose/estimator.py", line 8, in
import tensorflow as tf
File "/usr/local/lib/python3.6/dist-packages/tensorflow/init.py", line 24, in
from tensorflow.python import *
File "/usr/local/lib/python3.6/dist-packages/tensorflow/python/init.py", line 49, in
from tensorflow.python import pywrap_tensorflow
File "/usr/local/lib/python3.6/dist-packages/tensorflow/python/pywrap_tensorflow.py", line 52, in
raise ImportError(msg)
ImportError: Traceback (most recent call last):
File "/usr/local/lib/python3.6/dist-packages/tensorflow/python/pywrap_tensorflow.py", line 41, in
from tensorflow.python.pywrap_tensorflow_internal import *
File "/usr/local/lib/python3.6/dist-packages/tensorflow/python/pywrap_tensorflow_internal.py", line 28, in
_pywrap_tensorflow_internal = swig_import_helper()
File "/usr/local/lib/python3.6/dist-packages/tensorflow/python/pywrap_tensorflow_internal.py", line 24, in swig_import_helper
_mod = imp.load_module('_pywrap_tensorflow_internal', fp, pathname, description)
File "/usr/lib/python3.6/imp.py", line 243, in load_module
return load_dynamic(name, filename, file)
File "/usr/lib/python3.6/imp.py", line 343, in load_dynamic
return _load(spec)
ImportError: libcusolver.so.8.0: cannot open shared object file: No such file or directory

Failed to load the native TensorFlow runtime.

See https://www.tensorflow.org/install/install_sources#common_installation_problems

for some common reasons and solutions. Include the entire stack trace
above this error message when asking for help.

大神 你好：
我运行 Python run.py的时候 模式一 “当前为人体姿态估计模式” 功能正常

但是，运行功能三的时候 ，相机能够打开，但是一旦检测到人物 就错误提示：

Traceback (most recent call last):
File "run.py", line 231, in show_camera
xmin = int(d[0])
ValueError: cannot convert float NaN to integer
Aborted (core dumped)

我将trackers输出得到：

trackers= [[nan nan nan nan 1.]]

我以为是numpy转换出了问题， 我就手动转换 加了一句：trackers = np.nan_to_num(trackers)
这下相机能够打开，功能三也不卡核，但是也没有结果，我输出了一些参数：

检测到人的情况：
trackers= []
show= <type 'numpy.ndarray'>
humans= [<pose.estimator.Human instance at 0x7f67df2fa0e0>]
bboxes= [[0.0, 0.0, 0.0, 0.0, 0.9999]]
trackers= []
show= <type 'numpy.ndarray'>
humans= [<pose.estimator.Human instance at 0x7f67df2fa4d0>]
bboxes= [[0.0, 0.0, 0.0, 0.0, 0.9999]]
trackers= []
show= <type 'numpy.ndarray'>
humans= [<pose.estimator.Human instance at 0x7f67df2fa2d8>]
bboxes= [[0.0, 0.0, 0.0, 0.0, 0.9999]]
trackers= []

没有检测到人的情况：
humans= []
bboxes= []
show= <type 'numpy.ndarray'>
humans= []
bboxes= []
show= <type 'numpy.ndarray'>
humans= []
bboxes= []
show= <type 'numpy.ndarray'>
humans= []
bboxes= []
show= <type 'numpy.ndarray'>
humans= []

结果就是空值，请大神指点，不胜感激

Thanks for nice work . I am doing same type of action recognition but my classes are different. I have four classes "waving" ,"clapping" and pointing . I have 300 videos for every class . Can u guide me and tell me the exact process of training of my own custom data to this technique . Thanks

你好！
你的工作非常有意义！ 我现在也想做这方面的研究，我现在已经可以通过网络定位出图片中人体骨骼点的位置。但是在视屏中如何认别出动作，比如站起/走开/坐下？我就没什么思路了。所以想请你指导下！
谢谢！

Hi, when I use 行为识别, I got an error, below

/home/wade/Desktop/Real-Time-Action-Recognition/utils/sort.py:37: RuntimeWarning: invalid value encountered in double_scalars
r = w / float(h)
('trackers', array([[nan, nan, nan, nan, 1.]]))
Traceback (most recent call last):
File "run.py", line 218, in show_camera
xmin = int(d[0])
ValueError: cannot convert float NaN to integer
Aborted (core dumped)

Could you help, please

hi guys,
when i run run.py, this issue:
Traceback (most recent call last):
File "run.py", line 258, in show_camera
self.fps = 0 / (end - start)
ZeroDivisionError: float division by zero

and it's crashed python.

Anyone. Can you help me? thanks

能不能提供一下您现在的 weights_c3d_mask.h5和cnn_2d_crop.h5，所找的数据集有点不太行，如果可以的话请发到[email protected]邮箱，谢谢