geaxgx / tello-openpose Goto Github PK
View Code? Open in Web Editor NEWLicense: MIT License
License: MIT License
Hi,
I've changed the Openpose wrapper to work with a lighter pose estimation framework which can run on smaller GPUs and also supports CPU using OpenVINO toolkit. A lot of work still remains but would love to know your thoughts on this.
The repo is available here: https://github.com/katphlab/tello-openpose
Thanks :)
First of all to be frank i became fan of your work on tello openpose .Sir i had been working for past four weeks to install tello openpose and make it work on tello ubuntu 18.04 but getting errors and i referred issues posted in the repository still i was not able to solve it.
please provide video for installation of your openpose layer and installation of all dependancies and eveything required to implement on tello drone please sir
thank you sir
Running in Ubuntu 18.04, I am getting the below flood of messages. I have uninstalled and reinstalled 'av' as well as ffmpeg. Are you seeing the same? It does work, the video is just has artifacts off and on.
Auto-detecting all available GPUs... Detected 1 GPU(s), using 1 of them starting at GPU 0.
error while decoding MB 52 42, bytestream -6
error while decoding MB 52 25, bytestream -8
error while decoding MB 46 42, bytestream -7
error while decoding MB 37 14, bytestream -10
error while decoding MB 6 15, bytestream -6
error while decoding MB 1 26, bytestream -12
error while decoding MB 1 26, bytestream -8
...
error while decoding MB 6 35, bytestream -6
error while decoding MB 26 42, bytestream -10
error while decoding MB 24 42, bytestream -6
error while decoding MB 59 14, bytestream -6
error while decoding MB 5 14, bytestream -6
error while decoding MB 7 14, bytestream -12
error while decoding MB 50 13, bytestream -12
error while decoding MB 26 14, bytestream -10
Tello: 11:46:10.644: Info: video data 375640 bytes 183.2KB/sec loss=-5
0x77@0x77mac ~/tello-openpose> python3 tello_openpose.py
objc[1633]: Class CaptureDelegate is implemented in both /usr/local/lib/python3.7/site-packages/cv2/cv2.cpython-37m-darwin.so (0x11cecd6a8) and /usr/local/opt/opencv/lib/libopencv_videoio.4.1.dylib (0x126c9d920). One of the two will be used. Which one is undefined.
objc[1633]: Class SDLTranslatorResponder is implemented in both /usr/local/opt/sdl2/lib/libSDL2-2.0.0.dylib (0x117e3b258) and /usr/local/lib/python3.7/site-packages/pygame/.dylibs/libSDL-1.2.0.dylib (0x12a381680). One of the two will be used. Which one is undefined.
pygame 1.9.6
Hello from the pygame community. https://www.pygame.org/contribute.html
Traceback (most recent call last):
File "tello_openpose.py", line 1004, in <module>
main(use_multiprocessing=args.multiprocess, log_level=args.log_level)
File "tello_openpose.py", line 127, in main
log_level=log_level, child_cnx=child_cnx)
File "tello_openpose.py", line 212, in __init__
self.drone = tellopy.Tello(start_recv_thread=not self.use_multiprocessing)
TypeError: __init__() got an unexpected keyword argument 'start_recv_thread'
0x77@0x77mac ~/tello-openpose>
Hi, I finally managed to run tello_openpose.py only in CPU only mode on macOS High Sierra. I was not able to compile with CUDA and cudNN because of Caffe.
My terminal shows lots of these:
Tello: 16:27:55.145: Info: video data 378945 bytes 182.2KB/sec
The problem is I don't see any window with the stream nor the pose recognition.
Even tried taking off with the morse code trick. Tello just stands there.
Am I missing something?
Thanks for this great project.
Hello!
Can you explain how you calculated x,y,z pos in this code please?
` def log_data_handler(self, event, sender, data):
"""
Listener to log data from the drone.
"""
global sensors
sensors = data
pos_x = -data.mvo.pos_x
pos_y = -data.mvo.pos_y
pos_z = -data.mvo.pos_z
if abs(pos_x) + abs(pos_y) + abs(pos_z) > 0.07:
if self.ref_pos_x == -1: # First time we have meaningful values, we store them as reference
self.ref_pos_x = pos_x
self.ref_pos_y = pos_y
self.ref_pos_z = pos_z
else:
self.pos_x = pos_x - self.ref_pos_x
self.pos_y = pos_y - self.ref_pos_y
self.pos_z = pos_z - self.ref_pos_z
qx = data.imu.q1
qy = data.imu.q2
qz = data.imu.q3
qw = data.imu.q0
self.yaw = quarter_to_yaw_deg(qx, qy, qz, qw)`
I don't really understand what you did in this part.
Thank you and best regards.
cpu?gpu ?memory size?
I have completely rewritten this project focusing on simplicity. Everything should work out of the box.
Replaced Openpose by MediaPipe
Removed multiprocessing support
Replaced pynput by pygame
Added Path mapping
Hello
Thank you for this tutorial !
I am thinking about buying a Tello Drone
Do I need to buy the standard or the Edu version for Posenet ?
Thanks
File "C:/Users/Ricardo/PycharmProjects/Tello/OPenpose.py", line 354
log.debug(f'special key {keyname0} pressed')
^
SyntaxError: invalid syntax
this happens when I try to run tello_openpose.py
and also cannot find reference from multiprocessing import sharedctypes
if I remove the f prefix, Will the code still work?
Please, could you help me to setup this code? im new in face recognition and I was very impressed about your project.
Hello. I am trying to run the OP.py file to test out openpose and keep getting an error. I have correctly installed Openpose and have tested it on my computer. I made sure BUILD_PYTHON was enabled and still am getting this error. I believe the error has to do with the file path I am using, however, I'm not sure what the correct path would be. Currently, my tello-openpose-master folder is located in the same folder as my openpose-master folder: D:\Dev. This is the error I am getting:
D:\Dev\Python\python.exe D:/Dev/tello-openpose-master/OP.py
Error: OpenPose library could not be found. Did you enable BUILD_PYTHON
in CMake and have this Python script in the right folder?
Traceback (most recent call last):
File "D:/Dev/tello-openpose-master/OP.py", line 33, in
raise e
File "D:/Dev/tello-openpose-master/OP.py", line 24, in
import pyopenpose as op
ModuleNotFoundError: No module named 'pyopenpose'
Process finished with exit code 1
Any help would be appreciated. Thank you!
I have testing your op.py using webcam.
After program start the screen is just black and freeze.
I have successfully installed open pose and tested webcam another python program.
Any help would be appreciated.
Thank you.
Hello! I wonder if you could provide instructions or code of how to get the multithreaded version to work. Currently openpose is capped at a FPS of around 10 with a RTX 2070 and is barely unusable. Thank you!
I got errors when I try to test OP.py
The error I get is:
Traceback (most recent call last):
File "OP.py", line 454, in
nb_persons,body_kps,face_kps = my_op.eval(frame)
File "OP.py", line 215, in eval
self.opWrapper.emplaceAndPop([self.datum])
TypeError: emplaceAndPop(): incompatible function arguments. The following argument types are supported:
1. (self: openpose.pyopenpose.WrapperPython, arg0: std::vector<std::shared_ptrop::Datum, std::allocator<std::shared_ptrop::Datum > >) -> bool
Invoked with: <openpose.pyopenpose.WrapperPython object at 0x7f86d8a14ed8>, [<openpose.pyopenpose.Datum object at 0x7f86d8a14f10>]
Did you forget to#include <pybind11/stl.h>
? Or <pybind11/complex.h>,
<pybind11/functional.h>, <pybind11/chrono.h>, etc. Some automatic
conversions are optional and require extra headers to be included
when compiling your pybind11 module.
How can I resolve this?
Hello!
Can you explain how you calculated x,y,z pos in this code please?
if abs(pos_x) + abs(pos_y) + abs(pos_z) > 0.07: if self.ref_pos_x == -1: # First time we have meaningful values, we store them as reference self.ref_pos_x = pos_x self.ref_pos_y = pos_y self.ref_pos_z = pos_z else: self.pos_x = pos_x - self.ref_pos_x self.pos_y = pos_y - self.ref_pos_y self.pos_z = pos_z - self.ref_pos_z
I don't really understand what you did in this part.
Thank you and best regards.
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.