Giter Site home page Giter Site logo

chonyy / ai-basketball-analysis Goto Github PK

View Code? Open in Web Editor NEW
926.0 36.0 176.0 292.04 MB

:basketball::robot::basketball: AI web app and API to analyze basketball shots and shooting pose.

Home Page: https://ai-basketball-analysis.herokuapp.com/

License: Other

Python 51.48% CSS 13.44% HTML 29.35% Batchfile 3.11% Shell 2.62%
basketball machine-learning tensorflow api computer-vision object-detection artificial-intelligence openpose deep-learning pose-estimation

ai-basketball-analysis's Introduction

ai-basketball-analysis's People

Contributors

anurag-chauhan-289 avatar chonyy avatar dependabot[bot] avatar zames-chang avatar

Stargazers

 avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar

Watchers

 avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar

ai-basketball-analysis's Issues

Problem in running !python app.py

I followed every steps. Run each cell one by one. In between i got stuck where !ldconfig threw an error of libmkldnn.so.0 is not a symbolic link. So I deleted libmkldnn.so.0.14.0 and then it was fine. Now I got stuck at the last script. It is throwing new errors after resolving some import issues. Kindly revert back.
Thanks.

In windows 10 64 bit os : problem with OpenPose

Error: OpenPose library could not be found. Did you enable BUILD_PYTHON in CMake and have this Python script in the right folder?
Debugging middleware caught exception in streamed response at a point where response headers were already sent.
Traceback (most recent call last):
File "C:\WORKSP1\python\CONDA\BASKET1\AI-BAS1\venv\lib\site-packages\werkzeug\wsgi.py", line 506, in next
return self._next()
File "C:\WORKSP
1\python\CONDA\BASKET1\AI-BAS1\venv\lib\site-packages\werkzeug\wrappers\base_response.py", line 45, in _iter_encoded
for item in iterable:
File "C:\Workspace\python\CONDA\Basketball_shooting_pose\AI-basketball-analysis\src\app_helper.py", line 19, in getVideoStream
datum, opWrapper = openpose_init()
File "C:\Workspace\python\CONDA\Basketball_shooting_pose\AI-basketball-analysis\src\utils.py", line 47, in openpose_init
raise e
File "C:\Workspace\python\CONDA\Basketball_shooting_pose\AI-basketball-analysis\src\utils.py", line 39, in openpose_init
import OpenPose.Release.pyopenpose as op
ModuleNotFoundError: No module named 'OpenPose.Release.pyopenpose'

Too slow on web server

Since Fast RCNN is a very CPU-bound object detection model, it loop over all sub image to find out possible. Although it does a lot optimization like Dynamic Programming. It still not a good fit on real time object detection.

I recommend you to use yolo4. I is the fastest object detection right now If I am not wrong.

There is python API in file darknet.py. Since I don't have datasets for training, I cannot help you to training deep learning model. Sorry~

Dataset

I wonder if you will be publishing your dataset for detection. Thanks. Impressive work by the way!

erro: import OpenPose.Release.pyopenpose as op ImportError: DLL load failed:

How to solve the following problems:
Traceback (most recent call last):
File "D:\Miniconda3\envs\TF-openpose\lib\site-packages\werkzeug\wsgi.py", line 462, in next
return self._next()
File "D:\Miniconda3\envs\TF-openpose\lib\site-packages\werkzeug\wrappers\response.py", line 50, in _iter_encoded
for item in iterable:
File "D:\pycharm\PythonProject\AI-basketball\src\app_helper.py", line 19, in getVideoStream
datum, opWrapper = openpose_init()
File "D:\pycharm\PythonProject\AI-basketball\src\utils.py", line 46, in openpose_init
raise e
File "D:\pycharm\PythonProject\AI-basketball\src\utils.py", line 38, in openpose_init
import OpenPose.Release.pyopenpose as op
ImportError: DLL load failed: 找不到指定的模块。
I would greatly appreciate it if you could provide some suggestions

Facing some errors and dont konw how to solve it

Error in atexit._run_exitfuncs:
Traceback (most recent call last):
File "C:\Users\Andre Wen\Desktop\AI-basketball-analysis-master\envir3.9\lib\site-packages\matplotlib_pylab_helpers.py", line 82, in destroy_all
manager.destroy()
File "C:\Users\Andre Wen\Desktop\AI-basketball-analysis-master\envir3.9\lib\site-packages\matplotlib\backends_backend_tk.py", line 569, in destroy
self._window_dpi.trace_remove('write', self.window_dpi_cbname)
File "D:\Lib\tkinter_init
.py", line 427, in trace_remove
self._tk.call('trace', 'remove', 'variable',
RuntimeError: main thread is not in main loop
2023-03-08 12:48:27.611651: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1532] Created device /job:localhost/replica:0/task:0/device:GPU:0 with 2211 MB memory: -> device: 0, name: NVIDIA GeForce GTX 1660 Ti, pci bus id: 0000:01:00.0, compute capability: 7.5

  • Restarting with watchdog (windowsapi)

ERROR: Unable to extract uploader id;

Attempting to run the project on the Colab website, but i receive the following an error during the following step:

Download the above youtube video, cut the first 5 seconds and do the pose detection on that 5 seconds:
image

Something went wrong while importing Openpose

While performing analysis on Video, I run into the following error. The app works with the pictures, the following problem arises only when video is selected.

Something went wrong when importing OpenPose
Debugging middleware caught exception in streamed response at a point where response headers were already sent.
Traceback (most recent call last):
File "C:\Users\Devil\AppData\Roaming\Python\Python37\site-packages\werkzeug\wsgi.py", line 506, in next
return self._next()
File "C:\Users\Devil\AppData\Roaming\Python\Python37\site-packages\werkzeug\wrappers\base_response.py", line 45, in _iter_encoded
for item in iterable:
File "D:\GritFeat\CV\AI-basketball-analysis-master\src\app_helper.py", line 19, in getVideoStream
datum, opWrapper = openpose_init()
File "D:\GritFeat\CV\AI-basketball-analysis-master\src\utils.py", line 47, in openpose_init
raise e
File "D:\GritFeat\CV\AI-basketball-analysis-master\src\utils.py", line 39, in openpose_init
import OpenPose.Release.pyopenpose as op
ModuleNotFoundError: No module named 'OpenPose.Release.pyopenpose'

Video and camera characteristics

Hi,
Which camera do you suggest to buy to record the videos ?
Can you suggest me the ideal characteristics for the video to be analyzed? For example frame per second and dimension.

I tried with 120 frames but the analysis is very slow, It is faster with 30 frame/s.

Thanks a lot and congratulations for the excellent work.

BR
/Tony

I can't run this file

I'm sorry to bother you.
when I execute this file,It doesn't work.
I can open web pages and upload video files,but it donsen't work.
When I upload image,it feedback an error to me like"AttributeError: 'NoneType' object has no attribute 'shape'"

I'm sorry but I have to learn from this archive:(

非常感謝您

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.