GithubHelp home page GithubHelp logo

Comments (4)

Sqeak avatar Sqeak commented on August 15, 2024 1

Thank you! My picamera eventually arrived in the mail and everything worked flawlessly!

from ml-examples.

Sqeak avatar Sqeak commented on August 15, 2024

And is there a way i can remove the TensorFlow errors, I've tried other versions but they don't work

from ml-examples.

mark-arm avatar mark-arm commented on August 15, 2024

Easy things first: the TensorFlow warnings are just future compatibility warnings and can be ignored. If you want them to go away you can modify the lines of code referred to as described, e.g. change tf.Session to tf.compat.v1.Session and so on.

The error in preprocessing the image suggests the changes you made to use a USB webcam are not producing the same kind of output as is expected. I suggest printing out one of the frames and/or its shape and checking that it really is an array of width x height x depth. The fact that record.py runs without error is misleading - it just saves the data to a file, it doesn't care whether it is in the right format or not.

from ml-examples.

ZissisT avatar ZissisT commented on August 15, 2024

I had the same and just disabled V2 behavior in pinet.py:

import tensorflow.compat.v1 as tf
tf.disable_v2_behavior()

For webcam to work I had to change code like this in record.py:

#from camera import Camera
import cv2

def main():
.
.
    camera = cv2.VideoCapture(0)
    camera.set(cv2.CAP_PROP_FPS, 30)
    record(camera, name, seconds)
.
.
.
.
def record(camera, filename, seconds):
        ret, frame = camera.read()
        if ret == False:
            print("Failed to retrieve frame")
            break 
        frame = cv2.flip(frame, 1)
        frame = cv2.rotate(frame, cv2.ROTATE_90_COUNTERCLOCKWISE)
        frame = cv2.resize(frame, (128, 128), interpolation = cv2.INTER_AREA)
        frames.append(frame)
.
.
    dump(frames, open(filename, 'wb'), protocol=2)
    camera.release() 
    cv2.destroyAllWindows()
    print('done.')
.
.

throws some deprecation warnings, but works for me. Hope it helps others who want to use webcam with newer tf installed in a device other than Pi.

from ml-examples.

Related Issues (20)

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.