TensorFlow-Lite-Object-Detection-on-Android-and-Raspberry-Pi
TensorFlow-Lite-Object-Detection-on-Android-and-Raspberry-Pi copied to clipboard
Error: Corrupt JPEG data
trafficstars
I tried to follow your explanation for setting up the Raspberry Pi with a USB-Webcam and I think it works out well. But it works only when I use the sample TFLite model. If I use my own tensorflow lite model (trained with TF Model Maker) the window for the video stream will not open up. For both of the TFLite models however I get thousands of lines with "Corrupt JPEG data: 1 extraneous bytes before marker". What did I do wrong?