DEEP LEARNING MODELS OF THE MANIPULATOR ON THE RASPBERRY PI PLATFORM FOR OBJECTS FINDING

Dmytro Myroniuk, Bohdan Blagitko

Abstract


This article analyzed basic concepts of convolutional neural network construction. The modern deep learning architectures for solving image classification tasks describes. The prototype manipulator for the object finding realizes by using the Raspberry Pi 4 platform and TFLite framework. The garbage-finding manipulator prototype realizes.

Keywords: convolutional neural networks, deep learning, modeling, image classification.


Full Text:

PDF

References


  1. Ian Goodfellow, Yoshua Bengio, Aaron Courville. Deep Learning. An MIT Press Book //Ian Goodfellow, Yoshua Bengio, Aaron Courville. - MIT Press, 2016. - 716 p.
  2. Benchmark Analysis of Representative Deep Neural Network Architectures. Retrieved from:https://www.groundai.com/project/benchmark-analysis-of-representative-deep-neural-network-architectures/1
  3. TensorFlow Lite guide. Retrieved from: https://www.tensorflow.org/lite/guide
  4. Post-training quantization. Retrieved from: https://www.tensorflow.org/lite/performance/post_training_quantization
  5. Ufactory Offical Website. Retrieved from: https://www.ufactory.cc/#/en/support/download/products.
  6. Custom Electronics Robo-arm. Retrieved from: http://www.customelectronics.ru/robo-ruka-chast-1-opisanye/.
  7. COCO – Common Objects in Context. Retrieved from: http://cocodataset.org/#home
  8. Simply explain YOLOv5. Retrieved from: https://www.programmersought.com/article/20545272716/
  9. Raspberry Pi 4 Model B. Retrieved from https://www.raspberrypi.org/products/raspberry-pi-4-model-b/
  10. MobileNet Review. Retrieved from:https://lixinso.medium.com/mobilenet-c08928f2dba7




DOI: http://dx.doi.org/10.30970/eli.18.1

Refbacks

  • There are currently no refbacks.