Object Detection with OpenCV, Tensorflow Hub & Python | #pyguru смотреть онлайн

In this tutorial we will be learning how to implement a simple object detection tool in Google colab. For this we will be using the following libraries : opencv, Tensorflow, tensorflow_hub, pandas, numpy, matplotlib. We will be learning object detection workflow along with detecting a number of objects in several images.

We are going to use a model from the Tensorflow Hub library, which has multiple ready to deploy models trained in all kinds of datasets and to solve all kinds of problems. For our use, I filtered models trained for object detection tasks and models in the TFLite format. The chosen model was the EfficientDet-Lite2 Object detection model. It was trained on the COCO17 dataset with 91 different labels and optimized for the TFLite application.

This model returns:
1 - The box boundaries of the detection
2 - The detection scores (probabilities of a given class)
3 - The detection classes
4 - The number of detections.

Download model : https://tfhub.dev/tensorflow/efficientdet/lite2/detection/1

Download labels csv : https://drive.google.com/file/d/10wXjxb7MTOD-flZW7ux182ntAiBklG3C/view?usp=drivesdk

Colab Notebook link : https://colab.research.google.com/drive/1ttK0K16Njo-8q_m4Svdq12wQ7YN3wJeE

All resources used in this tutorial : https://drive.google.com/folderview?id=1FwDFHGt-yBUtLIL427cu7KEW3KZWjqnF


The original source of this tutorial is taken from a article written by Gabriel Cassimiro, you can read the article here : https://towardsdatascience.com/object-detection-with-tensorflow-model-and-opencv-d839f3e42849

#python #opencv #tensorflow #tensorflowhub #objectdetection #numpy #colab #coco17 #iot #tensors #pandas #classification
#pythonguru python guru