Shulou(Shulou.com)06/01 Report--

This article will explain in detail how to analyze the Keras version of the SSD object detection model. The content of the article is of high quality, so the editor shares it for you as a reference. I hope you will have a certain understanding of the relevant knowledge after reading this article.

SSD is an Object Detection method.

The following is the keras version based on the paper SSD: Single Shot MultiBox Detector. In this paper, under the condition of ensuring both speed and accuracy, a SSD object detection model is proposed, which, like the popular detection model, turns the whole detection process into a single deep neural network. It is convenient for training and optimization, and the detection speed is improved at the same time. SSD will output a series of discretization bounding boxes that are generated on feature maps at different levels (layers) and have different aspect ratio.

Detection of vehicle by model

Detection of animals by model

Video Detection of Model

How to use the installation dependency package cv2==3.3.0keras==1.2.2matplotlib==2.1.0tensorflow==1.3.0numpy==1.13.3

If you want to run through the video module, you need extra pip install scikit-video.

Specific operation git clone git@github.com:kuhung/SSD_keras.gitcd SSD_keras

Download the pre-training model

Https://github.com/kuhung/SSD_keras/releases

Copy the pre-training model into SSD_keras

Cp weights_SSD300.hdf5 into SSD_keras

The detection of pictures

Https://github.com/kuhung/SSD_keras/blob/master/SSD.ipynb

To cut the picture in preparation for the next step

Https://github.com/kuhung/SSD_keras/blob/master/SSD_crop.py

Detect video

Cd video_utilspython videotest_example.py hy.mp4 on how to analyze the SSD object detection model Keras version to share here, I hope the above content can be of some help to you, can learn more knowledge. If you think the article is good, you can share it for more people to see.

Welcome to subscribe "Shulou Technology Information " to get latest news, interesting things and hot topics in the IT industry, and controls the hottest and latest Internet news, technology news and IT industry trends.