Baliapa Lakshmana et al.: Practical Machine Learning for Computer Vision
[Student] - [Gloria] No, no, no. Machine-driving for computer vision is a practical book that uses machine-mode models to show how to extract information from images. Machine-ming engineers and data scientists can learn to solve various image problems, such as image groupings, object detection, Autoincoders, images, coefficients, and captions by using proven ML techniques. From the making of data sets to all sorts of processes: pre-handling, model design, training, testing, distribution, interpretation, and a great introduction to deep-downing. The three authors of Google, using the hard-core ML architecture in a flexible and sustainable way, show how to develop accurate and explain computer vision ML models and put them into large productions. The reader can learn to design, train, test and predict with a model written in Tensaple and Kerras. The book is about to cover: design ML architecture for computer vision tasks. Select models suitable for task. Models such as resnet, squeamnet, efficents, and effoditnet. Create an entire ML pipeline that trains, verifys, distributes and explains the data before the image. Improves the potential of learning. The possible and responsible AI model. The best example is the ability to distribute the image to web service models or the device to monitors and monitors the MLML.
Korean title: 실전! 컴퓨터비전을 위한 머신러닝
Korean author: 발리아파 락슈마난 외
Korean publisher: 위키북스
ISBN-13: 9791158394417












