Poiščite in štejte predmete z zaznavanjem predmetov

Ta vzorec kode je del Kako začeti z IBM Maximo Visual Inspection učna pot.

Povzetek

Object detection has different uses and different opportunities than image classification. This code pattern demonstrates how to use IBM Maximo Visual Inspection Object Detection to detect and label objects within an image (in this case, Coca-Cola products), based on customized training. You can then easily customize this initial data set example with your own data sets-without writing any code.

Opis

Imagine that you’re a supplier of an item (such as a soft drink) and you want to know how many bottles there are on a store’s shelf. You can build an app that helps you do just that. IBM Maximo Visual Inspection uses deep learning to create trained models based on images that you upload and label. You don’t need to write any code to train, deploy, and test a new object detection model. You simply upload the images, use your mouse to label the objects in your images, and then let IBM Maximo Visual Inspection do the learning.

S tem vzorcem boste uporabili usposabljanje za globoko učenje, da ustvarite model za zaznavanje predmetov. Z le nekaj kliki lahko usposobite in uvedete model. Ko usposobite in uvedete model, vam končna točka REST omogoča lociranje in štetje elementov na sliki. Vzorec kode vključuje vzorčni nabor podatkov, ki vam bo v pomoč pri izdelavi detektorja steklenic kokakole, vendar lahko uporabite svoje primere in zaznate druge predmete.

IBM Maximo Visual Inspection presents REST APIs for inference operations. You can use any REST client for object detection with your custom model, and you can use IBM Maximo Visual Inspection UI to test it. This example includes an example Node.js app that demonstrates how to upload an image and then draw the image with labels and bounding boxes around detected objects.

Ko dokončate ta vzorec kode, bi morali vedeti, kako:

• Create a data set for object detection with IBM Maximo Visual Inspection
• Usposobite in uvedite model na podlagi nabora podatkov
• Testirajte model s klici REST

Pretok

1. Upload the images to create an IBM Maximo Visual Inspection data set.
2. Označite predmete v naboru slikovnih podatkov pred treningom.
3. Train, deploy, and test the model in IBM Maximo Visual Inspection.
4. Uporabite odjemalca REST za zaznavanje predmetov na slikah.

navodila

Poiščite podrobne korake za ta vzorec v README. Ti koraki vam bodo pokazali, kako:

1. Klonirajte repo powerai-vision-object-detection GitHub.
2. Prijavite se v IBM Maximo Visual Inspection.
3. Ustvarite nov nabor podatkov za usposabljanje za odkrivanje predmetov.
4. Ustvarite oznake za predmete usposabljanja in jih označite.
5. Ustvari nalogo DL.
6. Namestite in preizkusite model.
7. Zaženite aplikacijo.

zaključek

This code pattern demonstrated how to use IBM Maximo Visual Inspection Object Detection to detect and label objects within an image based on customized training. The code pattern is part of the Kako začeti z IBM Maximo Visual Inspection učna pot. Če želite nadaljevati niz in izvedeti več o funkcijah IBM Maximo Visual Inspection, si oglejte naslednji vzorec kode, Sledenje predmetom v videu z OpenCV in Deep Learning.

Vir: https://developer.ibm.com/patterns/locate-and-count-items-with-object-detection/