From the course: GeoAI in ArcGIS Pro and Survey123
Unlock this course with a free trial
Join today to access over 25,300 courses taught by industry experts.
Export your deep learning model for analysis - ArcGIS Pro Tutorial
From the course: GeoAI in ArcGIS Pro and Survey123
Export your deep learning model for analysis
Now, let's export our digitized cars to set up our model. In the image classification pane on the right, let's go ahead and undock that so that you can see it clearly. There we go. And now we've saved our image chips already. And here we have to select export training data. It's complicated and often confusing for my students, so let me practically break down what's happening with each of these parameters so you make good decisions on your AI workflows. The output path is going to be your working folder for your project. If you need to change that, you can. Here, under Image Format, typically I'm going to just choose a TIFF since it's a lossless format, but you can adjust it as well. Tile size X and Y refer to the pixel size of the image chips that are created. Bigger chips reflect bigger digitized features. So, I've seen some examples of 400 and 512, but typically I've accepted 256. Honestly, it's a parameter you can adjust, but when we build the model in a bit, multiple models will…
Practice while you learn with exercise files
Download the files the instructor uses to teach the course. Follow along and learn by watching, listening and practicing.
Contents
-
-
-
-
-
(Locked)
AutoDL training with Label Objects for deep learning models4m 16s
-
(Locked)
Export your deep learning model for analysis3m 34s
-
(Locked)
Train your own AI object detection model2m 59s
-
(Locked)
Neural network deep learning model output check3m 27s
-
(Locked)
Solution: Train and find parking lot cars5m 21s
-
(Locked)
-
-