I’m using the local code editing feature of an object detection project (ID 271840) on a Windows 10 machine. I ran the training function and obtained a detection model in .h5 format. When I try to detect an image, I perform all the preprocessing steps: I resize it to 1x96x96x3 and convert it to float32. In the prediction result, I obtained an array of 1x12x12x6. However, the first value is always 1, and the subsequent values are very small, in the order of e-13/e-14. I’m having difficulty interpreting this result, can you assist me? Is this the correct format? How should I analyze it?
hey guys, I found the solution:
Good job @hellen.ancelmo and thanks for posting the solution. Can be of help to others!