Giters

perseus784 / BvS

An Image classifier to identify whether the given image is Batman or Superman using a CNN with high accuracy. (From getting images from google to saving our trained model for reuse.)

Home Page:https://medium.com/@ipaar3/how-i-built-a-convolutional-image-classifier-using-tensorflow-from-scratch-f852c34e1c95

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

One image class

tentenponce opened this issue · comments

commented

I've tried this but I have only 1 class of image. When I run the trainer.py, the loss always giving me 0. Is this still applicable if I have only 1 class of image?

commented

if it only has one class, then what do you want to classify at all?

commented

It seems that I misunderstood how Image Classifiers work, it requires to have atleast 2 class to identify which is which. What I actually want is similarity percentage of the image base on the image registered on the model. For my use case, I want to identify a certain ID, I achieve it by training it with two classes. First class is the specific ID that I want to recognize, and the second class were just random IDs.