I have implemented a multi-label image classification model where I can choose which model to use, I was surprised to find out that in my case mobilenet_v1_224 performed much better (95% Accuracy) than the inception models (around 88% Accuracy), I'm using pretrained models (that I download from here and adding a final layer that I train on my own data (3000 images). I wanted to get your opinion and see if maybe I'm doing something wrong.


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.