DeepLogo's training/testing performance on the given database?

[tianqig]

This is a very interesting project on logo recognition based deep learning. It would be great if author can include the classification results on the given logo image datasets.

Thanks

[satojkovic]

@tianqig

Thank you for the comment.
Here is the train and test results of flickr logo dataset.

Minibatch loss at step 10000: 25.272474
Minibatch accuracy: 98.4%                               
Validation accuracy: 94.7%                              
Test accuracy: 94.9%                                    
Model saved in file: models/deep_logo_model 

[tianqig]

@satojkovic

Great to know the good performance. Congratulations to you! I will take a close look.

[satojkovic]

@tianqig

Thank you so much!!