Fine-grained Dog Classification competition

• This is a dog classification competition held by Baidu. Further information at http://js.baidu.com/

Framework

• Keras
• Tensorflow Backend

Hardware

• Geforce GTX TITANX 12G
• Intel® Core™ i7-6700 CPU
• Memory 16G
• Operate system Ubuntu 14.04

Data

• Download the images from Baidu Cloud
  • Training Set: http://pan.baidu.com/s/1slLOqBz Key: 5axb
  • Test set: http://pan.baidu.com/s/1gfaf9rt Key：fl5n
• Put the images into diffrent directory by their class labels. Refer to altoFolders.py for doing this.
• Take 20% of the labeled data for validation. Refer to divforValidation.py.

Base Model

• VGG19 for deep feature extraction, which is provided in keras models.
• InceptionV3 for deep feature extraction, which is provided in keras models.
• Softmax for classification.

Evaluate

• Predict the classes for unlabeled data one by one refering to predict_onebyone and by generator refering to predict_bygenerator.by.

to be continued

Feel free to contact me if you have any issues or better ideas about anything.

by Holy