Project Report: A Dog Breed Classifier

A Dog Breed Classifier

Setting

• Jupyter Notebook
• Keras

Model

• ResNet50

Implementation

• normalization
  • the mean pixel must be subtracted from every pixel in each image
• keras.applications.resnet50
  • ResNet50
  • preprocess_input  (source)
    • input: a tensor
    • return: Preprocessed tensor
• numpy.argmax
  • By taking the argmax of the predicted probability vector, we obtain an integer corresponding to the model's predicted object class, which we can identify with an object category through the use of the dictionary.
• keras.layers
  • Conv2D
    • keras.layers.Conv2D(filters, kernel_size, strides=(1, 1), padding='valid', data_format=None, dilation_rate=(1, 1), activation=None, use_bias=True, kernel_initializer='glorot_uniform', bias_initializer='zeros', kernel_regularizer=None, bias_regularizer=None, activity_regularizer=None, kernel_constraint=None, bias_constraint=None)
    • When using this layer as the first layer in a model, provide the keyword argument input_shape (tuple of integers, does not include the sample axis), e.g. input_shape=(128, 128, 3) for 128x128 RGB pictures in  data_format="channels_last".
  • MaxPooling2D
  • GlobalAveragePooling2D