joelouismarino

class LRN(Layer):
    def __init__(self, alpha=0.0001,k=1,beta=0.75,n=5, **kwargs):
      self.alpha = alpha
      self.k = k
      self.beta = beta
      self.n = n
      super(LRN, self).__init__(**kwargs)
    
    def call(self, x, mask=None):
      b, ch, r, c = x.shape

joelouismarino

pool1_norm1 = LRN(name='pool1/norm1')(pool1_3x3_s2)

joelouismarino

inception_3a_1x1 = Convolution2D(64,1,1, border_mode='same', activation='relu', name='inception_3a/1x1')(pool2_3x3_s2)
inception_3a_3x3_reduce = Convolution2D(96,1,1, border_mode='same', activation='relu', name='inception_3a/3x3_reduce')(pool2_3x3_s2)
inception_3a_3x3 = Convolution2D(128,3,3, border_mode='same', activation='relu', name='inception_3a/3x3')(inception_3a_3x3_reduce)
inception_3a_5x5_reduce = Convolution2D(16,1,1, border_mode='same', activation='relu', name='inception_3a/5x5_reduce')(pool2_3x3_s2)
inception_3a_5x5 = Convolution2D(32,5,5, border_mode='same', activation='relu', name='inception_3a/5x5')(inception_3a_5x5_reduce)
inception_3a_pool = MaxPooling2D(pool_size=(3,3), strides=(1,1), border_mode='same', name='inception_3a/pool')(pool2_3x3_s2)
inception_3a_pool_proj = Convolution2D(32,1,1, border_mode='same', activation='relu', name='inception_3a/pool_proj')(inception_3a_pool)
inception_3a_output = merge([inception_3a_1x1, inception_3a_3x3, inception_3a_5x5, inception_3a_pool_proj], mode='con

joelouismarino

layer {
	name: "pool5/7x7_s1"
	type: "Pooling"
	bottom: "inception_5b/output"
	top: "pool5/7x7_s1"
	pooling_param {
		pool: AVE
		kernel_size: 7
		stride: 1
	}

joelouismarino

pool5_7x7_s1 = AveragePooling2D(pool_size=(7,7), strides=(1,1), name='pool5/7x7_s2')(inception_5b_output)

joelouismarino

layer {
	name: "pool5/drop_7x7_s1"
	type: "Dropout"
	bottom: "pool5/7x7_s1"
	top: "pool5/7x7_s1"
	dropout_param {
		dropout_ratio: 0.4
	}
}

joelouismarino

loss3_flat = Flatten()(pool5_7x7_s1)
pool5_drop_7x7_s1 = Dropout(0.4, name='pool5/drop_7x7_s1')(loss3_flat)

joelouismarino

layer {
    name: "loss3/classifier"
    type: "InnerProduct"
    bottom: "pool5/7x7_s1"
    top: "loss3/classifier"
    param {
	lr_mult: 1
	decay_mult: 1
    }
    param {

joelouismarino

loss3_classifier = Dense(1000, name='loss3/classifier')(pool5_drop_7x7_s1)
loss3_classifier_act = Activation('softmax', name='prob')(loss3_classifier)

joelouismarino

googlenet = Model(input=input, output=[loss1_classifier_act, loss2_classifier_act, loss3_classifier_act])