joelouismarino

from googlenet_custom_layers import PoolHelper, LRN
from keras.models import model_from_json

model = model_from_json(open('googlenet_architecture.json').read(), custom_objects={"PoolHelper": PoolHelper, "LRN": LRN})
model.load_weights('googlenet_weights.h5')

joelouismarino

name: "GoogleNet"
input: "data"
input_dim: 10
input_dim: 3
input_dim: 224
input_dim: 224

joelouismarino

input = Input(shape=(3, 224, 224))

joelouismarino

layer {
    name: "conv1/7x7_s2"
    type: "Convolution"
    bottom: "data"
    top: "conv1/7x7_s2"
    param {
	lr_mult: 1
	decay_mult: 1
    }
    param {

joelouismarino

conv1_7x7_s2 = Convolution2D(64, 7, 7, subsample=(2,2), border_mode='same', activation='relu', name='conv1/7x7_s2')(input)

joelouismarino

layer {
    name: "pool1/3x3_s2"
    type: "Pooling"
    bottom: "conv1/7x7_s2"
    top: "pool1/3x3_s2"
    pooling_param {
	pool: MAX
	kernel_size: 3
	stride: 2
    }

joelouismarino

pool1_3x3_s2 = MaxPooling2D(pool_size=(3, 3), strides=(2, 2), border_mode='valid', name='pool1/3x3_s2')(conv1_7x7_s2)

joelouismarino

conv1_zero_pad = ZeroPadding2D(padding=(1, 1))(conv1_7x7_s2)
pool1_helper = PoolHelper()(conv1_zero_pad)
pool1_3x3_s2 = MaxPooling2D(pool_size=(3, 3), strides=(2, 2), border_mode='valid', name='pool1/3x3_s2')(pool1_helper)

joelouismarino

class PoolHelper(Layer):
    def __init__(self, **kwargs):
	    super(PoolHelper, self).__init__(**kwargs)
    
    def call(self, x, mask=None):
	    return x[:,:,1:,1:]
    
    def get_config(self):
	    config = {}
	    base_config = super(PoolHelper, self).get_config()

joelouismarino

layer {
    name: "pool1/norm1"
    type: "LRN"
    bottom: "pool1/3x3_s2"
    top: "pool1/norm1"
    lrn_param {
	local_size: 5
	alpha: 0.0001
	beta: 0.75
    }