def __init__(self, num_classes=1000):
super(AlexNet, self).__init__()
self.features = nn.Sequential(
nn.Conv2d(3, 96, kernel_size=11, stride=4, padding=0),
nn.ReLU(inplace=True),
LRN(local_size=5, alpha=0.0001, beta=0.75),
nn.MaxPool2d(kernel_size=3, stride=2),
nn.Conv2d(96, 256, kernel_size=5, padding=2, groups=2),
nn.ReLU(inplace=True),
LRN(local_size=5, alpha=0.0001, beta=0.75),
nn.MaxPool2d(kernel_size=3, stride=2),
nn.Conv2d(256, 384, kernel_size=3, padding=1),
nn.ReLU(inplace=True),
nn.Conv2d(384, 384, kernel_size=3, padding=1, groups=2),
nn.ReLU(inplace=True),
nn.Conv2d(384, 256, kernel_size=3, padding=1, groups=2),
nn.ReLU(inplace=True),
nn.MaxPool2d(kernel_size=3, stride=2),
)
self.classifier = nn.Sequential(
nn.Linear(256 * 5 * 5, 4096),
nn.ReLU(inplace=True),
nn.Dropout(),
nn.Linear(4096, 4096),
nn.ReLU(inplace=True),
nn.Dropout(),
nn.Linear(4096, num_classes),
)
def handle_concat(spec, bottoms):
local_size = spec.lrn_param.local_size
alpha = spec.lrn_param.alpha
beta = spec.lrn_param.beta
return LRN(alpha=alpha,
beta=beta,
n=local_size,
name=spec.name,
data_format='channels_first')(bottoms)
def make_layers(cfg, batch_norm=False):
layers = []
inchannels = 3
print(cfg)
for v in cfg:
if v == 'M':
layers += [nn.MaxPool2d(kernel_size=2, stride=2)]
elif v == 'L':
layers += [LRN(local_size=5, alpha=0.0001, beta=0.75)]
else:
f = int(v.split('_')[0])
s = int(v.split('_')[1])
if batch_norm:
if f is 1:
layers += [conv1x1(inchannels, s), nn.BatchNorm2d(s), nn.ReLU(inplace = True)]
else:
layers += [conv3x3(inchannels, s), nn.BatchNorm2d(s), nn.ReLU(inplace=True)]
else:
if f is 1:
layers += [conv1x1(inchannels, s), nn.ReLU(inplace = True)]
else:
layers += [conv3x3(inchannels, s), nn.ReLU(inplace=True)]
inchannels = s
return nn.Sequential(*layers)
def create_googlenet(weights_path=None):
# creates GoogLeNet a.k.a. Inception v1 (Szegedy, 2015)
input = Input(shape=(3, 224, 224))
input_pad = ZeroPadding2D(padding=(3, 3))(input)
conv1_7x7_s2 = Conv2D(64, (7, 7),
strides=(2, 2),
padding='valid',
activation='relu',
name='conv1/7x7_s2',
kernel_regularizer=l2(0.0002))(input_pad)
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),
padding='valid',
name='pool1/3x3_s2')(pool1_helper)
pool1_norm1 = LRN(name='pool1/norm1')(pool1_3x3_s2)
conv2_3x3_reduce = Conv2D(64, (1, 1),
padding='same',
activation='relu',
name='conv2/3x3_reduce',
kernel_regularizer=l2(0.0002))(pool1_norm1)
conv2_3x3 = Conv2D(192, (3, 3),
padding='same',
activation='relu',
name='conv2/3x3',
kernel_regularizer=l2(0.0002))(conv2_3x3_reduce)
conv2_norm2 = LRN(name='conv2/norm2')(conv2_3x3)
conv2_zero_pad = ZeroPadding2D(padding=(1, 1))(conv2_norm2)
pool2_helper = PoolHelper()(conv2_zero_pad)
pool2_3x3_s2 = MaxPooling2D(pool_size=(3, 3),
strides=(2, 2),
padding='valid',
name='pool2/3x3_s2')(pool2_helper)
inception_3a_1x1 = Conv2D(64, (1, 1),
padding='same',
activation='relu',
name='inception_3a/1x1',
kernel_regularizer=l2(0.0002))(pool2_3x3_s2)
inception_3a_3x3_reduce = Conv2D(
96, (1, 1),
padding='same',
activation='relu',
name='inception_3a/3x3_reduce',
kernel_regularizer=l2(0.0002))(pool2_3x3_s2)
inception_3a_3x3_pad = ZeroPadding2D(padding=(1,
1))(inception_3a_3x3_reduce)
inception_3a_3x3 = Conv2D(
128, (3, 3),
padding='valid',
activation='relu',
name='inception_3a/3x3',
kernel_regularizer=l2(0.0002))(inception_3a_3x3_pad)
inception_3a_5x5_reduce = Conv2D(
16, (1, 1),
padding='same',
activation='relu',
name='inception_3a/5x5_reduce',
kernel_regularizer=l2(0.0002))(pool2_3x3_s2)
inception_3a_5x5_pad = ZeroPadding2D(padding=(2,
2))(inception_3a_5x5_reduce)
inception_3a_5x5 = Conv2D(
32, (5, 5),
padding='valid',
activation='relu',
name='inception_3a/5x5',
kernel_regularizer=l2(0.0002))(inception_3a_5x5_pad)
inception_3a_pool = MaxPooling2D(pool_size=(3, 3),
strides=(1, 1),
padding='same',
name='inception_3a/pool')(pool2_3x3_s2)
inception_3a_pool_proj = Conv2D(
32, (1, 1),
padding='same',
activation='relu',
name='inception_3a/pool_proj',
kernel_regularizer=l2(0.0002))(inception_3a_pool)
inception_3a_output = Concatenate(axis=1, name='inception_3a/output')([
inception_3a_1x1, inception_3a_3x3, inception_3a_5x5,
inception_3a_pool_proj
])
inception_3b_1x1 = Conv2D(
128, (1, 1),
padding='same',
activation='relu',
name='inception_3b/1x1',
kernel_regularizer=l2(0.0002))(inception_3a_output)
inception_3b_3x3_reduce = Conv2D(
128, (1, 1),
padding='same',
activation='relu',
name='inception_3b/3x3_reduce',
kernel_regularizer=l2(0.0002))(inception_3a_output)
inception_3b_3x3_pad = ZeroPadding2D(padding=(1,
1))(inception_3b_3x3_reduce)
inception_3b_3x3 = Conv2D(
192, (3, 3),
padding='valid',
activation='relu',
name='inception_3b/3x3',
kernel_regularizer=l2(0.0002))(inception_3b_3x3_pad)
inception_3b_5x5_reduce = Conv2D(
32, (1, 1),
padding='same',
activation='relu',
name='inception_3b/5x5_reduce',
kernel_regularizer=l2(0.0002))(inception_3a_output)
inception_3b_5x5_pad = ZeroPadding2D(padding=(2,
2))(inception_3b_5x5_reduce)
inception_3b_5x5 = Conv2D(
96, (5, 5),
padding='valid',
activation='relu',
name='inception_3b/5x5',
kernel_regularizer=l2(0.0002))(inception_3b_5x5_pad)
inception_3b_pool = MaxPooling2D(
pool_size=(3, 3),
strides=(1, 1),
padding='same',
name='inception_3b/pool')(inception_3a_output)
inception_3b_pool_proj = Conv2D(
64, (1, 1),
padding='same',
activation='relu',
name='inception_3b/pool_proj',
kernel_regularizer=l2(0.0002))(inception_3b_pool)
inception_3b_output = Concatenate(axis=1, name='inception_3b/output')([
inception_3b_1x1, inception_3b_3x3, inception_3b_5x5,
inception_3b_pool_proj
])
inception_3b_output_zero_pad = ZeroPadding2D(
padding=(1, 1))(inception_3b_output)
pool3_helper = PoolHelper()(inception_3b_output_zero_pad)
pool3_3x3_s2 = MaxPooling2D(pool_size=(3, 3),
strides=(2, 2),
padding='valid',
name='pool3/3x3_s2')(pool3_helper)
inception_4a_1x1 = Conv2D(192, (1, 1),
padding='same',
activation='relu',
name='inception_4a/1x1',
kernel_regularizer=l2(0.0002))(pool3_3x3_s2)
inception_4a_3x3_reduce = Conv2D(
96, (1, 1),
padding='same',
activation='relu',
name='inception_4a/3x3_reduce',
kernel_regularizer=l2(0.0002))(pool3_3x3_s2)
inception_4a_3x3_pad = ZeroPadding2D(padding=(1,
1))(inception_4a_3x3_reduce)
inception_4a_3x3 = Conv2D(
208, (3, 3),
padding='valid',
activation='relu',
name='inception_4a/3x3',
kernel_regularizer=l2(0.0002))(inception_4a_3x3_pad)
inception_4a_5x5_reduce = Conv2D(
16, (1, 1),
padding='same',
activation='relu',
name='inception_4a/5x5_reduce',
kernel_regularizer=l2(0.0002))(pool3_3x3_s2)
inception_4a_5x5_pad = ZeroPadding2D(padding=(2,
2))(inception_4a_5x5_reduce)
inception_4a_5x5 = Conv2D(
48, (5, 5),
padding='valid',
activation='relu',
name='inception_4a/5x5',
kernel_regularizer=l2(0.0002))(inception_4a_5x5_pad)
inception_4a_pool = MaxPooling2D(pool_size=(3, 3),
strides=(1, 1),
padding='same',
name='inception_4a/pool')(pool3_3x3_s2)
inception_4a_pool_proj = Conv2D(
64, (1, 1),
padding='same',
activation='relu',
name='inception_4a/pool_proj',
kernel_regularizer=l2(0.0002))(inception_4a_pool)
inception_4a_output = Concatenate(axis=1, name='inception_4a/output')([
inception_4a_1x1, inception_4a_3x3, inception_4a_5x5,
inception_4a_pool_proj
])
loss1_ave_pool = AveragePooling2D(
pool_size=(5, 5), strides=(3, 3),
name='loss1/ave_pool')(inception_4a_output)
loss1_conv = Conv2D(128, (1, 1),
padding='same',
activation='relu',
name='loss1/conv',
kernel_regularizer=l2(0.0002))(loss1_ave_pool)
loss1_flat = Flatten()(loss1_conv)
loss1_fc = Dense(1024,
activation='relu',
name='loss1/fc',
kernel_regularizer=l2(0.0002))(loss1_flat)
loss1_drop_fc = Dropout(rate=0.7)(loss1_fc)
loss1_classifier = Dense(1000,
name='loss1/classifier',
kernel_regularizer=l2(0.0002))(loss1_drop_fc)
loss1_classifier_act = Activation('softmax')(loss1_classifier)
inception_4b_1x1 = Conv2D(
160, (1, 1),
padding='same',
activation='relu',
name='inception_4b/1x1',
kernel_regularizer=l2(0.0002))(inception_4a_output)
inception_4b_3x3_reduce = Conv2D(
112, (1, 1),
padding='same',
activation='relu',
name='inception_4b/3x3_reduce',
kernel_regularizer=l2(0.0002))(inception_4a_output)
inception_4b_3x3_pad = ZeroPadding2D(padding=(1,
1))(inception_4b_3x3_reduce)
inception_4b_3x3 = Conv2D(
224, (3, 3),
padding='valid',
activation='relu',
name='inception_4b/3x3',
kernel_regularizer=l2(0.0002))(inception_4b_3x3_pad)
inception_4b_5x5_reduce = Conv2D(
24, (1, 1),
padding='same',
activation='relu',
name='inception_4b/5x5_reduce',
kernel_regularizer=l2(0.0002))(inception_4a_output)
inception_4b_5x5_pad = ZeroPadding2D(padding=(2,
2))(inception_4b_5x5_reduce)
inception_4b_5x5 = Conv2D(
64, (5, 5),
padding='valid',
activation='relu',
name='inception_4b/5x5',
kernel_regularizer=l2(0.0002))(inception_4b_5x5_pad)
inception_4b_pool = MaxPooling2D(
pool_size=(3, 3),
strides=(1, 1),
padding='same',
name='inception_4b/pool')(inception_4a_output)
inception_4b_pool_proj = Conv2D(
64, (1, 1),
padding='same',
activation='relu',
name='inception_4b/pool_proj',
kernel_regularizer=l2(0.0002))(inception_4b_pool)
inception_4b_output = Concatenate(axis=1, name='inception_4b/output')([
inception_4b_1x1, inception_4b_3x3, inception_4b_5x5,
inception_4b_pool_proj
])
inception_4c_1x1 = Conv2D(
128, (1, 1),
padding='same',
activation='relu',
name='inception_4c/1x1',
kernel_regularizer=l2(0.0002))(inception_4b_output)
inception_4c_3x3_reduce = Conv2D(
128, (1, 1),
padding='same',
activation='relu',
name='inception_4c/3x3_reduce',
kernel_regularizer=l2(0.0002))(inception_4b_output)
inception_4c_3x3_pad = ZeroPadding2D(padding=(1,
1))(inception_4c_3x3_reduce)
inception_4c_3x3 = Conv2D(
256, (3, 3),
padding='valid',
activation='relu',
name='inception_4c/3x3',
kernel_regularizer=l2(0.0002))(inception_4c_3x3_pad)
inception_4c_5x5_reduce = Conv2D(
24, (1, 1),
padding='same',
activation='relu',
name='inception_4c/5x5_reduce',
kernel_regularizer=l2(0.0002))(inception_4b_output)
inception_4c_5x5_pad = ZeroPadding2D(padding=(2,
2))(inception_4c_5x5_reduce)
inception_4c_5x5 = Conv2D(
64, (5, 5),
padding='valid',
activation='relu',
name='inception_4c/5x5',
kernel_regularizer=l2(0.0002))(inception_4c_5x5_pad)
inception_4c_pool = MaxPooling2D(
pool_size=(3, 3),
strides=(1, 1),
padding='same',
name='inception_4c/pool')(inception_4b_output)
inception_4c_pool_proj = Conv2D(
64, (1, 1),
padding='same',
activation='relu',
name='inception_4c/pool_proj',
kernel_regularizer=l2(0.0002))(inception_4c_pool)
inception_4c_output = Concatenate(axis=1, name='inception_4c/output')([
inception_4c_1x1, inception_4c_3x3, inception_4c_5x5,
inception_4c_pool_proj
])
inception_4d_1x1 = Conv2D(
112, (1, 1),
padding='same',
activation='relu',
name='inception_4d/1x1',
kernel_regularizer=l2(0.0002))(inception_4c_output)
inception_4d_3x3_reduce = Conv2D(
144, (1, 1),
padding='same',
activation='relu',
name='inception_4d/3x3_reduce',
kernel_regularizer=l2(0.0002))(inception_4c_output)
inception_4d_3x3_pad = ZeroPadding2D(padding=(1,
1))(inception_4d_3x3_reduce)
inception_4d_3x3 = Conv2D(
288, (3, 3),
padding='valid',
activation='relu',
name='inception_4d/3x3',
kernel_regularizer=l2(0.0002))(inception_4d_3x3_pad)
inception_4d_5x5_reduce = Conv2D(
32, (1, 1),
padding='same',
activation='relu',
name='inception_4d/5x5_reduce',
kernel_regularizer=l2(0.0002))(inception_4c_output)
inception_4d_5x5_pad = ZeroPadding2D(padding=(2,
2))(inception_4d_5x5_reduce)
inception_4d_5x5 = Conv2D(
64, (5, 5),
padding='valid',
activation='relu',
name='inception_4d/5x5',
kernel_regularizer=l2(0.0002))(inception_4d_5x5_pad)
inception_4d_pool = MaxPooling2D(
pool_size=(3, 3),
strides=(1, 1),
padding='same',
name='inception_4d/pool')(inception_4c_output)
inception_4d_pool_proj = Conv2D(
64, (1, 1),
padding='same',
activation='relu',
name='inception_4d/pool_proj',
kernel_regularizer=l2(0.0002))(inception_4d_pool)
inception_4d_output = Concatenate(axis=1, name='inception_4d/output')([
inception_4d_1x1, inception_4d_3x3, inception_4d_5x5,
inception_4d_pool_proj
])
loss2_ave_pool = AveragePooling2D(
pool_size=(5, 5), strides=(3, 3),
name='loss2/ave_pool')(inception_4d_output)
loss2_conv = Conv2D(128, (1, 1),
padding='same',
activation='relu',
name='loss2/conv',
kernel_regularizer=l2(0.0002))(loss2_ave_pool)
loss2_flat = Flatten()(loss2_conv)
loss2_fc = Dense(1024,
activation='relu',
name='loss2/fc',
kernel_regularizer=l2(0.0002))(loss2_flat)
loss2_drop_fc = Dropout(rate=0.7)(loss2_fc)
loss2_classifier = Dense(1000,
name='loss2/classifier',
kernel_regularizer=l2(0.0002))(loss2_drop_fc)
loss2_classifier_act = Activation('softmax')(loss2_classifier)
inception_4e_1x1 = Conv2D(
256, (1, 1),
padding='same',
activation='relu',
name='inception_4e/1x1',
kernel_regularizer=l2(0.0002))(inception_4d_output)
inception_4e_3x3_reduce = Conv2D(
160, (1, 1),
padding='same',
activation='relu',
name='inception_4e/3x3_reduce',
kernel_regularizer=l2(0.0002))(inception_4d_output)
inception_4e_3x3_pad = ZeroPadding2D(padding=(1,
1))(inception_4e_3x3_reduce)
inception_4e_3x3 = Conv2D(
320, (3, 3),
padding='valid',
activation='relu',
name='inception_4e/3x3',
kernel_regularizer=l2(0.0002))(inception_4e_3x3_pad)
inception_4e_5x5_reduce = Conv2D(
32, (1, 1),
padding='same',
activation='relu',
name='inception_4e/5x5_reduce',
kernel_regularizer=l2(0.0002))(inception_4d_output)
inception_4e_5x5_pad = ZeroPadding2D(padding=(2,
2))(inception_4e_5x5_reduce)
inception_4e_5x5 = Conv2D(
128, (5, 5),
padding='valid',
activation='relu',
name='inception_4e/5x5',
kernel_regularizer=l2(0.0002))(inception_4e_5x5_pad)
inception_4e_pool = MaxPooling2D(
pool_size=(3, 3),
strides=(1, 1),
padding='same',
name='inception_4e/pool')(inception_4d_output)
inception_4e_pool_proj = Conv2D(
128, (1, 1),
padding='same',
activation='relu',
name='inception_4e/pool_proj',
kernel_regularizer=l2(0.0002))(inception_4e_pool)
inception_4e_output = Concatenate(axis=1, name='inception_4e/output')([
inception_4e_1x1, inception_4e_3x3, inception_4e_5x5,
inception_4e_pool_proj
])
inception_4e_output_zero_pad = ZeroPadding2D(
padding=(1, 1))(inception_4e_output)
pool4_helper = PoolHelper()(inception_4e_output_zero_pad)
pool4_3x3_s2 = MaxPooling2D(pool_size=(3, 3),
strides=(2, 2),
padding='valid',
name='pool4/3x3_s2')(pool4_helper)
inception_5a_1x1 = Conv2D(256, (1, 1),
padding='same',
activation='relu',
name='inception_5a/1x1',
kernel_regularizer=l2(0.0002))(pool4_3x3_s2)
inception_5a_3x3_reduce = Conv2D(
160, (1, 1),
padding='same',
activation='relu',
name='inception_5a/3x3_reduce',
kernel_regularizer=l2(0.0002))(pool4_3x3_s2)
inception_5a_3x3_pad = ZeroPadding2D(padding=(1,
1))(inception_5a_3x3_reduce)
inception_5a_3x3 = Conv2D(
320, (3, 3),
padding='valid',
activation='relu',
name='inception_5a/3x3',
kernel_regularizer=l2(0.0002))(inception_5a_3x3_pad)
inception_5a_5x5_reduce = Conv2D(
32, (1, 1),
padding='same',
activation='relu',
name='inception_5a/5x5_reduce',
kernel_regularizer=l2(0.0002))(pool4_3x3_s2)
inception_5a_5x5_pad = ZeroPadding2D(padding=(2,
2))(inception_5a_5x5_reduce)
inception_5a_5x5 = Conv2D(
128, (5, 5),
padding='valid',
activation='relu',
name='inception_5a/5x5',
kernel_regularizer=l2(0.0002))(inception_5a_5x5_pad)
inception_5a_pool = MaxPooling2D(pool_size=(3, 3),
strides=(1, 1),
padding='same',
name='inception_5a/pool')(pool4_3x3_s2)
inception_5a_pool_proj = Conv2D(
128, (1, 1),
padding='same',
activation='relu',
name='inception_5a/pool_proj',
kernel_regularizer=l2(0.0002))(inception_5a_pool)
inception_5a_output = Concatenate(axis=1, name='inception_5a/output')([
inception_5a_1x1, inception_5a_3x3, inception_5a_5x5,
inception_5a_pool_proj
])
inception_5b_1x1 = Conv2D(
384, (1, 1),
padding='same',
activation='relu',
name='inception_5b/1x1',
kernel_regularizer=l2(0.0002))(inception_5a_output)
inception_5b_3x3_reduce = Conv2D(
192, (1, 1),
padding='same',
activation='relu',
name='inception_5b/3x3_reduce',
kernel_regularizer=l2(0.0002))(inception_5a_output)
inception_5b_3x3_pad = ZeroPadding2D(padding=(1,
1))(inception_5b_3x3_reduce)
inception_5b_3x3 = Conv2D(
384, (3, 3),
padding='valid',
activation='relu',
name='inception_5b/3x3',
kernel_regularizer=l2(0.0002))(inception_5b_3x3_pad)
inception_5b_5x5_reduce = Conv2D(
48, (1, 1),
padding='same',
activation='relu',
name='inception_5b/5x5_reduce',
kernel_regularizer=l2(0.0002))(inception_5a_output)
inception_5b_5x5_pad = ZeroPadding2D(padding=(2,
2))(inception_5b_5x5_reduce)
inception_5b_5x5 = Conv2D(
128, (5, 5),
padding='valid',
activation='relu',
name='inception_5b/5x5',
kernel_regularizer=l2(0.0002))(inception_5b_5x5_pad)
inception_5b_pool = MaxPooling2D(
pool_size=(3, 3),
strides=(1, 1),
padding='same',
name='inception_5b/pool')(inception_5a_output)
inception_5b_pool_proj = Conv2D(
128, (1, 1),
padding='same',
activation='relu',
name='inception_5b/pool_proj',
kernel_regularizer=l2(0.0002))(inception_5b_pool)
inception_5b_output = Concatenate(axis=1, name='inception_5b/output')([
inception_5b_1x1, inception_5b_3x3, inception_5b_5x5,
inception_5b_pool_proj
])
pool5_7x7_s1 = AveragePooling2D(pool_size=(7, 7),
strides=(1, 1),
name='pool5/7x7_s2')(inception_5b_output)
loss3_flat = Flatten()(pool5_7x7_s1)
pool5_drop_7x7_s1 = Dropout(rate=0.4)(loss3_flat)
loss3_classifier = Dense(1000,
name='loss3/classifier',
kernel_regularizer=l2(0.0002))(pool5_drop_7x7_s1)
loss3_classifier_act = Activation('softmax', name='prob')(loss3_classifier)
googlenet = Model(inputs=input,
outputs=[
loss1_classifier_act, loss2_classifier_act,
loss3_classifier_act
])
if weights_path:
googlenet.load_weights(weights_path)
if keras.backend.backend() == 'tensorflow':
# convert the convolutional kernels for tensorflow
ops = []
for layer in googlenet.layers:
if layer.__class__.__name__ == 'Conv2D':
original_w = K.get_value(layer.kernel)
converted_w = convert_kernel(original_w)
ops.append(tf.assign(layer.kernel, converted_w).op)
K.get_session().run(ops)
return googlenet
def build(input_shape, num_classes):
input = Input(shape=input_shape)
conv1_7x7 = Conv2D(filters=64,
kernel_size=(7, 7),
strides=(2, 2),
padding='same',
activation='relu',
name='conv1/7x7_s2')(input)
pool1_3x3 = MaxPooling2D(pool_size=(3, 3),
strides=(2, 2),
padding='same',
name='pool1/3x3_s2')(conv1_7x7)
pool1_norm1 = LRN(name='pool1/norm1')(pool1_3x3)
conv2_3x3_reduce = Conv2D(filters=64,
kernel_size=(1, 1),
padding='valid',
activation='relu',
name='conv2/3x3_reduce')(pool1_norm1)
conv2_3x3 = Conv2D(filters=192,
kernel_size=(3, 3),
padding='same',
activation='relu',
name='conv2/3x3')(conv2_3x3_reduce)
conv2_norm2 = LRN(name='conv2/norm2')(conv2_3x3)
pool2_3x3 = MaxPooling2D(pool_size=(3, 3),
strides=(2, 2),
padding='same',
name='pool2/3x3_s2')(conv2_norm2)
inception_3a_1x1 = Conv2D(filters=64,
kernel_size=(1, 1),
padding='same',
activation='relu',
name='inception_3a/1x1')(pool2_3x3)
inception_3a_3x3_reduce = Conv2D(
filters=96,
kernel_size=(1, 1),
padding='same',
activation='relu',
name='inception_3a/3x3_reduce')(pool2_3x3)
inception_3a_3x3 = Conv2D(
filters=128,
kernel_size=(3, 3),
padding='same',
activation='relu',
name='inception_3a/3x3')(inception_3a_3x3_reduce)
inception_3a_5x5_reduce = Conv2D(
filters=16,
kernel_size=(1, 1),
padding='same',
activation='relu',
name='inception_3a/5x5_reduce')(pool2_3x3)
inception_3a_5x5 = Conv2D(
filters=32,
kernel_size=(5, 5),
padding='same',
activation='relu',
name='inception_3a/5x5')(inception_3a_5x5_reduce)
inception_3a_pool = MaxPooling2D(pool_size=(3, 3),
strides=(1, 1),
padding='same',
name='inception_3a/pool')(pool2_3x3)
inception_3a_pool_proj = Conv2D(
filters=32,
kernel_size=(1, 1),
padding='same',
activation='relu',
name='inception_3a/pool_proj')(inception_3a_pool)
inception_3a_output = Concatenate(axis=-1,
name='inception_3a/output')([
inception_3a_1x1,
inception_3a_3x3,
inception_3a_5x5,
inception_3a_pool_proj
])
inception_3b_1x1 = Conv2D(filters=128,
kernel_size=(1, 1),
padding='same',
activation='relu',
name='inception_3b/1x1')(inception_3a_output)
inception_3b_3x3_reduce = Conv2D(
filters=128,
kernel_size=(1, 1),
padding='same',
activation='relu',
name='inception_3b/3x3_reduce')(inception_3a_output)
inception_3b_3x3 = Conv2D(
filters=192,
kernel_size=(3, 3),
padding='same',
activation='relu',
name='inception_3b/3x3')(inception_3b_3x3_reduce)
inception_3b_5x5_reduce = Conv2D(
filters=32,
kernel_size=(1, 1),
padding='same',
activation='relu',
name='inception_3b/5x5_reduce')(inception_3a_output)
inception_3b_5x5 = Conv2D(
filters=96,
kernel_size=(5, 5),
padding='same',
activation='relu',
name='inception_3b/5x5')(inception_3b_5x5_reduce)
inception_3b_pool = MaxPooling2D(
pool_size=(3, 3),
strides=(1, 1),
padding='same',
name='inception_3b/pool')(inception_3a_output)
inception_3b_pool_proj = Conv2D(
filters=64,
kernel_size=(1, 1),
padding='same',
activation='relu',
name='inception_3b/pool_proj')(inception_3b_pool)
inception_3b_output = Concatenate(axis=-1,
name='inception_3b/output')([
inception_3b_1x1,
inception_3b_3x3,
inception_3b_5x5,
inception_3b_pool_proj
])
inception_4a_1x1 = Conv2D(filters=192,
kernel_size=(1, 1),
padding='same',
activation='relu',
name='inception_4a/1x1')(inception_3b_output)
inception_4a_3x3_reduce = Conv2D(
filters=96,
kernel_size=(1, 1),
padding='same',
activation='relu',
name='inception_4a/3x3_reduce')(inception_3b_output)
inception_4a_3x3 = Conv2D(
filters=208,
kernel_size=(3, 3),
padding='same',
activation='relu',
name='inception_4a/3x3',
kernel_regularizer=l2(0.0002))(inception_4a_3x3_reduce)
inception_4a_5x5_reduce = Conv2D(
filters=16,
kernel_size=(1, 1),
padding='same',
activation='relu',
name='inception_4a/5x5_reduce')(inception_3b_output)
inception_4a_5x5 = Conv2D(
filters=48,
kernel_size=(5, 5),
padding='same',
activation='relu',
name='inception_4a/5x5')(inception_4a_5x5_reduce)
inception_4a_pool = MaxPooling2D(
pool_size=(3, 3),
strides=(1, 1),
padding='same',
name='inception_4a/pool')(inception_3b_output)
inception_4a_pool_proj = Conv2D(
filters=64,
kernel_size=(1, 1),
padding='same',
activation='relu',
name='inception_4a/pool_proj')(inception_4a_pool)
inception_4a_output = Concatenate(axis=-1,
name='inception_4a/output')([
inception_4a_1x1,
inception_4a_3x3,
inception_4a_5x5,
inception_4a_pool_proj
])
loss1_ave_pool = AveragePooling2D(
pool_size=(5, 5), strides=(3, 3),
name='loss1/ave_pool')(inception_4a_output)
loss1_conv = Conv2D(filters=128,
kernel_size=(1, 1),
padding='same',
activation='relu',
name='loss1/conv')(loss1_ave_pool)
loss1_fc = Dense(1024, activation='relu', name='loss1/fc')(loss1_conv)
loss1_drop_fc = Dropout(rate=0.5)(loss1_fc)
loss1_classifier = Dense(num_classes,
name='loss1/classifier')(loss1_drop_fc)
loss1_classifier_act = Activation('softmax')(loss1_classifier)
inception_4b_1x1 = Conv2D(filters=160,
kernel_size=(1, 1),
padding='same',
activation='relu',
name='inception_4b/1x1')(inception_4a_output)
inception_4b_3x3_reduce = Conv2D(
filters=112,
kernel_size=(1, 1),
padding='same',
activation='relu',
name='inception_4b/3x3_reduce')(inception_4a_output)
inception_4b_3x3 = Conv2D(
filters=224,
kernel_size=(3, 3),
padding='same',
activation='relu',
name='inception_4b/3x3')(inception_4b_3x3_reduce)
inception_4b_5x5_reduce = Conv2D(
filters=24,
kernel_size=(1, 1),
padding='same',
activation='relu',
name='inception_4b/5x5_reduce')(inception_4a_output)
inception_4b_5x5 = Conv2D(
filters=64,
kernel_size=(5, 5),
padding='same',
activation='relu',
name='inception_4b/5x5')(inception_4b_5x5_reduce)
inception_4b_pool = MaxPooling2D(
pool_size=(3, 3),
strides=(1, 1),
padding='same',
name='inception_4b/pool')(inception_4a_output)
inception_4b_pool_proj = Conv2D(
filters=64,
kernel_size=(1, 1),
padding='same',
activation='relu',
name='inception_4b/pool_proj')(inception_4b_pool)
inception_4b_output = Concatenate(axis=-1,
name='inception_4b/output')([
inception_4b_1x1,
inception_4b_3x3,
inception_4b_5x5,
inception_4b_pool_proj
])
inception_4c_1x1 = Conv2D(filters=128,
kernel_size=(1, 1),
padding='same',
activation='relu',
name='inception_4c/1x1')(inception_4b_output)
inception_4c_3x3_reduce = Conv2D(
filters=128,
kernel_size=(1, 1),
padding='same',
activation='relu',
name='inception_4c/3x3_reduce')(inception_4b_output)
inception_4c_3x3 = Conv2D(
filters=256,
kernel_size=(3, 3),
padding='same',
activation='relu',
name='inception_4c/3x3')(inception_4c_3x3_reduce)
inception_4c_5x5_reduce = Conv2D(
filters=24,
kernel_size=(1, 1),
padding='same',
activation='relu',
name='inception_4c/5x5_reduce')(inception_4b_output)
inception_4c_5x5 = Conv2D(
filters=64,
kernel_size=(5, 5),
padding='same',
activation='relu',
name='inception_4c/5x5')(inception_4c_5x5_reduce)
inception_4c_pool = MaxPooling2D(
pool_size=(3, 3),
strides=(1, 1),
padding='same',
name='inception_4c/pool')(inception_4b_output)
inception_4c_pool_proj = Conv2D(
filters=64,
kernel_size=(1, 1),
padding='same',
activation='relu',
name='inception_4c/pool_proj')(inception_4c_pool)
inception_4c_output = Concatenate(axis=-1,
name='inception_4c/output')([
inception_4c_1x1,
inception_4c_3x3,
inception_4c_5x5,
inception_4c_pool_proj
])
inception_4d_1x1 = Conv2D(filters=112,
kernel_size=(1, 1),
padding='same',
activation='relu',
name='inception_4d/1x1')(inception_4c_output)
inception_4d_3x3_reduce = Conv2D(
filters=144,
kernel_size=(1, 1),
padding='same',
activation='relu',
name='inception_4d/3x3_reduce')(inception_4c_output)
inception_4d_3x3 = Conv2D(
filters=288,
kernel_size=(3, 3),
padding='same',
activation='relu',
name='inception_4d/3x3')(inception_4d_3x3_reduce)
inception_4d_5x5_reduce = Conv2D(
filters=32,
kernel_size=(1, 1),
padding='same',
activation='relu',
name='inception_4d/5x5_reduce')(inception_4c_output)
inception_4d_5x5 = Conv2D(
filters=64,
kernel_size=(5, 5),
padding='same',
activation='relu',
name='inception_4d/5x5')(inception_4d_5x5_reduce)
inception_4d_pool = MaxPooling2D(
pool_size=(3, 3),
strides=(1, 1),
padding='same',
name='inception_4d/pool')(inception_4c_output)
inception_4d_pool_proj = Conv2D(
filters=64,
kernel_size=(1, 1),
padding='same',
activation='relu',
name='inception_4d/pool_proj')(inception_4d_pool)
inception_4d_output = Concatenate(axis=-1,
name='inception_4d/output')([
inception_4d_1x1,
inception_4d_3x3,
inception_4d_5x5,
inception_4d_pool_proj
])
loss2_ave_pool = AveragePooling2D(
pool_size=(5, 5), strides=(3, 3),
name='loss2/ave_pool')(inception_4d_output)
loss2_conv = Conv2D(filters=128,
kernel_size=(1, 1),
padding='same',
activation='relu',
name='loss2/conv')(loss2_ave_pool)
loss2_fc = Dense(1024, activation='relu', name='loss2/fc')(loss2_conv)
loss2_drop_fc = Dropout(rate=0.5)(loss2_fc)
loss2_classifier = Dense(num_classes,
name='loss2/classifier')(loss2_drop_fc)
loss2_classifier_act = Activation('softmax')(loss2_classifier)
inception_4e_1x1 = Conv2D(filters=256,
kernel_size=(1, 1),
padding='same',
activation='relu',
name='inception_4e/1x1')(inception_4d_output)
inception_4e_3x3_reduce = Conv2D(
filters=160,
kernel_size=(1, 1),
padding='same',
activation='relu',
name='inception_4e/3x3_reduce')(inception_4d_output)
inception_4e_3x3 = Conv2D(
filters=320,
kernel_size=(3, 3),
padding='same',
activation='relu',
name='inception_4e/3x3')(inception_4e_3x3_reduce)
inception_4e_5x5_reduce = Conv2D(
filters=32,
kernel_size=(1, 1),
padding='same',
activation='relu',
name='inception_4e/5x5_reduce')(inception_4d_output)
inception_4e_5x5 = Conv2D(
filters=128,
kernel_size=(5, 5),
padding='same',
activation='relu',
name='inception_4e/5x5')(inception_4e_5x5_reduce)
inception_4e_pool = MaxPooling2D(
pool_size=(3, 3),
strides=(1, 1),
padding='same',
name='inception_4e/pool')(inception_4d_output)
inception_4e_pool_proj = Conv2D(
filters=128,
kernel_size=(1, 1),
padding='same',
activation='relu',
name='inception_4e/pool_proj')(inception_4e_pool)
inception_4e_output = Concatenate(axis=-1,
name='inception_4e/output')([
inception_4e_1x1,
inception_4e_3x3,
inception_4e_5x5,
inception_4e_pool_proj
])
inception_5a_1x1 = Conv2D(filters=256,
kernel_size=(1, 1),
padding='same',
activation='relu',
name='inception_5a/1x1')(inception_4e_output)
inception_5a_3x3_reduce = Conv2D(
filters=160,
kernel_size=(1, 1),
padding='same',
activation='relu',
name='inception_5a/3x3_reduce')(inception_4e_output)
inception_5a_3x3 = Conv2D(
filters=320,
kernel_size=(3, 3),
padding='same',
activation='relu',
name='inception_5a/3x3')(inception_5a_3x3_reduce)
inception_5a_5x5_reduce = Conv2D(
filters=32,
kernel_size=(1, 1),
padding='same',
activation='relu',
name='inception_5a/5x5_reduce')(inception_4e_output)
inception_5a_5x5 = Conv2D(
filters=128,
kernel_size=(5, 5),
padding='same',
activation='relu',
name='inception_5a/5x5')(inception_5a_5x5_reduce)
inception_5a_pool = MaxPooling2D(
pool_size=(3, 3),
strides=(1, 1),
padding='same',
name='inception_5a/pool')(inception_4e_output)
inception_5a_pool_proj = Conv2D(
filters=128,
kernel_size=(1, 1),
padding='same',
activation='relu',
name='inception_5a/pool_proj')(inception_5a_pool)
inception_5a_output = Concatenate(axis=-1,
name='inception_5a/output')([
inception_5a_1x1,
inception_5a_3x3,
inception_5a_5x5,
inception_5a_pool_proj
])
inception_5b_1x1 = Conv2D(filters=384,
kernel_size=(1, 1),
padding='same',
activation='relu',
name='inception_5b/1x1')(inception_5a_output)
inception_5b_3x3_reduce = Conv2D(
filters=192,
kernel_size=(1, 1),
padding='same',
activation='relu',
name='inception_5b/3x3_reduce')(inception_5a_output)
inception_5b_3x3 = Conv2D(
filters=384,
kernel_size=(3, 3),
padding='same',
activation='relu',
name='inception_5b/3x3')(inception_5b_3x3_reduce)
inception_5b_5x5_reduce = Conv2D(
filters=48,
kernel_size=(1, 1),
padding='same',
activation='relu',
name='inception_5b/5x5_reduce')(inception_5a_output)
inception_5b_5x5 = Conv2D(
filters=128,
kernel_size=(5, 5),
padding='same',
activation='relu',
name='inception_5b/5x5')(inception_5b_5x5_reduce)
inception_5b_pool = MaxPooling2D(
pool_size=(3, 3),
strides=(1, 1),
padding='same',
name='inception_5b/pool')(inception_5a_output)
inception_5b_pool_proj = Conv2D(
filters=128,
kernel_size=(1, 1),
padding='same',
activation='relu',
name='inception_5b/pool_proj')(inception_5b_pool)
inception_5b_output = Concatenate(axis=-1,
name='inception_5b/output')([
inception_5b_1x1,
inception_5b_3x3,
inception_5b_5x5,
inception_5b_pool_proj
])
pool5_7x7_s1 = AveragePooling2D(
pool_size=(7, 7), strides=(1, 1),
name='pool5/7x7_s2')(inception_5b_output)
pool5_drop_7x7_s1 = Dropout(rate=0.5)(pool5_7x7_s1)
loss3_classifier = Dense(num_classes,
name='loss3/classifier')(pool5_drop_7x7_s1)
loss3_classifier_act = Activation('softmax',
name='prob')(loss3_classifier)
inception_v1 = Model(inputs=input,
outputs=[
loss1_classifier_act, loss2_classifier_act,
loss3_classifier_act
])
return inception_v1
y_train_valid = keras.utils.to_categorical(y_train_valid, num_classes)
y_test = keras.utils.to_categorical(y_test, num_classes)
model = Sequential()
model.add(ZeroPadding2D(padding=(3, 3)))
model.add(
Conv2D(64, (7, 7),
strides=(2, 2),
padding='valid',
activation='relu',
kernel_regularizer=l2(0.0002)))
model.add(ZeroPadding2D(padding=(1, 1)))
model.add(PoolHelper())
model.add(MaxPooling2D(pool_size=(3, 3), strides=(2, 2), padding='valid'))
model.add(LRN())
model.add(
Conv2D(64, (1, 1),
padding='same',
activation='relu',
kernel_regularizer=l2(0.0002)))
model.add(
Conv2D(192, (3, 3),
padding='same',
activation='relu',
kernel_regularizer=l2(0.0002)))
model.add(LRN())
model.add(ZeroPadding2D(padding=(1, 1)))
model.add(PoolHelper())
model.add(MaxPooling2D(pool_size=(3, 3), strides=(2, 2), padding='valid'))
def googlenet(input_shape=(224, 224, 3), classes=7, weights_path=None):
# shape, classes 수정
input = Input(input_shape)
input_pad = ZeroPadding2D(padding=(3, 3))(input)
conv1_7x7_s2 = Conv2D(64, (7, 7),
strides=(2, 2),
padding='valid',
activation='relu',
name='conv1/7x7_s2',
kernel_regularizer=l2(0.0002))(input_pad)
conv1_zero_pad = ZeroPadding2D(padding=(1, 1))(conv1_7x7_s2)
pool1_helper = PoolHelper()(
conv1_zero_pad) # 짝수를 하나씩 지움으로써 홀수차원으로 만든다. 직접 만든함수.
pool1_3x3_s2 = MaxPooling2D(pool_size=(3, 3),
strides=(2, 2),
padding='valid',
name='pool1/3x3_s2')(pool1_helper)
pool1_norm1 = LRN(name='pool1/norm1')(pool1_3x3_s2)
conv2_3x3_reduce = Conv2D(64, (1, 1),
padding='same',
activation='relu',
name='conv2/3x3_reduce',
kernel_regularizer=l2(0.0002))(pool1_norm1)
conv2_3x3 = Conv2D(192, (3, 3),
padding='same',
activation='relu',
name='conv2/3x3',
kernel_regularizer=l2(0.0002))(conv2_3x3_reduce)
conv2_norm2 = LRN(name='conv2/norm2')(conv2_3x3)
conv2_zero_pad = ZeroPadding2D(padding=(1, 1))(conv2_norm2)
pool2_helper = PoolHelper()(conv2_zero_pad)
pool2_3x3_s2 = MaxPooling2D(pool_size=(3, 3),
strides=(2, 2),
padding='valid',
name='pool2/3x3_s2')(pool2_helper)
inception_3a_1x1 = Conv2D(64, (1, 1),
padding='same',
activation='relu',
name='inception_3a/1x1',
kernel_regularizer=l2(0.0002))(pool2_3x3_s2)
inception_3a_3x3_reduce = Conv2D(
96, (1, 1),
padding='same',
activation='relu',
name='inception_3a/3x3_reduce',
kernel_regularizer=l2(0.0002))(pool2_3x3_s2)
inception_3a_3x3_pad = ZeroPadding2D(padding=(1,
1))(inception_3a_3x3_reduce)
inception_3a_3x3 = Conv2D(
128, (3, 3),
padding='valid',
activation='relu',
name='inception_3a/3x3',
kernel_regularizer=l2(0.0002))(inception_3a_3x3_pad)
inception_3a_5x5_reduce = Conv2D(
16, (1, 1),
padding='same',
activation='relu',
name='inception_3a/5x5_reduce',
kernel_regularizer=l2(0.0002))(pool2_3x3_s2)
inception_3a_5x5_pad = ZeroPadding2D(padding=(2,
2))(inception_3a_5x5_reduce)
inception_3a_5x5 = Conv2D(
32, (5, 5),
padding='valid',
activation='relu',
name='inception_3a/5x5',
kernel_regularizer=l2(0.0002))(inception_3a_5x5_pad)
inception_3a_pool = MaxPooling2D(pool_size=(3, 3),
strides=(1, 1),
padding='same',
name='inception_3a/pool')(pool2_3x3_s2)
inception_3a_pool_proj = Conv2D(
32, (1, 1),
padding='same',
activation='relu',
name='inception_3a/pool_proj',
kernel_regularizer=l2(0.0002))(inception_3a_pool)
inception_3a_output = Concatenate(axis=-1, name='inception_3a/output')([
inception_3a_1x1, inception_3a_3x3, inception_3a_5x5,
inception_3a_pool_proj
])
# Concatenate axis 수정.
inception_3b_1x1 = Conv2D(
128, (1, 1),
padding='same',
activation='relu',
name='inception_3b/1x1',
kernel_regularizer=l2(0.0002))(inception_3a_output)
inception_3b_3x3_reduce = Conv2D(
128, (1, 1),
padding='same',
activation='relu',
name='inception_3b/3x3_reduce',
kernel_regularizer=l2(0.0002))(inception_3a_output)
inception_3b_3x3_pad = ZeroPadding2D(padding=(1,
1))(inception_3b_3x3_reduce)
inception_3b_3x3 = Conv2D(
192, (3, 3),
padding='valid',
activation='relu',
name='inception_3b/3x3',
kernel_regularizer=l2(0.0002))(inception_3b_3x3_pad)
inception_3b_5x5_reduce = Conv2D(
32, (1, 1),
padding='same',
activation='relu',
name='inception_3b/5x5_reduce',
kernel_regularizer=l2(0.0002))(inception_3a_output)
inception_3b_5x5_pad = ZeroPadding2D(padding=(2,
2))(inception_3b_5x5_reduce)
inception_3b_5x5 = Conv2D(
96, (5, 5),
padding='valid',
activation='relu',
name='inception_3b/5x5',
kernel_regularizer=l2(0.0002))(inception_3b_5x5_pad)
inception_3b_pool = MaxPooling2D(
pool_size=(3, 3),
strides=(1, 1),
padding='same',
name='inception_3b/pool')(inception_3a_output)
inception_3b_pool_proj = Conv2D(
64, (1, 1),
padding='same',
activation='relu',
name='inception_3b/pool_proj',
kernel_regularizer=l2(0.0002))(inception_3b_pool)
inception_3b_output = Concatenate(axis=-1, name='inception_3b/output')([
inception_3b_1x1, inception_3b_3x3, inception_3b_5x5,
inception_3b_pool_proj
])
inception_3b_output_zero_pad = ZeroPadding2D(
padding=(1, 1))(inception_3b_output)
pool3_helper = PoolHelper()(inception_3b_output_zero_pad)
pool3_3x3_s2 = MaxPooling2D(pool_size=(3, 3),
strides=(2, 2),
padding='valid',
name='pool3/3x3_s2')(pool3_helper)
inception_4a_1x1 = Conv2D(192, (1, 1),
padding='same',
activation='relu',
name='inception_4a/1x1',
kernel_regularizer=l2(0.0002))(pool3_3x3_s2)
inception_4a_3x3_reduce = Conv2D(
96, (1, 1),
padding='same',
activation='relu',
name='inception_4a/3x3_reduce',
kernel_regularizer=l2(0.0002))(pool3_3x3_s2)
inception_4a_3x3_pad = ZeroPadding2D(padding=(1,
1))(inception_4a_3x3_reduce)
inception_4a_3x3 = Conv2D(
208, (3, 3),
padding='valid',
activation='relu',
name='inception_4a/3x3',
kernel_regularizer=l2(0.0002))(inception_4a_3x3_pad)
inception_4a_5x5_reduce = Conv2D(
16, (1, 1),
padding='same',
activation='relu',
name='inception_4a/5x5_reduce',
kernel_regularizer=l2(0.0002))(pool3_3x3_s2)
inception_4a_5x5_pad = ZeroPadding2D(padding=(2,
2))(inception_4a_5x5_reduce)
inception_4a_5x5 = Conv2D(
48, (5, 5),
padding='valid',
activation='relu',
name='inception_4a/5x5',
kernel_regularizer=l2(0.0002))(inception_4a_5x5_pad)
inception_4a_pool = MaxPooling2D(pool_size=(3, 3),
strides=(1, 1),
padding='same',
name='inception_4a/pool')(pool3_3x3_s2)
inception_4a_pool_proj = Conv2D(
64, (1, 1),
padding='same',
activation='relu',
name='inception_4a/pool_proj',
kernel_regularizer=l2(0.0002))(inception_4a_pool)
inception_4a_output = Concatenate(axis=-1, name='inception_4a/output')([
inception_4a_1x1, inception_4a_3x3, inception_4a_5x5,
inception_4a_pool_proj
])
loss1_ave_pool = AveragePooling2D(
pool_size=(5, 5), strides=(3, 3),
name='loss1/ave_pool')(inception_4a_output)
loss1_conv = Conv2D(128, (1, 1),
padding='same',
activation='relu',
name='loss1/conv',
kernel_regularizer=l2(0.0002))(loss1_ave_pool)
loss1_flat = Flatten()(loss1_conv)
loss1_fc = Dense(1024,
activation='relu',
name='loss1/fc',
kernel_regularizer=l2(0.0002))(loss1_flat)
loss1_drop_fc = Dropout(rate=0.7)(loss1_fc)
loss1_classifier = Dense(classes,
name='loss1/classifier',
kernel_regularizer=l2(0.0002))(loss1_drop_fc)
loss1_classifier_act = Activation('softmax')(loss1_classifier)
inception_4b_1x1 = Conv2D(
160, (1, 1),
padding='same',
activation='relu',
name='inception_4b/1x1',
kernel_regularizer=l2(0.0002))(inception_4a_output)
inception_4b_3x3_reduce = Conv2D(
112, (1, 1),
padding='same',
activation='relu',
name='inception_4b/3x3_reduce',
kernel_regularizer=l2(0.0002))(inception_4a_output)
inception_4b_3x3_pad = ZeroPadding2D(padding=(1,
1))(inception_4b_3x3_reduce)
inception_4b_3x3 = Conv2D(
224, (3, 3),
padding='valid',
activation='relu',
name='inception_4b/3x3',
kernel_regularizer=l2(0.0002))(inception_4b_3x3_pad)
inception_4b_5x5_reduce = Conv2D(
24, (1, 1),
padding='same',
activation='relu',
name='inception_4b/5x5_reduce',
kernel_regularizer=l2(0.0002))(inception_4a_output)
inception_4b_5x5_pad = ZeroPadding2D(padding=(2,
2))(inception_4b_5x5_reduce)
inception_4b_5x5 = Conv2D(
64, (5, 5),
padding='valid',
activation='relu',
name='inception_4b/5x5',
kernel_regularizer=l2(0.0002))(inception_4b_5x5_pad)
inception_4b_pool = MaxPooling2D(
pool_size=(3, 3),
strides=(1, 1),
padding='same',
name='inception_4b/pool')(inception_4a_output)
inception_4b_pool_proj = Conv2D(
64, (1, 1),
padding='same',
activation='relu',
name='inception_4b/pool_proj',
kernel_regularizer=l2(0.0002))(inception_4b_pool)
inception_4b_output = Concatenate(axis=-1, name='inception_4b/output')([
inception_4b_1x1, inception_4b_3x3, inception_4b_5x5,
inception_4b_pool_proj
])
inception_4c_1x1 = Conv2D(
128, (1, 1),
padding='same',
activation='relu',
name='inception_4c/1x1',
kernel_regularizer=l2(0.0002))(inception_4b_output)
inception_4c_3x3_reduce = Conv2D(
128, (1, 1),
padding='same',
activation='relu',
name='inception_4c/3x3_reduce',
kernel_regularizer=l2(0.0002))(inception_4b_output)
inception_4c_3x3_pad = ZeroPadding2D(padding=(1,
1))(inception_4c_3x3_reduce)
inception_4c_3x3 = Conv2D(
256, (3, 3),
padding='valid',
activation='relu',
name='inception_4c/3x3',
kernel_regularizer=l2(0.0002))(inception_4c_3x3_pad)
inception_4c_5x5_reduce = Conv2D(
24, (1, 1),
padding='same',
activation='relu',
name='inception_4c/5x5_reduce',
kernel_regularizer=l2(0.0002))(inception_4b_output)
inception_4c_5x5_pad = ZeroPadding2D(padding=(2,
2))(inception_4c_5x5_reduce)
inception_4c_5x5 = Conv2D(
64, (5, 5),
padding='valid',
activation='relu',
name='inception_4c/5x5',
kernel_regularizer=l2(0.0002))(inception_4c_5x5_pad)
inception_4c_pool = MaxPooling2D(
pool_size=(3, 3),
strides=(1, 1),
padding='same',
name='inception_4c/pool')(inception_4b_output)
inception_4c_pool_proj = Conv2D(
64, (1, 1),
padding='same',
activation='relu',
name='inception_4c/pool_proj',
kernel_regularizer=l2(0.0002))(inception_4c_pool)
inception_4c_output = Concatenate(axis=-1, name='inception_4c/output')([
inception_4c_1x1, inception_4c_3x3, inception_4c_5x5,
inception_4c_pool_proj
])
inception_4d_1x1 = Conv2D(
112, (1, 1),
padding='same',
activation='relu',
name='inception_4d/1x1',
kernel_regularizer=l2(0.0002))(inception_4c_output)
inception_4d_3x3_reduce = Conv2D(
144, (1, 1),
padding='same',
activation='relu',
name='inception_4d/3x3_reduce',
kernel_regularizer=l2(0.0002))(inception_4c_output)
inception_4d_3x3_pad = ZeroPadding2D(padding=(1,
1))(inception_4d_3x3_reduce)
inception_4d_3x3 = Conv2D(
288, (3, 3),
padding='valid',
activation='relu',
name='inception_4d/3x3',
kernel_regularizer=l2(0.0002))(inception_4d_3x3_pad)
inception_4d_5x5_reduce = Conv2D(
32, (1, 1),
padding='same',
activation='relu',
name='inception_4d/5x5_reduce',
kernel_regularizer=l2(0.0002))(inception_4c_output)
inception_4d_5x5_pad = ZeroPadding2D(padding=(2,
2))(inception_4d_5x5_reduce)
inception_4d_5x5 = Conv2D(
64, (5, 5),
padding='valid',
activation='relu',
name='inception_4d/5x5',
kernel_regularizer=l2(0.0002))(inception_4d_5x5_pad)
inception_4d_pool = MaxPooling2D(
pool_size=(3, 3),
strides=(1, 1),
padding='same',
name='inception_4d/pool')(inception_4c_output)
inception_4d_pool_proj = Conv2D(
64, (1, 1),
padding='same',
activation='relu',
name='inception_4d/pool_proj',
kernel_regularizer=l2(0.0002))(inception_4d_pool)
inception_4d_output = Concatenate(axis=-1, name='inception_4d/output')([
inception_4d_1x1, inception_4d_3x3, inception_4d_5x5,
inception_4d_pool_proj
])
loss2_ave_pool = AveragePooling2D(
pool_size=(5, 5), strides=(3, 3),
name='loss2/ave_pool')(inception_4d_output)
loss2_conv = Conv2D(128, (1, 1),
padding='same',
activation='relu',
name='loss2/conv',
kernel_regularizer=l2(0.0002))(loss2_ave_pool)
loss2_flat = Flatten()(loss2_conv)
loss2_fc = Dense(1024,
activation='relu',
name='loss2/fc',
kernel_regularizer=l2(0.0002))(loss2_flat)
loss2_drop_fc = Dropout(rate=0.7)(loss2_fc)
loss2_classifier = Dense(classes,
name='loss2/classifier',
kernel_regularizer=l2(0.0002))(loss2_drop_fc)
loss2_classifier_act = Activation('softmax')(loss2_classifier)
inception_4e_1x1 = Conv2D(
256, (1, 1),
padding='same',
activation='relu',
name='inception_4e/1x1',
kernel_regularizer=l2(0.0002))(inception_4d_output)
inception_4e_3x3_reduce = Conv2D(
160, (1, 1),
padding='same',
activation='relu',
name='inception_4e/3x3_reduce',
kernel_regularizer=l2(0.0002))(inception_4d_output)
inception_4e_3x3_pad = ZeroPadding2D(padding=(1,
1))(inception_4e_3x3_reduce)
inception_4e_3x3 = Conv2D(
320, (3, 3),
padding='valid',
activation='relu',
name='inception_4e/3x3',
kernel_regularizer=l2(0.0002))(inception_4e_3x3_pad)
inception_4e_5x5_reduce = Conv2D(
32, (1, 1),
padding='same',
activation='relu',
name='inception_4e/5x5_reduce',
kernel_regularizer=l2(0.0002))(inception_4d_output)
inception_4e_5x5_pad = ZeroPadding2D(padding=(2,
2))(inception_4e_5x5_reduce)
inception_4e_5x5 = Conv2D(
128, (5, 5),
padding='valid',
activation='relu',
name='inception_4e/5x5',
kernel_regularizer=l2(0.0002))(inception_4e_5x5_pad)
inception_4e_pool = MaxPooling2D(
pool_size=(3, 3),
strides=(1, 1),
padding='same',
name='inception_4e/pool')(inception_4d_output)
inception_4e_pool_proj = Conv2D(
128, (1, 1),
padding='same',
activation='relu',
name='inception_4e/pool_proj',
kernel_regularizer=l2(0.0002))(inception_4e_pool)
inception_4e_output = Concatenate(axis=-1, name='inception_4e/output')([
inception_4e_1x1, inception_4e_3x3, inception_4e_5x5,
inception_4e_pool_proj
])
inception_4e_output_zero_pad = ZeroPadding2D(
padding=(1, 1))(inception_4e_output)
pool4_helper = PoolHelper()(inception_4e_output_zero_pad)
pool4_3x3_s2 = MaxPooling2D(pool_size=(3, 3),
strides=(2, 2),
padding='valid',
name='pool4/3x3_s2')(pool4_helper)
inception_5a_1x1 = Conv2D(256, (1, 1),
padding='same',
activation='relu',
name='inception_5a/1x1',
kernel_regularizer=l2(0.0002))(pool4_3x3_s2)
inception_5a_3x3_reduce = Conv2D(
160, (1, 1),
padding='same',
activation='relu',
name='inception_5a/3x3_reduce',
kernel_regularizer=l2(0.0002))(pool4_3x3_s2)
inception_5a_3x3_pad = ZeroPadding2D(padding=(1,
1))(inception_5a_3x3_reduce)
inception_5a_3x3 = Conv2D(
320, (3, 3),
padding='valid',
activation='relu',
name='inception_5a/3x3',
kernel_regularizer=l2(0.0002))(inception_5a_3x3_pad)
inception_5a_5x5_reduce = Conv2D(
32, (1, 1),
padding='same',
activation='relu',
name='inception_5a/5x5_reduce',
kernel_regularizer=l2(0.0002))(pool4_3x3_s2)
inception_5a_5x5_pad = ZeroPadding2D(padding=(2,
2))(inception_5a_5x5_reduce)
inception_5a_5x5 = Conv2D(
128, (5, 5),
padding='valid',
activation='relu',
name='inception_5a/5x5',
kernel_regularizer=l2(0.0002))(inception_5a_5x5_pad)
inception_5a_pool = MaxPooling2D(pool_size=(3, 3),
strides=(1, 1),
padding='same',
name='inception_5a/pool')(pool4_3x3_s2)
inception_5a_pool_proj = Conv2D(
128, (1, 1),
padding='same',
activation='relu',
name='inception_5a/pool_proj',
kernel_regularizer=l2(0.0002))(inception_5a_pool)
inception_5a_output = Concatenate(axis=-1, name='inception_5a/output')([
inception_5a_1x1, inception_5a_3x3, inception_5a_5x5,
inception_5a_pool_proj
])
inception_5b_1x1 = Conv2D(
384, (1, 1),
padding='same',
activation='relu',
name='inception_5b/1x1',
kernel_regularizer=l2(0.0002))(inception_5a_output)
inception_5b_3x3_reduce = Conv2D(
192, (1, 1),
padding='same',
activation='relu',
name='inception_5b/3x3_reduce',
kernel_regularizer=l2(0.0002))(inception_5a_output)
inception_5b_3x3_pad = ZeroPadding2D(padding=(1,
1))(inception_5b_3x3_reduce)
inception_5b_3x3 = Conv2D(
384, (3, 3),
padding='valid',
activation='relu',
name='inception_5b/3x3',
kernel_regularizer=l2(0.0002))(inception_5b_3x3_pad)
inception_5b_5x5_reduce = Conv2D(
48, (1, 1),
padding='same',
activation='relu',
name='inception_5b/5x5_reduce',
kernel_regularizer=l2(0.0002))(inception_5a_output)
inception_5b_5x5_pad = ZeroPadding2D(padding=(2,
2))(inception_5b_5x5_reduce)
inception_5b_5x5 = Conv2D(
128, (5, 5),
padding='valid',
activation='relu',
name='inception_5b/5x5',
kernel_regularizer=l2(0.0002))(inception_5b_5x5_pad)
inception_5b_pool = MaxPooling2D(
pool_size=(3, 3),
strides=(1, 1),
padding='same',
name='inception_5b/pool')(inception_5a_output)
inception_5b_pool_proj = Conv2D(
128, (1, 1),
padding='same',
activation='relu',
name='inception_5b/pool_proj',
kernel_regularizer=l2(0.0002))(inception_5b_pool)
inception_5b_output = Concatenate(axis=-1, name='inception_5b/output')([
inception_5b_1x1, inception_5b_3x3, inception_5b_5x5,
inception_5b_pool_proj
])
pool5_7x7_s1 = AveragePooling2D(pool_size=(7, 7),
strides=(1, 1),
name='pool5/7x7_s2')(inception_5b_output)
loss3_flat = Flatten()(pool5_7x7_s1)
pool5_drop_7x7_s1 = Dropout(rate=0.4)(loss3_flat)
loss3_classifier = Dense(classes,
name='loss3/classifier',
kernel_regularizer=l2(0.0002))(pool5_drop_7x7_s1)
loss3_classifier_act = Activation('softmax', name='prob')(loss3_classifier)
googlenet = Model(inputs=input,
outputs=[
loss1_classifier_act, loss2_classifier_act,
loss3_classifier_act
])
if weights_path:
googlenet.load_weights(weights_path)
# if tf.keras.backend.backend() == 'tensorflow':
# # 우리는 tf.keras를 쓰므로, 이상황은 늘 True.
# # 또한, 아래의 코드도 시행할 필요가 없다.
# # 혹시모를 , 나중의 상황에 대비해 코드만 남겨놓는다.
#
# ops = []
# for layer in googlenet.layers:
# if layer.__class__.__name__ == 'Conv2D': # layer의 class의 이름이 'conv2d'이면 ~
# original_w = K.get_value(layer.kernel)
# converted_w = convert_kernel(original_w)
# ops.append(tf.assign(layer.kernel, converted_w).op)
# K.get_session().run(ops)
return googlenet
def create_cnn_model(weights_path=None):
# creates our cnn model
#filters which total weights is “n*m*k*l” (Here the input has l=32 feature maps as inputs, k=64 feature maps as outputs)
#Then there is a term called bias for each feature map. So, the total number of parameters are “(n*m*l+1)*k”.
'''
PARAMETERS
https://towardsdatascience.com/understanding-and-calculating-the-number-of-parameters-in-convolution-neural-networks-cnns-fc88790d530d
https://medium.com/@shashikachamod4u/calculate-output-size-and-number-of-trainable-parameters-in-a-convolution-layer-1d64cae6c009
https://medium.com/@iamvarman/how-to-calculate-the-number-of-parameters-in-the-cnn-5bd55364d7ca
https://cs231n.github.io/convolutional-networks/
'''
input = Input(shape=(1, IMG_WIDTH, IMG_HEIGHT))
input_pad = ZeroPadding2D(padding=(3, 3))(input)
conv1_1_3x3_s1 = Conv2D(32, (3, 3),
strides=(1, 1),
padding='same',
activation='relu',
name='conv1_1/3x3_s1',
kernel_regularizer=l2(l2_regulizer))(input_pad)
conv1_2_3x3_s1 = Conv2D(
32, (3, 3),
strides=(1, 1),
padding='same',
activation='relu',
name='conv1_2/3x3_s1',
kernel_regularizer=l2(l2_regulizer))(conv1_1_3x3_s1)
conv1_zero_pad = ZeroPadding2D(padding=(1, 1))(conv1_2_3x3_s1)
pool1_helper = PoolHelper()(conv1_zero_pad)
pool1_2_2x2_s1 = MaxPooling2D(pool_size=(2, 2),
strides=(1, 1),
padding='same',
name='pool1/2x2_s1')(pool1_helper)
pool1_norm1 = LRN(name='pool1/norm1')(pool1_2_2x2_s1)
conv2_1_3x3_reduce = Conv2D(
64, (1, 1),
padding='same',
activation='relu',
name='conv2_1/3x3_reduce',
kernel_regularizer=l2(l2_regulizer))(pool1_norm1)
conv2_2_3x3 = Conv2D(
64, (3, 3),
padding='same',
activation='relu',
name='conv2_2/3x3',
kernel_regularizer=l2(l2_regulizer))(conv2_1_3x3_reduce)
conv2_norm2 = LRN(name='conv2/norm2')(conv2_2_3x3)
conv2_zero_pad = ZeroPadding2D(padding=(1, 1))(conv2_norm2)
pool2_helper = PoolHelper()(conv2_zero_pad)
pool2_3x3_s2 = MaxPooling2D(pool_size=(3, 3),
strides=(2, 2),
padding='same',
name='pool2/3x3_s2')(pool2_helper)
conv3_1_3x3_s1 = Conv2D(128, (3, 3),
strides=(1, 1),
padding='same',
activation='relu',
name='conv3_1/3x3_s1',
kernel_regularizer=l2(l2_regulizer))(pool2_3x3_s2)
conv3_2_3x3_s1 = Conv2D(
128, (3, 3),
strides=(1, 1),
padding='same',
activation='relu',
name='conv3_2/3x3_s1',
kernel_regularizer=l2(l2_regulizer))(conv3_1_3x3_s1)
conv3_zero_pad = ZeroPadding2D(padding=(1, 1))(conv3_2_3x3_s1)
pool3_helper = PoolHelper()(conv3_zero_pad)
pool3_2_2x2_s1 = MaxPooling2D(pool_size=(2, 2),
strides=(1, 1),
padding='same',
name='pool3/2x2_s1')(pool3_helper)
pool3_norm1 = LRN(name='pool3/norm1')(pool3_2_2x2_s1)
conv4_1_3x3_reduce = Conv2D(
256, (1, 1),
padding='same',
activation='relu',
name='conv4_1/3x3_reduce',
kernel_regularizer=l2(l2_regulizer))(pool3_norm1)
conv4_2_3x3 = Conv2D(
256, (3, 3),
padding='same',
activation='relu',
name='conv4_2/3x3',
kernel_regularizer=l2(l2_regulizer))(conv4_1_3x3_reduce)
conv4_norm2 = LRN(name='conv4/norm2')(conv4_2_3x3)
conv4_zero_pad = ZeroPadding2D(padding=(1, 1))(conv4_norm2)
pool4_helper = PoolHelper()(conv4_zero_pad)
pool4_3x3_s2 = MaxPooling2D(pool_size=(3, 3),
strides=(2, 2),
padding='same',
name='pool4/3x3_s2')(pool4_helper)
conv5_1_3x3_s1 = Conv2D(512, (3, 3),
strides=(1, 1),
padding='same',
activation='relu',
name='conv5_1/3x3_s1',
kernel_regularizer=l2(l2_regulizer))(pool4_3x3_s2)
conv5_2_3x3_s1 = Conv2D(
512, (3, 3),
strides=(1, 1),
padding='same',
activation='relu',
name='conv5_2/3x3_s1',
kernel_regularizer=l2(l2_regulizer))(conv5_1_3x3_s1)
conv5_zero_pad = ZeroPadding2D(padding=(1, 1))(conv5_2_3x3_s1)
pool5_helper = PoolHelper()(conv5_zero_pad)
pool5_2_2x2_s1 = MaxPooling2D(pool_size=(2, 2),
strides=(1, 1),
padding='same',
name='pool5/2x2_s1')(pool5_helper)
pool5_norm1 = LRN(name='pool5/norm1')(pool5_2_2x2_s1)
conv6_1_3x3_reduce = Conv2D(
1024, (1, 1),
padding='same',
activation='relu',
name='conv6_1/3x3_reduce',
kernel_regularizer=l2(l2_regulizer))(pool5_norm1)
conv6_2_3x3 = Conv2D(
1024, (3, 3),
padding='same',
activation='relu',
name='conv6_2/3x3',
kernel_regularizer=l2(l2_regulizer))(conv6_1_3x3_reduce)
conv6_norm2 = LRN(name='conv6/norm2')(conv6_2_3x3)
conv6_zero_pad = ZeroPadding2D(padding=(1, 1))(conv6_norm2)
pool6_helper = PoolHelper()(conv6_zero_pad)
pool6_3x3_s2 = MaxPooling2D(pool_size=(3, 3),
strides=(2, 2),
padding='same',
name='pool6/3x3_s2')(pool6_helper)
pool7_2x2_s1 = AveragePooling2D(pool_size=(2, 2),
strides=(1, 1),
name='pool7/2x2_s1')(pool6_3x3_s2)
loss_flat = Flatten()(pool7_2x2_s1)
pool7_drop_2x2_s1 = Dropout(rate=0.5)(loss_flat)
loss_classifier = Dense(
num_classes,
name='loss3/classifier',
kernel_regularizer=l2(l2_regulizer))(pool7_drop_2x2_s1)
loss_classifier_act = Activation('softmax', name='prob')(loss_classifier)
mynet = Model(inputs=input, outputs=[loss_classifier_act])
if weights_path:
mynet.load_weights(weights_path)
if keras.backend.backend() == 'tensorflow':
# convert the convolutional kernels for tensorflow
ops = []
for layer in mynet.layers:
if layer.__class__.__name__ == 'Conv2D':
original_w = K.get_value(layer.kernel)
converted_w = convert_kernel(original_w)
ops.append(tf.assign(layer.kernel, converted_w).op)
K.get_session().run(ops)
return mynet
ops.append(tf.assign(layer.kernel, converted_w).op)
K.get_session().run(ops)
return mynet
if __name__ == "__main__":
filepath2 = filepath + aug
filepath += aug + "_weights-{epoch:02d}-{loss:.4f}.hdf5"
# Test pretrained model
if checkpoint == 'n':
model = create_cnn_model() #'googlenet_weights.h5'
elif checkpoint == 'model':
custom_objects = {'PoolHelper': PoolHelper(), 'LRN': LRN()}
filepath2 += "my_cnn_model.h5"
model = tf.keras.models.load_model(filepath2,
custom_objects=custom_objects)
else:
filepath2 += "my_cnn_weights.h5"
model = create_cnn_model(filepath2)
if optimizer == 'sgd':
optim = SGD(lr=0.01, decay=1e-6, momentum=0.9, nesterov=True)
else:
optim = Adam(
lr=0.001, beta_1=0.9, beta_2=0.999, epsilon=1e-8
) #epsilon=1e-08, for Keras; epsilon=1e-08 for tensorflow; epsilon=1e-8 for Tocrch or MxNet
model.compile(
optimizer=optim,