Я использую предварительно обученную модель ResNet50 в качестве строительного блока для Unet:
def ResNet50(include_top=True, weights='imagenet',
input_tensor=None, input_shape=None,
pooling=None,
classes=1000):
if weights not in {'imagenet', None}:
raise ValueError('The `weights` argument should be either '
'`None` (random initialization) or `imagenet` '
'(pre-training on ImageNet).')
if weights == 'imagenet' and include_top and classes != 1000:
raise ValueError('If using `weights` as imagenet with `include_top`'
' as true, `classes` should be 1000')
if input_tensor is None:
img_input = Input(shape=input_shape)
else:
if not K.is_keras_tensor(input_tensor):
img_input = Input(tensor=input_tensor, shape=input_shape)
else:
img_input = input_tensor
if K.image_data_format() == 'channels_last':
bn_axis = 3
else:
bn_axis = 1
x = Conv2D(64, (7, 7), strides=(2, 2), padding='same', name='conv1')(img_input)
x = BatchNormalization(axis=bn_axis, name='bn_conv1')(x)
x = Activation('relu')(x)
x = MaxPooling2D((3, 3), strides=(2, 2), padding="same")(x)
x = conv_block(x, 3, [64, 64, 256], stage=2, block='a', strides=(1, 1))
x = identity_block(x, 3, [64, 64, 256], stage=2, block='b')
x = identity_block(x, 3, [64, 64, 256], stage=2, block='c')
x = conv_block(x, 3, [128, 128, 512], stage=3, block='a')
x = identity_block(x, 3, [128, 128, 512], stage=3, block='b')
x = identity_block(x, 3, [128, 128, 512], stage=3, block='c')
x = identity_block(x, 3, [128, 128, 512], stage=3, block='d')
x = conv_block(x, 3, [256, 256, 1024], stage=4, block='a')
x = identity_block(x, 3, [256, 256, 1024], stage=4, block='b')
x = identity_block(x, 3, [256, 256, 1024], stage=4, block='c')
x = identity_block(x, 3, [256, 256, 1024], stage=4, block='d')
x = identity_block(x, 3, [256, 256, 1024], stage=4, block='e')
x = identity_block(x, 3, [256, 256, 1024], stage=4, block='f')
x = conv_block(x, 3, [512, 512, 2048], stage=5, block='a')
x = identity_block(x, 3, [512, 512, 2048], stage=5, block='b')
x = identity_block(x, 3, [512, 512, 2048], stage=5, block='c')
# Ensure that the model takes into account
# any potential predecessors of `input_tensor`.
if input_tensor is not None:
inputs = get_source_inputs(input_tensor)
else:
inputs = img_input
# Create model.
model = Model(inputs, x, name='resnet50')
# load weights
if weights == 'imagenet':
if include_top:
weights_path = get_file('resnet50_weights_tf_dim_ordering_tf_kernels.h5',
WEIGHTS_PATH,
cache_subdir='models',
md5_hash='a7b3fe01876f51b976af0dea6bc144eb')
else:
weights_path = get_file('resnet50_weights_tf_dim_ordering_tf_kernels_notop.h5',
WEIGHTS_PATH_NO_TOP,
cache_subdir='models',
md5_hash='a268eb855778b3df3c7506639542a6af')
model.load_weights(weights_path,by_name=True)
return model
Создание Unet:
def conv_block_simple(prevlayer, filters, prefix, strides=(1, 1)):
conv = Conv2D(filters, (3, 3), padding="same", kernel_initializer="he_normal", strides=strides, name=prefix + "_conv")(prevlayer)
conv = BatchNormalization(name=prefix + "_bn")(conv)
conv = Activation('relu', name=prefix + "_activation")(conv)
return conv
def conv_block_simple_no_bn(prevlayer, filters, prefix, strides=(1, 1)):
conv = Conv2D(filters, (3, 3), padding="same", kernel_initializer="he_normal", strides=strides, name=prefix + "_conv")(prevlayer)
conv = Activation('relu', name=prefix + "_activation")(conv)
return conv
K.clear_session()
def get_unet_resnet(input_shape):
resnet_base = ResNet50(input_shape=input_shape, include_top=False)
for l in resnet_base.layers:
l.trainable = False
conv1 = resnet_base.get_layer("activation_1").output
conv2 = resnet_base.get_layer("activation_10").output
conv3 = resnet_base.get_layer("activation_22").output
conv4 = resnet_base.get_layer("activation_40").output
conv5 = resnet_base.get_layer("activation_49").output
up6 = concatenate([UpSampling2D()(conv5), conv4], axis=-1)
conv6 = conv_block_simple(up6, 256, "conv6_1")
conv6 = conv_block_simple(conv6, 256, "conv6_2")
up7 = concatenate([UpSampling2D()(conv6), conv3], axis=-1)
conv7 = conv_block_simple(up7, 192, "conv7_1")
conv7 = conv_block_simple(conv7, 192, "conv7_2")
up8 = concatenate([UpSampling2D()(conv7), conv2], axis=-1)
conv8 = conv_block_simple(up8, 128, "conv8_1")
conv8 = conv_block_simple(conv8, 128, "conv8_2")
up9 = concatenate([UpSampling2D()(conv8), conv1], axis=-1)
conv9 = conv_block_simple(up9, 64, "conv9_1")
conv9 = conv_block_simple(conv9, 64, "conv9_2")
up10 = UpSampling2D()(conv9)
conv10 = conv_block_simple(up10, 32, "conv10_1")
conv10 = conv_block_simple(conv10, 32, "conv10_2")
conv10 = SpatialDropout2D(0.2)(conv10)
x = Conv2D(1, (1, 1), activation="sigmoid", name="prediction")(conv10)
model = Model(resnet_base.input, x)
model.summary()
return model
Я заморозил предварительно обученные слои ResNet50, как предлагалось в нескольких статьях:
for l in resnet_base.layers:
l.trainable = False
Без заморозки сеть работает нормально, но имеет тенденцию к чрезмерной перегрузке, которую я уменьшил с более высоким значением SpatialDropout2D().Однако, когда я замораживаю его, потери поезда уменьшаются, но потери валидации распространяются на какое-то странное высокое значение, но на самом деле стагнируют.Я не могу понять, почему замороженная сеть работает на обучающем множестве, а на проверочном множестве - нет.Я не вижу логической причины для этого (на моем текущем уровне знаний).
Я пытался играть со скоростью обучения, но безуспешно.
В чем может быть проблема?Любая помощь будет высоко оценен.Спасибо.