def create_actor_network(self, state_size, action_dim):
"""Create actor network."""
print ("[MESSAGE] Build actor network.""")
S = Input(shape=state_size)
h_0 = Conv2D(32, (3, 3), padding="same",
kernel_regularizer=l2(0.0001),
activation="relu")(S)
h_1 = Conv2D(32, (3, 3), padding="same",
kernel_regularizer=l2(0.0001),
activation="relu")(h_0)
h_1 = AveragePooling2D(2, 2)(h_1)
h_1 = Flatten()(h_1)
h_1 = Dense(600, activation="relu")(h_1)
A = Dense(action_dim, activation="softmax")(h_1)
model = Model(inputs=S, outputs=A)
return model, model.trainable_weights, S
python类AveragePooling2D()的实例源码
def addTransition(previousLayer, nChannels, nOutChannels, dropRate, blockNum):
bn = BatchNormalization(name = 'tr_BatchNorm_{}'.format(blockNum), axis = 1)(previousLayer)
relu = Activation('relu', name ='tr_relu_{}'.format(blockNum))(bn)
conv = Convolution2D(nOutChannels, 1, 1, border_mode='same', name='tr_conv_{}'.format(blockNum))(relu)
if dropRate is not None:
dp = Dropout(dropRate, name='tr_dropout_{}'.format)(conv)
avgPool = AveragePooling2D(pool_size=(2, 2))(dp)
else:
avgPool = AveragePooling2D(pool_size=(2, 2))(conv)
return avgPool
def createModel(w=None,h=None):
# Input placeholder
original = Input(shape=(w, h, 4), name='icon_goes_here')
# Model layer stack
x = original
x = Convolution2D(64, 4, 4, activation='relu', border_mode='same', b_regularizer=l2(0.1))(x)
x = Convolution2D(64, 4, 4, activation='relu', border_mode='same', b_regularizer=l2(0.1))(x)
x = Convolution2D(64, 4, 4, activation='relu', border_mode='same', b_regularizer=l2(0.1))(x)
x = Convolution2D(64, 4, 4, activation='relu', border_mode='same', b_regularizer=l2(0.1))(x)
x = AveragePooling2D((2, 2), border_mode='valid')(x)
x = Convolution2D(16, 4, 4, activation='relu', border_mode='same', b_regularizer=l2(0.1))(x)
x = Convolution2D(4, 4, 4, activation='relu', border_mode='same', b_regularizer=l2(0.1))(x)
downscaled = x
# Compile model
hintbot = Model(input=original, output=downscaled)
hintbot.compile(optimizer='adam', loss='mean_squared_error')
# Train
if (os.path.isfile(load_weights_filepath)):
hintbot.load_weights(load_weights_filepath)
return hintbot
def classifier_layers(x, input_shape, stage_num, trainable=False):
# compile times on theano tend to be very high, so we use smaller ROI pooling regions to workaround
# (hence a smaller stride in the region that follows the ROI pool)
if K.backend() == 'tensorflow':
x = conv_block_td(x, 3, [512, 512, 1024], stage=stage_num, block='a', input_shape=input_shape, strides=(1, 2), trainable=trainable)
elif K.backend() == 'theano':
x = conv_block_td(x, 3, [512, 512, 1024], stage=stage_num, block='a', input_shape=input_shape, strides=(1, 1), trainable=trainable)
print 'INFO: Classifier layers x block a: ', x
x = identity_block_td(x, 3, [512, 512, 1024], stage=stage_num, block='c', trainable=trainable)
print 'INFO: Classifier layers x block b: ', x
x = identity_block_td(x, 3, [512, 512, 1024], stage=stage_num, block='d', trainable=trainable)
print 'INFO: Classifier layers x block c: ', x
#x = TimeDistributed(AveragePooling2D((2, 1)), name='avg_pool')(x)
return x
def block_inception_a(input):
if K.image_dim_ordering() == "th":
channel_axis = 1
else:
channel_axis = -1
branch_0 = conv2d_bn(input, 96, 1, 1)
branch_1 = conv2d_bn(input, 64, 1, 1)
branch_1 = conv2d_bn(branch_1, 96, 3, 3)
branch_2 = conv2d_bn(input, 64, 1, 1)
branch_2 = conv2d_bn(branch_2, 96, 3, 3)
branch_2 = conv2d_bn(branch_2, 96, 3, 3)
branch_3 = AveragePooling2D((3,3), strides=(1,1), border_mode='same')(input)
branch_3 = conv2d_bn(branch_3, 96, 1, 1)
x = merge([branch_0, branch_1, branch_2, branch_3], mode='concat', concat_axis=channel_axis)
return x
def block_inception_b(input):
if K.image_dim_ordering() == "th":
channel_axis = 1
else:
channel_axis = -1
branch_0 = conv2d_bn(input, 384, 1, 1)
branch_1 = conv2d_bn(input, 192, 1, 1)
branch_1 = conv2d_bn(branch_1, 224, 1, 7)
branch_1 = conv2d_bn(branch_1, 256, 7, 1)
branch_2 = conv2d_bn(input, 192, 1, 1)
branch_2 = conv2d_bn(branch_2, 192, 7, 1)
branch_2 = conv2d_bn(branch_2, 224, 1, 7)
branch_2 = conv2d_bn(branch_2, 224, 7, 1)
branch_2 = conv2d_bn(branch_2, 256, 1, 7)
branch_3 = AveragePooling2D((3,3), strides=(1,1), border_mode='same')(input)
branch_3 = conv2d_bn(branch_3, 128, 1, 1)
x = merge([branch_0, branch_1, branch_2, branch_3], mode='concat', concat_axis=channel_axis)
return x
def _initialize_model(self):
input_layer = Input(shape=self.input_shape)
tower_1 = Convolution2D(16, 1, 1, border_mode="same", activation="elu")(input_layer)
tower_1 = Convolution2D(16, 3, 3, border_mode="same", activation="elu")(tower_1)
tower_2 = Convolution2D(16, 1, 1, border_mode="same", activation="elu")(input_layer)
tower_2 = Convolution2D(16, 3, 3, border_mode="same", activation="elu")(tower_2)
tower_2 = Convolution2D(16, 3, 3, border_mode="same", activation="elu")(tower_2)
tower_3 = MaxPooling2D((3, 3), strides=(1, 1), border_mode="same")(input_layer)
tower_3 = Convolution2D(16, 1, 1, border_mode="same", activation="elu")(tower_3)
merged_layer = merge([tower_1, tower_2, tower_3], mode="concat", concat_axis=1)
output = AveragePooling2D((7, 7), strides=(8, 8))(merged_layer)
output = Flatten()(output)
output = Dense(self.action_count)(output)
model = Model(input=input_layer, output=output)
model.compile(rmsprop(lr=self.model_learning_rate, clipvalue=1), "mse")
return model
def resnet(repetition=2, k=1):
'''Wide Residual Network (with a slight modification)
depth == repetition*6 + 2
'''
from keras.models import Model
from keras.layers import Input, Dense, Flatten, AveragePooling2D
from keras.regularizers import l2
input_shape = (1, _img_len, _img_len)
output_dim = len(_columns)
x = Input(shape=input_shape)
z = conv2d(nb_filter=8, k_size=5, downsample=True)(x) # out_shape == 8, _img_len/ 2, _img_len/ 2
z = bn_lrelu(0.01)(z)
z = residual_block(nb_filter=k*16, repetition=repetition)(z) # out_shape == k*16, _img_len/ 4, _img_len/ 4
z = residual_block(nb_filter=k*32, repetition=repetition)(z) # out_shape == k*32, _img_len/ 8, _img_len/ 8
z = residual_block(nb_filter=k*64, repetition=repetition)(z) # out_shape == k*64, _img_len/16, _img_len/16
z = AveragePooling2D((_img_len/16, _img_len/16))(z)
z = Flatten()(z)
z = Dense(output_dim=output_dim, activation='sigmoid', W_regularizer=l2(_Wreg_l2), init='zero')(z)
return Model(input=x, output=z)
def make_model(
img_shape, charset_features, layer_name='block2_conv1',
output_pool=2, pool_type='max'):
if K.image_dim_ordering():
num_chars, char_h, char_w, char_channels = charset_features.shape
axis = -1
else:
num_chars, char_channels, char_h, char_w = charset_features.shape
axis = 1
vgg = vgg16.VGG16(input_shape=img_shape, include_top=False)
layer = vgg.get_layer(layer_name)
x = layer.output
# TODO: theano dim order
features_W = charset_features.transpose((1, 2, 3, 0)).astype(np.float32)
features_W = features_W[::-1, ::-1, :, :] / np.sqrt(np.sum(np.square(features_W), axis=(0, 1), keepdims=True))
x = BatchNormalization(mode=2)(x)
x = Convolution2D(
num_chars, char_h, char_w, border_mode='valid',
weights=[features_W, np.zeros(num_chars)])(x)
if output_pool > 1:
pool_class = dict(max=MaxPooling2D, avg=AveragePooling2D)[pool_type]
x = pool_class((output_pool, output_pool))(x)
#x = Argmax(axis)(x)
model = Model([vgg.input], [x])
return model
layers_builder.py 文件源码
项目：PSPNet-Keras-tensorflow
作者: Vladkryvoruchko
项目源码
文件源码
阅读 22
收藏 0
点赞 0
评论 0
def interp_block(prev_layer, level, feature_map_shape, input_shape):
if input_shape == (473, 473):
kernel_strides_map = {1: 60,
2: 30,
3: 20,
6: 10}
elif input_shape == (713, 713):
kernel_strides_map = {1: 90,
2: 45,
3: 30,
6: 15}
else:
print("Pooling parameters for input shape ", input_shape, " are not defined.")
exit(1)
names = [
"conv5_3_pool" + str(level) + "_conv",
"conv5_3_pool" + str(level) + "_conv_bn"
]
kernel = (kernel_strides_map[level], kernel_strides_map[level])
strides = (kernel_strides_map[level], kernel_strides_map[level])
prev_layer = AveragePooling2D(kernel, strides=strides)(prev_layer)
prev_layer = Conv2D(512, (1, 1), strides=(1, 1), name=names[0],
use_bias=False)(prev_layer)
prev_layer = BN(name=names[1])(prev_layer)
prev_layer = Activation('relu')(prev_layer)
prev_layer = Lambda(Interp, arguments={'shape': feature_map_shape})(prev_layer)
return prev_layer
def create_critic_network(self, state_size, action_dim):
"""create critic network."""
print ("[MESSAGE] Build critic network.""")
S = Input(shape=state_size)
A = Input(shape=(action_dim,))
# input
h_0 = Conv2D(32, (3, 3), padding="same",
kernel_regularizer=l2(0.0001),
activation="relu")(S)
h_1 = Conv2D(32, (3, 3), padding="same",
kernel_regularizer=l2(0.0001),
activation="relu")(h_0)
h_1 = AveragePooling2D(2, 2)(h_1)
h_1 = Flatten()(h_1)
h_1 = Dense(600, activation="relu")(h_1)
# action
a_1 = Dense(600, activation="linear")(A)
h_2 = add([h_1, a_1])
h_3 = Dense(600, activation="relu")(h_2)
V = Dense(action_dim, activation="softmax")(h_3)
model = Model(inputs=[S, A], outputs=V)
model.compile(loss='categorical_crossentropy',
optimizer="adam")
return model, A, S
def _add_auxiliary_head(x, classes, weight_decay):
'''Adds an auxiliary head for training the model
From section A.7 "Training of ImageNet models" of the paper, all NASNet models are
trained using an auxiliary classifier around 2/3 of the depth of the network, with
a loss weight of 0.4
# Arguments
x: input tensor
classes: number of output classes
weight_decay: l2 regularization weight
# Returns
a keras Tensor
'''
img_height = 1 if K.image_data_format() == 'channels_last' else 2
img_width = 2 if K.image_data_format() == 'channels_last' else 3
channel_axis = 1 if K.image_data_format() == 'channels_first' else -1
with K.name_scope('auxiliary_branch'):
auxiliary_x = Activation('relu')(x)
auxiliary_x = AveragePooling2D((5, 5), strides=(3, 3), padding='valid', name='aux_pool')(auxiliary_x)
auxiliary_x = Conv2D(128, (1, 1), padding='same', use_bias=False, name='aux_conv_projection',
kernel_initializer='he_normal', kernel_regularizer=l2(weight_decay))(auxiliary_x)
auxiliary_x = BatchNormalization(axis=channel_axis, momentum=_BN_DECAY, epsilon=_BN_EPSILON,
name='aux_bn_projection')(auxiliary_x)
auxiliary_x = Activation('relu')(auxiliary_x)
auxiliary_x = Conv2D(768, (auxiliary_x._keras_shape[img_height], auxiliary_x._keras_shape[img_width]),
padding='valid', use_bias=False, kernel_initializer='he_normal',
kernel_regularizer=l2(weight_decay), name='aux_conv_reduction')(auxiliary_x)
auxiliary_x = BatchNormalization(axis=channel_axis, momentum=_BN_DECAY, epsilon=_BN_EPSILON,
name='aux_bn_reduction')(auxiliary_x)
auxiliary_x = Activation('relu')(auxiliary_x)
auxiliary_x = GlobalAveragePooling2D()(auxiliary_x)
auxiliary_x = Dense(classes, activation='softmax', kernel_regularizer=l2(weight_decay),
name='aux_predictions')(auxiliary_x)
return auxiliary_x
def get_squeezenet(nb_classes):
input_img = Input(shape=(3, 227, 227))
x = Convolution2D(96, 7, 7, subsample=(2, 2), border_mode='valid')(input_img)
x = Activation('relu')(x)
x = MaxPooling2D(pool_size=(3, 3), strides=(2, 2))(x)
x = fire_module(x, 16, 64)
x = fire_module(x, 16, 64)
x = fire_module(x, 32, 128)
x = MaxPooling2D(pool_size=(3, 3), strides=(2, 2))(x)
x = fire_module(x, 32, 192)
x = fire_module(x, 48, 192)
x = fire_module(x, 48, 192)
x = fire_module(x, 64, 256)
x = MaxPooling2D(pool_size=(3, 3), strides=(2, 2))(x)
x = fire_module(x, 64, 256)
x = Dropout(0.5)(x)
x = ZeroPadding2D(padding=(1, 1))(x)
x = Convolution2D(nb_classes, 1, 1, border_mode='valid')(x)
# global pooling not available
x = AveragePooling2D(pool_size=(15, 15))(x)
x = Flatten()(x)
out = Dense(nb_classes, activation='softmax')(x)
model = Model(input=input_img, output=[out])
return model
def get_small_squeezenet(nb_classes):
input_img = Input(shape=(3, 32, 32))
x = Convolution2D(16, 3, 3, border_mode='same')(input_img)
x = Activation('relu')(x)
x = MaxPooling2D(pool_size=(3, 3))(x)
x = fire_module(x, 32, 128)
x = fire_module(x, 32, 128)
x = MaxPooling2D(pool_size=(2, 2))(x)
x = fire_module(x, 48, 192)
x = fire_module(x, 48, 192)
x = MaxPooling2D(pool_size=(2, 2))(x)
x = fire_module(x, 64, 256)
x = Dropout(0.5)(x)
x = ZeroPadding2D(padding=(1, 1))(x)
x = Convolution2D(nb_classes, 1, 1, border_mode='valid')(x)
# global pooling not available
x = AveragePooling2D(pool_size=(4, 4))(x)
x = Flatten()(x)
out = Dense(nb_classes, activation='softmax')(x)
model = Model(input=input_img, output=[out])
return model
def define_model(image_shape):
img_input = Input(shape=image_shape)
x = Convolution2D(32, 3, 3, subsample=(1, 1), border_mode='same')(img_input)
x = res_block(x, nb_filters=32, block=0, subsample_factor=1)
x = res_block(x, nb_filters=32, block=0, subsample_factor=1)
x = res_block(x, nb_filters=32, block=0, subsample_factor=1)
x = res_block(x, nb_filters=64, block=1, subsample_factor=2)
x = res_block(x, nb_filters=64, block=1, subsample_factor=1)
x = res_block(x, nb_filters=64, block=1, subsample_factor=1)
x = res_block(x, nb_filters=128, block=2, subsample_factor=2)
x = res_block(x, nb_filters=128, block=2, subsample_factor=1)
x = res_block(x, nb_filters=128, block=2, subsample_factor=1)
x = res_block(x, nb_filters=128, block=2, subsample_factor=1)
x = res_block(x, nb_filters=256, block=3, subsample_factor=2)
x = res_block(x, nb_filters=256, block=3, subsample_factor=1)
x = res_block(x, nb_filters=256, block=3, subsample_factor=1)
x = res_block(x, nb_filters=256, block=3, subsample_factor=1)
x = res_block(x, nb_filters=512, block=4, subsample_factor=2)
x = res_block(x, nb_filters=512, block=4, subsample_factor=1)
x = res_block(x, nb_filters=512, block=4, subsample_factor=1)
x = res_block(x, nb_filters=512, block=4, subsample_factor=1)
x = BatchNormalization(axis=3)(x)
x = Activation('relu')(x)
x = AveragePooling2D(pool_size=(3, 3), strides=(2, 2), border_mode='valid')(x)
x = Flatten()(x)
x = Dense(1, activation='sigmoid', name='predictions')(x)
model = Model(img_input, x)
model.compile(optimizer='adam', loss='binary_crossentropy', metrics=['accuracy', 'precision', 'recall', 'fmeasure'])
model.summary()
return model
def define_model(image_shape):
img_input = Input(shape=image_shape)
x = Convolution2D(32, 3, 3, subsample=(1, 1), border_mode='same')(img_input)
x = res_block(x, nb_filters=32, block=0, subsample_factor=1)
x = res_block(x, nb_filters=32, block=0, subsample_factor=1)
x = res_block(x, nb_filters=32, block=0, subsample_factor=1)
x = res_block(x, nb_filters=64, block=1, subsample_factor=2)
x = res_block(x, nb_filters=64, block=1, subsample_factor=1)
x = res_block(x, nb_filters=64, block=1, subsample_factor=1)
x = res_block(x, nb_filters=128, block=2, subsample_factor=2)
x = res_block(x, nb_filters=128, block=2, subsample_factor=1)
x = res_block(x, nb_filters=128, block=2, subsample_factor=1)
x = res_block(x, nb_filters=128, block=2, subsample_factor=1)
x = res_block(x, nb_filters=256, block=3, subsample_factor=2)
x = res_block(x, nb_filters=256, block=3, subsample_factor=1)
x = res_block(x, nb_filters=256, block=3, subsample_factor=1)
x = res_block(x, nb_filters=256, block=3, subsample_factor=1)
x = res_block(x, nb_filters=512, block=4, subsample_factor=2)
x = res_block(x, nb_filters=512, block=4, subsample_factor=1)
x = res_block(x, nb_filters=512, block=4, subsample_factor=1)
x = res_block(x, nb_filters=512, block=4, subsample_factor=1)
x = BatchNormalization(axis=3)(x)
x = Activation('relu')(x)
x = AveragePooling2D(pool_size=(3, 3), strides=(2, 2), border_mode='valid')(x)
x = Flatten()(x)
x = Dense(1, activation='sigmoid', name='predictions')(x)
model = Model(img_input, x)
model.compile(optimizer='adam', loss='binary_crossentropy', metrics=['accuracy', 'precision', 'recall', 'fmeasure'])
model.summary()
return model
def define_model(image_shape, transfer_weights_filepath):
img_input = Input(shape=image_shape)
x = Convolution2D(32, 3, 3, subsample=(1, 1), border_mode='same')(img_input)
x = res_block(x, nb_filters=32, block=0, subsample_factor=1)
x = res_block(x, nb_filters=32, block=0, subsample_factor=1)
x = res_block(x, nb_filters=32, block=0, subsample_factor=1)
x = res_block(x, nb_filters=64, block=1, subsample_factor=2)
x = res_block(x, nb_filters=64, block=1, subsample_factor=1)
x = res_block(x, nb_filters=64, block=1, subsample_factor=1)
x = res_block(x, nb_filters=128, block=2, subsample_factor=2)
x = res_block(x, nb_filters=128, block=2, subsample_factor=1)
x = res_block(x, nb_filters=128, block=2, subsample_factor=1)
x = res_block(x, nb_filters=128, block=2, subsample_factor=1)
x = res_block(x, nb_filters=256, block=3, subsample_factor=2)
x = res_block(x, nb_filters=256, block=3, subsample_factor=1)
x = res_block(x, nb_filters=256, block=3, subsample_factor=1)
x = res_block(x, nb_filters=256, block=3, subsample_factor=1)
x = BatchNormalization(axis=3)(x)
x = Activation('relu')(x)
x = AveragePooling2D(pool_size=(3, 3), strides=(2, 2), border_mode='valid')(x)
x = Flatten()(x)
x_orig = Dense(1, activation='sigmoid')(x)
model_base = Model(img_input, x_orig)
model_base.load_weights(transfer_weights_filepath)
bbox = Dense(4, activation='linear', name='bbox')(x)
model_bbox = Model(img_input, bbox)
model_bbox.compile(optimizer='adam', loss='mae')
model_bbox.summary()
return model_bbox
def define_model(image_shape, transfer_weights_filepath):
img_input = Input(shape=image_shape)
x = Convolution2D(32, 3, 3, subsample=(1, 1), border_mode='same')(img_input)
x = res_block(x, nb_filters=32, block=0, subsample_factor=1)
x = res_block(x, nb_filters=32, block=0, subsample_factor=1)
x = res_block(x, nb_filters=32, block=0, subsample_factor=1)
x = res_block(x, nb_filters=64, block=1, subsample_factor=2)
x = res_block(x, nb_filters=64, block=1, subsample_factor=1)
x = res_block(x, nb_filters=64, block=1, subsample_factor=1)
x = res_block(x, nb_filters=128, block=2, subsample_factor=2)
x = res_block(x, nb_filters=128, block=2, subsample_factor=1)
x = res_block(x, nb_filters=128, block=2, subsample_factor=1)
x = res_block(x, nb_filters=128, block=2, subsample_factor=1)
x = res_block(x, nb_filters=256, block=3, subsample_factor=2)
x = res_block(x, nb_filters=256, block=3, subsample_factor=1)
x = res_block(x, nb_filters=256, block=3, subsample_factor=1)
x = res_block(x, nb_filters=256, block=3, subsample_factor=1)
x = BatchNormalization(axis=3)(x)
x = Activation('relu')(x)
x = AveragePooling2D(pool_size=(3, 3), strides=(2, 2), border_mode='valid')(x)
x = Flatten()(x)
x_orig = Dense(1, activation='sigmoid')(x)
model_base = Model(img_input, x_orig)
model_base.load_weights(transfer_weights_filepath)
bbox = Dense(4, activation='linear', name='bbox')(x)
model_bbox = Model(img_input, bbox)
model_bbox.compile(optimizer='adam', loss='mae')
model_bbox.summary()
return model_bbox
def define_model(image_shape):
img_input = Input(shape=image_shape)
x = Convolution2D(128, 3, 3, subsample=(1, 1), border_mode='same')(img_input)
x = res_block(x, nb_filters=128, block=0, subsample_factor=1)
x = res_block(x, nb_filters=128, block=0, subsample_factor=1)
x = res_block(x, nb_filters=128, block=0, subsample_factor=1)
x = res_block(x, nb_filters=256, block=0, subsample_factor=2)
x = res_block(x, nb_filters=256, block=0, subsample_factor=1)
x = res_block(x, nb_filters=256, block=0, subsample_factor=1)
x = res_block(x, nb_filters=512, block=0, subsample_factor=2)
x = res_block(x, nb_filters=512, block=0, subsample_factor=1)
x = res_block(x, nb_filters=512, block=0, subsample_factor=1)
x = res_block(x, nb_filters=1024, block=0, subsample_factor=2)
x = res_block(x, nb_filters=1024, block=0, subsample_factor=1)
x = res_block(x, nb_filters=1024, block=0, subsample_factor=1)
x = BatchNormalization(axis=3)(x)
x = Activation('relu')(x)
x = AveragePooling2D(pool_size=(3, 3), strides=(2, 2), border_mode='valid')(x)
x = Flatten()(x)
x = Dense(1, activation='sigmoid', name='predictions')(x)
model = Model(img_input, x)
model.compile(optimizer='adam', loss='binary_crossentropy', metrics=['accuracy', 'precision', 'recall'])
model.summary()
return model
def define_model(image_shape):
img_input = Input(shape=image_shape)
x = Convolution2D(128, 3, 3, subsample=(1, 1), border_mode='same')(img_input)
x = res_block(x, nb_filters=128, block=0, subsample_factor=1)
x = res_block(x, nb_filters=128, block=0, subsample_factor=1)
x = res_block(x, nb_filters=128, block=0, subsample_factor=1)
x = res_block(x, nb_filters=256, block=1, subsample_factor=2)
x = res_block(x, nb_filters=256, block=1, subsample_factor=1)
x = res_block(x, nb_filters=256, block=1, subsample_factor=1)
x = res_block(x, nb_filters=512, block=2, subsample_factor=2)
x = res_block(x, nb_filters=512, block=2, subsample_factor=1)
x = res_block(x, nb_filters=512, block=2, subsample_factor=1)
x = BatchNormalization(axis=3)(x)
x = Activation('relu')(x)
x = AveragePooling2D(pool_size=(8, 8))(x)
x = Flatten()(x)
x = Dropout(0.2)(x)
x = Dense(1, activation='sigmoid', name='predictions')(x)
model = Model(img_input, x)
model.compile(optimizer='adam', loss='binary_crossentropy', metrics=['accuracy', 'precision', 'recall', 'fmeasure'])
model.summary()
return model
def define_model():
img_input = Input(shape=(32, 32, 1))
x = Convolution2D(32, 3, 3, subsample=(1, 1), border_mode='same')(img_input)
x = res_block(x, nb_filters=32, block=0, subsample_factor=1)
x = res_block(x, nb_filters=32, block=0, subsample_factor=1)
x = res_block(x, nb_filters=32, block=0, subsample_factor=1)
x = res_block(x, nb_filters=64, block=1, subsample_factor=2)
x = res_block(x, nb_filters=64, block=1, subsample_factor=1)
x = res_block(x, nb_filters=64, block=1, subsample_factor=1)
x = res_block(x, nb_filters=128, block=2, subsample_factor=2)
x = res_block(x, nb_filters=128, block=2, subsample_factor=1)
x = res_block(x, nb_filters=128, block=2, subsample_factor=1)
x = res_block(x, nb_filters=128, block=2, subsample_factor=1)
x = res_block(x, nb_filters=256, block=3, subsample_factor=2)
x = res_block(x, nb_filters=256, block=3, subsample_factor=1)
x = res_block(x, nb_filters=256, block=3, subsample_factor=1)
x = res_block(x, nb_filters=256, block=3, subsample_factor=1)
x = BatchNormalization(axis=3)(x)
x = Activation('relu')(x)
x = AveragePooling2D(pool_size=(3, 3), strides=(2, 2), border_mode='valid')(x)
x = Flatten()(x)
bbox = Dense(4, activation='linear', name='bbox')(x)
model_bbox = Model(img_input, bbox)
model_bbox.compile(optimizer='adam', loss='mae')
return model_bbox
def define_model():
img_input = Input(shape=(32, 32, 2))
x = Convolution2D(32, 3, 3, subsample=(1, 1), border_mode='same')(img_input)
x = res_block(x, nb_filters=32, block=0, subsample_factor=1)
x = res_block(x, nb_filters=32, block=0, subsample_factor=1)
x = res_block(x, nb_filters=32, block=0, subsample_factor=1)
x = res_block(x, nb_filters=64, block=1, subsample_factor=2)
x = res_block(x, nb_filters=64, block=1, subsample_factor=1)
x = res_block(x, nb_filters=64, block=1, subsample_factor=1)
x = res_block(x, nb_filters=128, block=2, subsample_factor=2)
x = res_block(x, nb_filters=128, block=2, subsample_factor=1)
x = res_block(x, nb_filters=128, block=2, subsample_factor=1)
x = res_block(x, nb_filters=128, block=2, subsample_factor=1)
x = res_block(x, nb_filters=256, block=3, subsample_factor=2)
x = res_block(x, nb_filters=256, block=3, subsample_factor=1)
x = res_block(x, nb_filters=256, block=3, subsample_factor=1)
x = res_block(x, nb_filters=256, block=3, subsample_factor=1)
x = BatchNormalization(axis=3)(x)
x = Activation('relu')(x)
x = AveragePooling2D(pool_size=(3, 3), strides=(2, 2), border_mode='valid')(x)
x = Flatten()(x)
bbox = Dense(4, activation='linear', name='bbox')(x)
model_bbox = Model(img_input, bbox)
model_bbox.compile(optimizer='adam', loss='mae')
return model_bbox
def define_model():
img_input = Input(shape=(64, 64, 3))
x = Convolution2D(32, 3, 3, subsample=(1, 1), border_mode='same')(img_input)
x = res_block(x, nb_filters=32, block=0, subsample_factor=1)
x = res_block(x, nb_filters=32, block=0, subsample_factor=1)
x = res_block(x, nb_filters=32, block=0, subsample_factor=1)
x = res_block(x, nb_filters=64, block=1, subsample_factor=2)
x = res_block(x, nb_filters=64, block=1, subsample_factor=1)
x = res_block(x, nb_filters=64, block=1, subsample_factor=1)
x = res_block(x, nb_filters=128, block=2, subsample_factor=2)
x = res_block(x, nb_filters=128, block=2, subsample_factor=1)
x = res_block(x, nb_filters=128, block=2, subsample_factor=1)
x = res_block(x, nb_filters=128, block=2, subsample_factor=1)
x = res_block(x, nb_filters=256, block=3, subsample_factor=2)
x = res_block(x, nb_filters=256, block=3, subsample_factor=1)
x = res_block(x, nb_filters=256, block=3, subsample_factor=1)
x = res_block(x, nb_filters=256, block=3, subsample_factor=1)
x = res_block(x, nb_filters=512, block=4, subsample_factor=2)
x = res_block(x, nb_filters=512, block=4, subsample_factor=1)
x = res_block(x, nb_filters=512, block=4, subsample_factor=1)
x = res_block(x, nb_filters=512, block=4, subsample_factor=1)
x = BatchNormalization(axis=3)(x)
x = Activation('relu')(x)
x = AveragePooling2D(pool_size=(3, 3), strides=(2, 2), border_mode='valid')(x)
x = Flatten()(x)
x = Dense(1, activation='sigmoid', name='predictions')(x)
model = Model(img_input, x)
model.compile(optimizer='adam', loss='binary_crossentropy')
return model
def define_model():
img_input = Input(shape=(64, 64, 5))
x = Convolution2D(32, 3, 3, subsample=(1, 1), border_mode='same')(img_input)
x = res_block(x, nb_filters=32, block=0, subsample_factor=1)
x = res_block(x, nb_filters=32, block=0, subsample_factor=1)
x = res_block(x, nb_filters=32, block=0, subsample_factor=1)
x = res_block(x, nb_filters=64, block=1, subsample_factor=2)
x = res_block(x, nb_filters=64, block=1, subsample_factor=1)
x = res_block(x, nb_filters=64, block=1, subsample_factor=1)
x = res_block(x, nb_filters=128, block=2, subsample_factor=2)
x = res_block(x, nb_filters=128, block=2, subsample_factor=1)
x = res_block(x, nb_filters=128, block=2, subsample_factor=1)
x = res_block(x, nb_filters=128, block=2, subsample_factor=1)
x = res_block(x, nb_filters=256, block=3, subsample_factor=2)
x = res_block(x, nb_filters=256, block=3, subsample_factor=1)
x = res_block(x, nb_filters=256, block=3, subsample_factor=1)
x = res_block(x, nb_filters=256, block=3, subsample_factor=1)
x = res_block(x, nb_filters=512, block=4, subsample_factor=2)
x = res_block(x, nb_filters=512, block=4, subsample_factor=1)
x = res_block(x, nb_filters=512, block=4, subsample_factor=1)
x = res_block(x, nb_filters=512, block=4, subsample_factor=1)
x = BatchNormalization(axis=3)(x)
x = Activation('relu')(x)
x = AveragePooling2D(pool_size=(3, 3), strides=(2, 2), border_mode='valid')(x)
x = Flatten()(x)
x = Dense(1, activation='sigmoid', name='predictions')(x)
model = Model(img_input, x)
model.compile(optimizer='adam', loss='binary_crossentropy')
return model
def define_model():
img_input = Input(shape=(32, 32, 1))
x = Convolution2D(32, 3, 3, subsample=(1, 1), border_mode='same')(img_input)
x = res_block(x, nb_filters=32, block=0, subsample_factor=1)
x = res_block(x, nb_filters=32, block=0, subsample_factor=1)
x = res_block(x, nb_filters=32, block=0, subsample_factor=1)
x = res_block(x, nb_filters=64, block=1, subsample_factor=2)
x = res_block(x, nb_filters=64, block=1, subsample_factor=1)
x = res_block(x, nb_filters=64, block=1, subsample_factor=1)
x = res_block(x, nb_filters=128, block=2, subsample_factor=2)
x = res_block(x, nb_filters=128, block=2, subsample_factor=1)
x = res_block(x, nb_filters=128, block=2, subsample_factor=1)
x = BatchNormalization(axis=3)(x)
x = Activation('relu')(x)
x = AveragePooling2D(pool_size=(8, 8))(x)
x = Flatten()(x)
x = Dense(1, activation='sigmoid', name='predictions')(x)
model = Model(img_input, x)
model.compile(optimizer='adam', loss='binary_crossentropy')
return model
def define_model():
img_input = Input(shape=(32, 32, 1))
x = Convolution2D(128, 3, 3, subsample=(1, 1), border_mode='same')(img_input)
x = res_block(x, nb_filters=128, block=0, subsample_factor=1)
x = res_block(x, nb_filters=128, block=0, subsample_factor=1)
x = res_block(x, nb_filters=128, block=0, subsample_factor=1)
x = res_block(x, nb_filters=256, block=1, subsample_factor=2)
x = res_block(x, nb_filters=256, block=1, subsample_factor=1)
x = res_block(x, nb_filters=256, block=1, subsample_factor=1)
x = res_block(x, nb_filters=512, block=2, subsample_factor=2)
x = res_block(x, nb_filters=512, block=2, subsample_factor=1)
x = res_block(x, nb_filters=512, block=2, subsample_factor=1)
x = BatchNormalization(axis=3)(x)
x = Activation('relu')(x)
x = AveragePooling2D(pool_size=(8, 8))(x)
x = Flatten()(x)
x = Dense(1, activation='sigmoid', name='predictions')(x)
model = Model(img_input, x)
model.compile(optimizer='adam', loss='binary_crossentropy')
return model
def test_delete_channels_averagepooling2d(channel_index, data_format):
layer = AveragePooling2D([2, 3], data_format=data_format)
layer_test_helper_flatten_2d(layer, channel_index, data_format)
def test_average_pooling_no_overlap(self):
# no_overlap: pool_size = strides
model = Sequential()
model.add(AveragePooling2D(input_shape=(16,16,3), pool_size=(2, 2),
strides=None, padding='valid'))
self._test_keras_model(model, delta=1e-2)
def test_average_pooling_inception_config_1(self):
# no_overlap: pool_size = strides
model = Sequential()
model.add(AveragePooling2D(input_shape=(16,16,3), pool_size=(3,3),
strides=(1,1), padding='same'))
self._test_keras_model(model, delta=1e-2)
def test_tiny_mcrnn_td(self):
model = Sequential()
model.add(Conv2D(3,(1,1), input_shape=(2,4,4), padding='same'))
model.add(AveragePooling2D(pool_size=(2,2)))
model.add(Reshape((2,3)))
model.add(TimeDistributed(Dense(5)))
self._test_keras_model(model)
