def create_simple_model(num_classes, layer1_filters=32, layer2_filters=64):
epochs = 5
n_conv = 2
model = models.Sequential()
# First layer
model.add(conv.ZeroPadding2D(
(1, 1),
input_shape=(1, IMG_COLS, IMG_ROWS),
))
model.add(
conv.Convolution2D(layer1_filters, n_conv, n_conv, activation="relu"))
model.add(conv.MaxPooling2D(strides=(2, 2)))
# Second layer
model.add(conv.ZeroPadding2D((1, 1)))
model.add(
conv.Convolution2D(layer2_filters, n_conv, n_conv, activation="relu"))
model.add(conv.MaxPooling2D(strides=(2, 2)))
model.add(core.Flatten())
model.add(core.Dropout(0.2))
model.add(core.Dense(128, activation="relu"))
model.add(core.Dense(num_classes, activation="softmax"))
model.summary()
model.compile(loss="categorical_crossentropy",
optimizer="adadelta",
metrics=["accuracy"])
return model, epochs
def Alex_Net(IMG_SIZE, class_num=16):
model = Sequential()
model.add(
Conv2D(96, (11, 11),
strides=(4, 4),
padding="valid",
input_shape=(IMG_SIZE[0], IMG_SIZE[1], 3),
kernel_regularizer=l2(0.0002)))
model.add(Activation("relu"))
model.add(BatchNormalization(axis=-1))
model.add(MaxPooling2D(pool_size=(3, 3), strides=(2, 2)))
model.add(Dropout(0.25))
model.add(
convolutional.ZeroPadding2D(padding=(2, 2), dim_ordering='default'))
model.add(
Conv2D(256, (5, 5), padding="valid", kernel_regularizer=l2(0.0002)))
model.add(Activation("relu"))
model.add(BatchNormalization(axis=-1))
model.add(MaxPooling2D(pool_size=(3, 3), strides=(2, 2)))
model.add(Dropout(0.25))
model.add(
convolutional.ZeroPadding2D(padding=(1, 1), dim_ordering='default'))
model.add(
Conv2D(384, (3, 3), padding="valid", kernel_regularizer=l2(0.0002)))
model.add(Activation("relu"))
model.add(BatchNormalization(axis=-1))
model.add(
convolutional.ZeroPadding2D(padding=(1, 1), dim_ordering='default'))
model.add(
Conv2D(384, (3, 3), padding="valid", kernel_regularizer=l2(0.0002)))
model.add(Activation("relu"))
model.add(BatchNormalization(axis=-1))
model.add(
convolutional.ZeroPadding2D(padding=(1, 1), dim_ordering='default'))
model.add(
Conv2D(256, (3, 3), padding="valid", kernel_regularizer=l2(0.0002)))
model.add(MaxPooling2D(pool_size=(3, 3), strides=(2, 2)))
model.add(Dropout(0.25))
model.add(Flatten())
model.add(Dense(4096, kernel_regularizer=l2(0.0002)))
model.add(Activation("relu"))
model.add(BatchNormalization(axis=-1))
model.add(Dropout(0.25))
model.add(Dense(4096, kernel_regularizer=l2(0.0002)))
model.add(Activation("relu"))
model.add(BatchNormalization(axis=-1))
model.add(Dropout(0.25))
model.add(Dense(class_num, kernel_regularizer=l2(0.0002)))
model.add(Activation("softmax"))
return model
def test_zero_padding_2d():
num_samples = 2
stack_size = 2
input_num_row = 4
input_num_col = 5
for data_format in ['channels_first', 'channels_last']:
inputs = np.ones((num_samples, input_num_row, input_num_col, stack_size))
inputs = np.ones((num_samples, stack_size, input_num_row, input_num_col))
# basic test
layer_test(convolutional.ZeroPadding2D,
kwargs={'padding': (2, 2), 'data_format': data_format},
input_shape=inputs.shape)
layer_test(convolutional.ZeroPadding2D,
kwargs={'padding': ((1, 2), (3, 4)), 'data_format': data_format},
input_shape=inputs.shape)
# correctness test
layer = convolutional.ZeroPadding2D(padding=(2, 2),
data_format=data_format)
layer.build(inputs.shape)
outputs = layer(K.variable(inputs))
np_output = K.eval(outputs)
if data_format == 'channels_last':
for offset in [0, 1, -1, -2]:
assert_allclose(np_output[:, offset, :, :], 0.)
assert_allclose(np_output[:, :, offset, :], 0.)
assert_allclose(np_output[:, 2:-2, 2:-2, :], 1.)
elif data_format == 'channels_first':
for offset in [0, 1, -1, -2]:
assert_allclose(np_output[:, :, offset, :], 0.)
assert_allclose(np_output[:, :, :, offset], 0.)
assert_allclose(np_output[:, 2:-2, 2:-2, :], 1.)
layer = convolutional.ZeroPadding2D(padding=((1, 2), (3, 4)),
data_format=data_format)
layer.build(inputs.shape)
outputs = layer(K.variable(inputs))
np_output = K.eval(outputs)
if data_format == 'channels_last':
for top_offset in [0]:
assert_allclose(np_output[:, top_offset, :, :], 0.)
for bottom_offset in [-1, -2]:
assert_allclose(np_output[:, bottom_offset, :, :], 0.)
for left_offset in [0, 1, 2]:
assert_allclose(np_output[:, :, left_offset, :], 0.)
for right_offset in [-1, -2, -3, -4]:
assert_allclose(np_output[:, :, right_offset, :], 0.)
assert_allclose(np_output[:, 1:-2, 3:-4, :], 1.)
elif data_format == 'channels_first':
for top_offset in [0]:
assert_allclose(np_output[:, :, top_offset, :], 0.)
for bottom_offset in [-1, -2]:
assert_allclose(np_output[:, :, bottom_offset, :], 0.)
for left_offset in [0, 1, 2]:
assert_allclose(np_output[:, :, :, left_offset], 0.)
for right_offset in [-1, -2, -3, -4]:
assert_allclose(np_output[:, :, :, right_offset], 0.)
assert_allclose(np_output[:, :, 1:-2, 3:-4], 1.)
def test_zero_padding_2d():
nb_samples = 9
stack_size = 7
input_nb_row = 11
input_nb_col = 12
input = np.ones((nb_samples, stack_size, input_nb_row, input_nb_col))
layer = convolutional.ZeroPadding2D(padding=(2, 2))
layer.input = K.variable(input)
for train in [True, False]:
out = K.eval(layer.get_output(train))
for offset in [0, 1, -1, -2]:
assert_allclose(out[:, :, offset, :], 0.)
assert_allclose(out[:, :, :, offset], 0.)
assert_allclose(out[:, :, 2:-2, 2:-2], 1.)
layer.get_config()
def test_zero_padding_2d(self):
nb_samples = 9
stack_size = 7
input_nb_row = 11
input_nb_col = 12
input = np.ones((nb_samples, stack_size, input_nb_row, input_nb_col))
layer = convolutional.ZeroPadding2D(pad=(2,2))
layer.input = theano.shared(value=input)
for train in [True, False]:
out = layer.get_output(train).eval()
for offset in [0,1,-1,-2]:
assert_allclose(out[:, :, offset, :], 0.)
assert_allclose(out[:, :, :, offset], 0.)
assert_allclose(out[:, :, 2:-2, 2:-2], 1.)
config = layer.get_config()
def test_mixing_preprocessing_and_regular_layers(self):
x0 = Input(shape=(10, 10, 3))
x1 = Input(shape=(10, 10, 3))
x2 = Input(shape=(10, 10, 3))
y0 = merge.Add()([x0, x1])
y1 = image_preprocessing.CenterCrop(8, 8)(x2)
y1 = convolutional.ZeroPadding2D(padding=1)(y1)
z = merge.Add()([y0, y1])
z = normalization.Normalization()(z)
z = convolutional.Conv2D(4, 3)(z)
stage = preprocessing_stage.FunctionalPreprocessingStage([x0, x1, x2],
z)
data = [
np.ones((12, 10, 10, 3), dtype='float32'),
np.ones((12, 10, 10, 3), dtype='float32'),
np.ones((12, 10, 10, 3), dtype='float32')
]
stage.adapt(data)
_ = stage(data)
stage.compile('rmsprop', 'mse')
with self.assertRaisesRegex(ValueError, 'Preprocessing stage'):
stage.fit(data, np.ones((12, 8, 8, 4)))
ds_x0 = tf.data.Dataset.from_tensor_slices(np.ones((12, 10, 10, 3)))
ds_x1 = tf.data.Dataset.from_tensor_slices(np.ones((12, 10, 10, 3)))
ds_x2 = tf.data.Dataset.from_tensor_slices(np.ones((12, 10, 10, 3)))
ds_x = tf.data.Dataset.zip((ds_x0, ds_x1, ds_x2))
ds_y = tf.data.Dataset.from_tensor_slices(np.ones((12, 8, 8, 4)))
dataset = tf.data.Dataset.zip((ds_x, ds_y)).batch(4)
with self.assertRaisesRegex(ValueError, 'Preprocessing stage'):
stage.fit(dataset)
_ = stage.evaluate(data, np.ones((12, 8, 8, 4)))
_ = stage.predict(data)
def test_zero_padding_2d():
nb_samples = 2
stack_size = 2
input_nb_row = 11
input_nb_col = 12
input = np.ones((nb_samples, stack_size, input_nb_row, input_nb_col))
# basic test
layer_test(convolutional.ZeroPadding2D,
kwargs={'padding': (2, 2)},
input_shape=input.shape)
# correctness test
layer = convolutional.ZeroPadding2D(padding=(2, 2))
layer.set_input(K.variable(input), shape=input.shape)
out = K.eval(layer.output)
for offset in [0, 1, -1, -2]:
assert_allclose(out[:, :, offset, :], 0.)
assert_allclose(out[:, :, :, offset], 0.)
assert_allclose(out[:, :, 2:-2, 2:-2], 1.)
layer.get_config()
def test_zero_padding_2d():
nb_samples = 2
stack_size = 2
input_nb_row = 4
input_nb_col = 5
dim_ordering = K.image_dim_ordering()
assert dim_ordering in {'tf', 'th'}, 'dim_ordering must be in {tf, th}'
if dim_ordering == 'tf':
input = np.ones((nb_samples, input_nb_row, input_nb_col, stack_size))
elif dim_ordering == 'th':
input = np.ones((nb_samples, stack_size, input_nb_row, input_nb_col))
# basic test
layer_test(convolutional.ZeroPadding2D,
kwargs={'padding': (2, 2)},
input_shape=input.shape)
layer_test(convolutional.ZeroPadding2D,
kwargs={'padding': (1, 2, 3, 4)},
input_shape=input.shape)
layer_test(convolutional.ZeroPadding2D,
kwargs={'padding': {'top_pad': 1, 'bottom_pad': 2, 'left_pad': 3, 'right_pad': 4}},
input_shape=input.shape)
# correctness test
layer = convolutional.ZeroPadding2D(padding=(2, 2))
layer.build(input.shape)
output = layer(K.variable(input))
np_output = K.eval(output)
if dim_ordering == 'tf':
for offset in [0, 1, -1, -2]:
assert_allclose(np_output[:, offset, :, :], 0.)
assert_allclose(np_output[:, :, offset, :], 0.)
assert_allclose(np_output[:, 2:-2, 2:-2, :], 1.)
elif dim_ordering == 'th':
for offset in [0, 1, -1, -2]:
assert_allclose(np_output[:, :, offset, :], 0.)
assert_allclose(np_output[:, :, :, offset], 0.)
assert_allclose(np_output[:, 2:-2, 2:-2, :], 1.)
layer = convolutional.ZeroPadding2D(padding=(1, 2, 3, 4))
layer.build(input.shape)
output = layer(K.variable(input))
np_output = K.eval(output)
if dim_ordering == 'tf':
for top_offset in [0]:
assert_allclose(np_output[:, top_offset, :, :], 0.)
for bottom_offset in [-1, -2]:
assert_allclose(np_output[:, bottom_offset, :, :], 0.)
for left_offset in [0, 1, 2]:
assert_allclose(np_output[:, :, left_offset, :], 0.)
for right_offset in [-1, -2, -3, -4]:
assert_allclose(np_output[:, :, right_offset, :], 0.)
assert_allclose(np_output[:, 1:-2, 3:-4, :], 1.)
elif dim_ordering == 'th':
for top_offset in [0]:
assert_allclose(np_output[:, :, top_offset, :], 0.)
for bottom_offset in [-1, -2]:
assert_allclose(np_output[:, :, bottom_offset, :], 0.)
for left_offset in [0, 1, 2]:
assert_allclose(np_output[:, :, :, left_offset], 0.)
for right_offset in [-1, -2, -3, -4]:
assert_allclose(np_output[:, :, :, right_offset], 0.)
assert_allclose(np_output[:, :, 1:-2, 3:-4], 1.)
layer.get_config()
import keras.optimizers as kopt
# read data from hard drive
train_data_raw = pd.read_csv("./input/train.csv").values
test_data_raw = pd.read_csv("./input/test.csv").values
img_cols = 28
img_rows = 28
train_X = train_data_raw[:, 1:].reshape(train_data_raw.shape[0], 1, img_rows, img_cols)
train_Y = kutils.to_categorical(train_data_raw[:, 0])
num_class = train_Y.shape[1]
num_filters_1 = 64
conv_dim = 3
cnn = kmodels.Sequential()
cnn.add(kconv.ZeroPadding2D((1,1), input_shape=(1, 28, 28),))
cnn.add(kconv.Convolution2D(num_filters_1, conv_dim, conv_dim, activation="relu"))
cnn.add(kpool.MaxPooling2D(strides=(2, 2)))
num_filters_2 = 128
cnn.add(kconv.ZeroPadding2D((1, 1)))
cnn.add(kconv.Convolution2D(num_filters_2, conv_dim, conv_dim, activation="relu"))
cnn.add(kpool.MaxPooling2D(strides=(2, 2)))
conv_dim_2 = 3
cnn.add(kconv.ZeroPadding2D((1, 1)))
cnn.add(kconv.Convolution2D(num_filters_2, conv_dim_2, conv_dim_2, activation="relu"))
cnn.add(kpool.MaxPooling2D(strides=(2, 2)))
cnn.add(kconv.ZeroPadding2D((1, 1)))
cnn.add(kconv.Convolution2D(num_filters_2, conv_dim_2, conv_dim_2, activation="relu"))
nb_filters_1 = 32 # 64
nb_filters_2 = 64 # 128
nb_filters_3 = 128 # 256
nb_conv = 3
trainX = train[:, 1:].reshape(train.shape[0], 1, img_rows, img_cols)
trainX = trainX.astype(float)
trainX /= 255.0 # preprocess the data
trainY = kutils.to_categorical(train[:, 0])
nb_classes = trainY.shape[1]
cnn = models.Sequential()
cnn.add(conv.ZeroPadding2D(
(1, 1),
input_shape=(1, 48, 48),
))
cnn.add(conv.Convolution2D(32, 3, 3, activation="relu"))
cnn.add(conv.ZeroPadding2D((1, 1)))
cnn.add(conv.Convolution2D(32, 3, 3, activation="relu"))
cnn.add(conv.MaxPooling2D(strides=(2, 2)))
cnn.add(conv.ZeroPadding2D((1, 1)))
cnn.add(conv.Convolution2D(64, 3, 3, activation="relu"))
cnn.add(conv.ZeroPadding2D((1, 1)))
cnn.add(conv.Convolution2D(64, 3, 3, activation="relu"))
cnn.add(conv.MaxPooling2D(strides=(2, 2)))
# cnn.add(conv.ZeroPadding2D((1, 1)))
# cnn.add(conv.Convolution2D(nb_filters_3, nb_conv, nb_conv, activation="relu"))
# cnn.add(conv.ZeroPadding2D((1, 1)))
filters = [64, 128]
kernel = 3
pool = 2
trainX = train[:, 1:].reshape(train.shape[0], 1, img_rows, img_cols)
trainX = trainX.astype(float)
trainX /= 255.0
trainY = kutils.to_categorical(train[:, 0])
nb_classes = trainY.shape[1]
cnn = models.Sequential()
cnn.add(conv.ZeroPadding2D(
(1, 1),
input_shape=(1, img_rows, img_cols),
))
cnn.add(conv.Convolution2D(filters[0], kernel, kernel))
cnn.add(core.Activation('relu'))
cnn.add(conv.MaxPooling2D(strides=(pool, pool)))
cnn.add(conv.ZeroPadding2D((1, 1)))
cnn.add(conv.Convolution2D(filters[1], kernel, kernel))
cnn.add(core.Activation('relu'))
cnn.add(conv.MaxPooling2D(strides=(pool, pool)))
cnn.add(conv.ZeroPadding2D((1, 1)))
cnn.add(core.Flatten())
#build CCPM
#使用max pooling而不是k-max pooling,实验的结果证明,max pooling的效果略好于k-max pooling
print ('Build model...')
convs = []
main_input = Input(shape=(maxlen,), dtype='int32')
embedding_map = Embedding(output_dim=embedding_dims, input_dim=max_features,
input_length=maxlen,W_regularizer=l2(reg_conf[0]))(main_input)
for index in range(embedding_dims):
print ("i:",index)
t = Lambda(slice,output_shape=(maxlen,1),arguments={'index':index},
name='slice_'+str(index+1))(embedding_map)
x = Reshape((maxlen,1,1))(t)
#第一层conv and pooling
x = convolutional.ZeroPadding2D(padding=(w1-1,0))(x)
#卷积1后的尺寸conv1
conv1 = maxlen+w1-1
x = Convolution2D(m1,w1,1,border_mode='valid',subsample=(1,1),
activation='linear',dim_ordering='tf',W_regularizer=l2(reg_conf[1]),
b_regularizer=l2(reg_conf[1]))(x)
#池化1的尺寸pool1
pool1 = 2#conv1+1-L1
print ("第一层pool size:",pool1)
x = MaxPooling2D(pool_size=(pool1,1),strides=(2,1),
border_mode='valid',dim_ordering='tf')(x)
#x = Activation('tanh')(x)
x = Activation('sigmoid')(x)
#第二层conv and pooling
x = convolutional.ZeroPadding2D(padding=(w2-2,0))(x)
def convnet_alexnet_lion_keras(image_dims):
# model = Sequential()
# model.add(Lambda(lambda x: (x / 255.0) - 0.5, input_shape=image_dims))
NR_CLASSES = 6
input = layers.Input(shape=image_dims, name="Input")
conv_1 = convolutional.Convolution2D(96,
11,
11,
border_mode='valid',
name="conv_1",
activation='relu',
init='glorot_uniform')(input)
pool_1 = convolutional.MaxPooling2D(pool_size=(3, 3),
name="pool_1")(conv_1)
zero_padding_1 = convolutional.ZeroPadding2D(padding=(1, 1),
name="zero_padding_1")(pool_1)
conv_2 = convolutional.Convolution2D(256,
3,
3,
border_mode='valid',
name="conv_2",
activation='relu',
init='glorot_uniform')(zero_padding_1)
pool_2 = convolutional.MaxPooling2D(pool_size=(3, 3),
name="pool_2")(conv_2)
zero_padding_2 = keras.layers.convolutional.ZeroPadding2D(
padding=(1, 1), name="zero_padding_2")(pool_2)
conv_3 = convolutional.Convolution2D(384,
3,
3,
border_mode='valid',
name="conv_3",
activation='relu',
init='glorot_uniform')(zero_padding_2)
conv_4 = convolutional.Convolution2D(384,
3,
3,
border_mode='valid',
name="conv_4",
activation='relu',
init='glorot_uniform')(conv_3)
conv_5 = convolutional.Convolution2D(256,
3,
3,
border_mode='valid',
name="conv_5",
activation='relu',
init='glorot_uniform')(conv_4)
pool_3 = convolutional.MaxPooling2D(pool_size=(3, 3),
name="pool_3")(conv_5)
flatten = core.Flatten(name="flatten")(pool_3)
fc_1 = core.Dense(4096,
name="fc_1",
activation='relu',
init='glorot_uniform')(flatten)
fc_1 = core.Dropout(0.5, name="fc_1_dropout")(fc_1)
output = core.Dense(4096,
name="Output",
activation='relu',
init='glorot_uniform')(fc_1)
output = core.Dropout(0.5, name="Output_dropout")(output)
fc_2 = core.Dense(NR_CLASSES,
name="fc_2",
activation='softmax',
init='glorot_uniform')(output)
return models.Model([input], [fc_2])
