def mk_model_with_bn():
model = Sequential()
model.add(
Convolution2D(filters=64,
kernel_size=(3, 3),
strides=(1, 1),
input_shape=(IMAGE_SIZE, IMAGE_SIZE, 1),
kernel_initializer=kernel_initializer()))
model.add(BatchNormalization())
model.add(Activation('relu'))
model.add(
Convolution2D(filters=64,
kernel_size=(3, 3),
strides=(1, 1),
kernel_initializer=kernel_initializer()))
model.add(BatchNormalization())
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Dropout(0.5))
model.add(
Convolution2D(filters=128,
kernel_size=(3, 3),
kernel_initializer=kernel_initializer()))
model.add(BatchNormalization())
model.add(Activation('relu'))
model.add(
Convolution2D(filters=128,
kernel_size=(3, 3),
kernel_initializer=kernel_initializer()))
model.add(BatchNormalization())
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Dropout(0.5))
model.add(
Convolution2D(filters=256,
kernel_size=(3, 3),
kernel_initializer=kernel_initializer()))
model.add(BatchNormalization())
model.add(Activation('relu'))
model.add(
Convolution2D(filters=256,
kernel_size=(3, 3),
kernel_initializer=kernel_initializer()))
model.add(BatchNormalization())
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Dropout(0.5))
model.add(Flatten())
model.add(Dense(256, kernel_initializer='he_normal'))
model.add(BatchNormalization())
model.add(Activation('relu'))
model.add(Dropout(0.5))
model.add(Dense(LABEL_NUM, kernel_initializer='he_normal'))
model.add(Activation('softmax'))
return model
def inference(input_shape, N_CLASSES):
'''build the model
args:
image: image batch, 4D tensor [batch_size, width, height, channels=3], dtype=tf.float32
return:
output tensor with the computed logits, float, [batch_size, n_classes]
'''
inputs = Input(shape=input_shape)
K.set_learning_phase(
False) # all new operations will be in test mode from now on
## Conv layer 1
x = dn_layer(inputs=inputs, name='layer1')
x = MaxPooling2D((2, 2), strides=(2, 2), name='layer1_maxpool')(x)
## Conv layer 2
x = dn_layer(inputs=x, num_filters=32, name='layer2')
x = MaxPooling2D((2, 2), strides=(2, 2), name='layer2_maxpool')(x)
## Conv layer 3
x = dn_layer(inputs=x, num_filters=64, name='layer3')
x = MaxPooling2D((2, 2), strides=(2, 2), name='layer3_maxpool')(x)
x = GlobalAveragePooling2D(name='GlobalAveragePooling2D')(x)
#x = Flatten(name='flatten')(x)
x = Dense(N_CLASSES, activation='softmax', name='predictions')(x)
model = Model(inputs=inputs, outputs=x)
return model
def main():
x_train, y_train, x_test, y_test = load_data()
model = Sequential()
model.add(
Conv2D(32,
kernel_size=(11, 11),
strides=4,
padding="same",
activation='relu',
input_shape=(48, 48, 1)))
model.add(MaxPooling2D(pool_size=(3, 3), strides=2, padding="valid"))
model.add(
Conv2D(32,
kernel_size=(5, 5),
strides=1,
padding="same",
activation='relu'))
model.add(MaxPooling2D(pool_size=(3, 3), strides=2, padding="valid"))
model.add(
Conv2D(32,
kernel_size=(3, 3),
strides=1,
padding="same",
activation='relu'))
model.add(
Conv2D(32,
kernel_size=(3, 3),
strides=1,
padding="same",
activation='relu'))
model.add(
Conv2D(32,
kernel_size=(3, 3),
strides=1,
padding="same",
activation='relu'))
model.add(Dense(1024, activation='relu'))
model.add(Dense(512, activation='relu'))
model.add(Dense(7, activation='softmax'))
model.compile(loss='binary_crossentropy',
optimizer='adam',
metrics=['accuracy'])
model.fit(x_train,
y_train,
batch_size=128,
epochs=5,
verbose=1,
validation_data=(x_test, y_test))
model.save(expanduser("~/emotion/alex_net.h5"))
accuracy, fbeta = test_model(model, x_test, y_test)
print("Accuracy: %s" % accuracy)
print("F-Beta: %s" % fbeta)
def model_fn(features, targets, mode, params):
"""Model function for Estimator."""
# 1. Configure the model via TensorFlow operations
# First, build all the model, a good idea is using Keras or tf.layers
# since these are high-level API's
conv1 = Conv2D(32, (5, 5), activation='relu',
input_shape=(28, 28, 1))(features)
pool1 = MaxPooling2D(pool_size=(2, 2))(conv1)
conv2 = Conv2D(64, (5, 5), activation='relu')(pool1)
pool2 = MaxPooling2D(pool_size=(2, 2))(conv2)
flat = Flatten()(pool2)
dense = Dense(1024, activation='relu')(flat)
preds = Dense(10, activation='softmax')(dense)
# 2. Define the loss function for training/evaluation
loss = None
train_op = None
# Calculate Loss (for both TRAIN and EVAL modes)
if mode != learn.ModeKeys.INFER:
loss = tf.losses.softmax_cross_entropy(onehot_labels=targets,
logits=preds)
# 3. Define the training operation/optimizer
# Configure the Training Op (for TRAIN mode)
if mode == learn.ModeKeys.TRAIN:
train_op = tf.contrib.layers.optimize_loss(
loss=loss,
global_step=tf.contrib.framework.get_global_step(),
learning_rate=params["learning_rate"],
optimizer="Adam",
)
# 4. Generate predictions
predictions_dict = {
"classes": tf.argmax(input=preds, axis=1),
"probabilities": tf.nn.softmax(preds, name="softmax_tensor")
}
# 5. Define how you want to evaluate the model
metrics = {
"accuracy":
tf.metrics.accuracy(tf.argmax(input=preds, axis=1),
tf.argmax(input=targets, axis=1))
}
# 6. Return predictions/loss/train_op/eval_metric_ops in ModelFnOps object
return model_fn_lib.ModelFnOps(mode=mode,
predictions=predictions_dict,
loss=loss,
train_op=train_op,
eval_metric_ops=metrics)
def discriminator_model():
model = Sequential()
model.add(Conv2D(64, (5, 5),padding='same',input_shape=(28, 28, 1)) )
model.add(Activation('tanh'))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Conv2D(128, (5, 5)))
model.add(Activation('tanh'))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Flatten())
model.add(Dense(1024))
model.add(Activation('tanh'))
model.add(Dense(1))
model.add(Activation('sigmoid'))
return model
def model_fn(features, labels, mode, params):
conv1 = Conv2D(32, (5, 5), activation='relu', input_shape=(28, 28, 1))(features["x"])
conv2 = Conv2D(64, (5, 5), activation='relu')(conv1)
conv3 = Conv2D(128, (2, 2), activation='relu')(conv2)
pool3 = MaxPooling2D(pool_size=(2, 2))(conv3)
conv4 = Conv2D(256, (5, 5), activation='relu')(pool3)
pool4 = MaxPooling2D(pool_size=(2, 2))(conv4)
flat = Flatten()(pool4)
dense1 = Dense(1024, activation='relu')(flat)
dense2 = Dense(1024, activation='relu')(dense1)
dense3 = Dense(1024, activation='relu')(dense2)
dense4 = Dense(1024, activation='relu')(dense3)
logits = Dense(10, activation='softmax')(dense4)
loss = tf.losses.softmax_cross_entropy(
onehot_labels=labels, logits=logits)
train_op = tf.contrib.layers.optimize_loss(
loss=loss,
global_step=tf.contrib.framework.get_global_step(),
learning_rate=params["learning_rate"],
optimizer="SGD")
predictions = {
"classes": tf.argmax(input=logits, axis=1),
"probabilities": tf.nn.softmax(logits)
}
eval_metric_ops = {
"accuracy": tf.metrics.accuracy(
tf.argmax(input=logits, axis=1),
tf.argmax(input=labels, axis=1))
}
return model_fn_lib.EstimatorSpec(
mode=mode,
predictions=predictions,
loss=loss,
train_op=train_op,
eval_metric_ops=eval_metric_ops)
def build(self, input_shape):
self.input_spec = [InputSpec(shape=input_shape)]
self.conv_layers = {c: [] for c in ['i', 'f', 'c', 'o', 'a', 'ahat']}
for l in range(self.nb_layers):
for c in ['i', 'f', 'c', 'o']:
act = self.LSTM_activation if c == 'c' else self.LSTM_inner_activation
self.conv_layers[c].append(
Convolution2D(self.R_stack_sizes[l],
self.R_filt_sizes[l],
padding='same',
data_format="channels_last",
activation=act))
act = 'relu' if l == 0 else self.A_activation
self.conv_layers['ahat'].append(
Convolution2D(self.stack_sizes[l],
self.Ahat_filt_sizes[l],
padding='same',
data_format="channels_last",
activation=act))
if l < self.nb_layers - 1:
self.conv_layers['a'].append(
Convolution2D(self.stack_sizes[l + 1],
self.A_filt_sizes[l],
padding='same',
data_format="channels_last",
activation=self.A_activation))
self.upsample = UpSampling2D(data_format="channels_last") # upsampling
self.pool = MaxPooling2D(data_format="channels_last") # downsampling
self._trainable_weights = []
nb_row, nb_col = (input_shape[-3], input_shape[-2])
# Super model
for c in sorted(self.conv_layers.keys()):
for l in range(len(self.conv_layers[c])):
ds_factor = 2**l
if c == 'ahat':
nb_channels = self.R_stack_sizes[l]
elif c == 'a':
nb_channels = 2 * self.stack_sizes[l]
else: # i, c, o, f
nb_channels = self.stack_sizes[l] * 2 + self.R_stack_sizes[
l]
if l < self.nb_layers - 1:
nb_channels += self.R_stack_sizes[l + 1]
in_shape = (input_shape[0], nb_row // ds_factor,
nb_col // ds_factor, nb_channels
) # up -> downsampling
self.conv_layers[c][l].build(in_shape)
self._trainable_weights += self.conv_layers[c][
l].trainable_weights
self.states = [None] * self.nb_layers * 3 # ['r', 'c', 'e']
if self.extrap_start_time is not None:
self.t_extrap = K.variable(np.array(self.extrap_start_time),
'int32')
self.states += [None] * 2
def mk_model(arch, data_type, classes):
if data_type == 'mnist':
channels = 1
elif data_type == 'aerial':
channels = 3
if arch == 'lenet-5':
model = Sequential() #モデルの初期化
#畳み込み第１層
model.add(Conv2D(
32, 5, padding='same',
input_shape=(28, 28, channels))) #output_shape=(None,28,28,32)
#filters=32, kernel_size=(5,5), strides(1,1), use_bias=True
#dilidation_rate(膨張率)=(1,1), kernel_initializer='glorot_uniform', bias_initializer='zeros'
#padding='sane'は出力のshapeが入力と同じになるように調整
#output_shape=(None(60000),28,28,32)
model.add(Activation('relu'))
model.add(MaxPooling2D(padding='same')) #output_shape=(None,14,14,32)
#pool_size=(2,2), strides(2,2)
#畳み込み第２層
model.add(Conv2D(64, 5, padding='same')) #output_shape=(None,14,14,64)
model.add(Activation('relu'))
model.add(MaxPooling2D(padding='same')) #output_shape=(None,7,7,64)
#平坦化
model.add(Flatten()) #output_shape=(None,3136(7*7*64))
#全結合第１層
model.add(Dense(1024)) #output_shape=(None,1024)
model.add(Activation('relu'))
model.add(Dropout(0.5)) #無視する割合を記述(例えば、0.2と記述した場合、80%の結合が残る)
#全結合第２層
model.add(Dense(classes)) #output_shape=(None,classes)
model.add(Activation('softmax'))
return model
elif arch == 'alexnet':
model = Sequential() #モデルの初期化
def build_model(num_output_classes):
conv1size = 32
conv2size = 64
convfiltsize = 4
densesize = 128
poolsize = (2, 2)
imgdepth = 3
dropout = 0.3
if IMG_COLORMODE == 'grayscale':
imgdepth = 1
inpshape = IMG_TGT_SIZE + (imgdepth, )
inputs = Input(shape=inpshape)
conv1 = Convolution2D(conv1size,
convfiltsize,
strides=(1, 1),
padding='valid',
activation='relu',
name='conv1',
data_format='channels_last')(inputs)
pool1 = MaxPooling2D(pool_size=poolsize, name='pool1')(conv1)
drop1 = Dropout(dropout)(pool1)
conv2 = Convolution2D(conv2size,
convfiltsize,
strides=(1, 1),
padding='valid',
activation='relu',
name='conv2',
data_format='channels_last')(drop1)
pool2 = MaxPooling2D(pool_size=poolsize, name='pool2')(conv2)
drop2 = Dropout(dropout)(pool2)
flat2 = Flatten()(drop2)
dense = Dense(densesize, name='dense')(flat2)
denseact = Activation('relu')(dense)
output = Dense(num_output_classes, name='output')(denseact)
outputact = Activation('softmax')(output)
model = Model(inputs=inputs, outputs=outputact)
model.compile(loss='categorical_crossentropy',
optimizer='adam',
metrics=['accuracy'])
return model
def simple_model():
model = Sequential()
model.add(
Convolution2D(filters=32,
kernel_size=(3, 3),
strides=(1, 1),
input_shape=(IMAGE_SIZE, IMAGE_SIZE, 1)))
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Convolution2D(filters=64, kernel_size=(3, 3)))
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Flatten())
model.add(Dense(256))
model.add(Activation('relu'))
model.add(Dropout(0.5))
model.add(Dense(LABEL_NUM))
model.add(Activation('softmax'))
return model
def mk_model():
model = Sequential()
model.add(
Convolution2D(filters=32,
kernel_size=(3, 3),
strides=(1, 1),
input_shape=(IMAGE_SIZE, IMAGE_SIZE, 1),
kernel_initializer=kernel_initializer()))
model.add(LeakyReLU(alpha=.1))
model.add(
Convolution2D(filters=32,
kernel_size=(3, 3),
strides=(1, 1),
kernel_initializer=kernel_initializer()))
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Dropout(0.5))
model.add(
Convolution2D(filters=64,
kernel_size=(3, 3),
kernel_initializer=kernel_initializer()))
model.add(LeakyReLU(alpha=0.1))
model.add(
Convolution2D(filters=64,
kernel_size=(3, 3),
kernel_initializer=kernel_initializer()))
model.add(LeakyReLU(alpha=0.1))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Dropout(0.5))
model.add(Flatten())
model.add(MaxoutDense(output_dim=256, nb_feature=4))
model.add(Activation('relu'))
model.add(Dropout(0.5))
model.add(Dense(LABEL_NUM, kernel_initializer='he_uniform'))
model.add(Activation('softmax'))
return model
def dw_conv(init, nb_filter, k):
residual = Conv2D(nb_filter * k, (1, 1),
strides=(2, 2),
padding='same',
use_bias=False)(init)
residual = BN(residual)
x = Conv2D(nb_filter * k, (3, 3), padding='same', use_bias=False)(init)
x = BN(x)
x = Activation('relu')(x)
x = Conv2D(nb_filter * k, (3, 3), padding='same', use_bias=False)(x)
x = BN(x)
x = MaxPooling2D((3, 3), strides=(2, 2), padding='same')(x)
x = layers.add([x, residual])
return x
def cnn_model_fn():
'''
define the model in function way
'''
# input shape is (img_rows, img_cols, fea_channel)
inputs = Input(shape=(img_rows, img_cols, 1))
x = Conv2D(32, kernel_size=(3, 3), activation='relu')(inputs)
x = Conv2D(64, (3, 3), activation='relu')(x)
x = MaxPooling2D(pool_size=(2, 2))(x)
x = Dropout(0.25)(x)
x = Flatten()(x)
x = Dense(128, activation='relu')(x)
x = Dropout(0.5)(x)
pred = Dense(num_classes, activation='softmax')(x)
# small change of Model parameters names, now is inputs, outputs
model = Model(inputs=inputs, outputs=pred)
model.compile(loss='categorical_crossentropy',
optimizer='adadelta',
metrics=['accuracy'])
return model
def cnn_model_tf(inputs):
'''
defin the model in tf way
'''
img, labels, keep_rate = inputs[0], inputs[1], inputs[2]
x = Conv2D(32, kernel_size=(3, 3), activation='relu')(img)
x = Conv2D(64, (3, 3), activation='relu')(x)
x = MaxPooling2D(pool_size=(2, 2))(x)
#x = Dropout(0.25)(x)
# mix with tf operator. ok.
x = tf.nn.dropout(x, keep_rate)
x = Flatten()(x)
x = Dense(128, activation='relu')(x)
#x = Dropout(0.5)(x)
x = tf.nn.dropout(x, keep_rate)
pred = Dense(num_classes, activation='softmax')(x)
loss = tf.reduce_mean(categorical_crossentropy(labels, pred))
# train
train_op = tf.train.AdadeltaOptimizer().minimize(loss)
correct_prediction = tf.equal(tf.argmax(pred, 1), tf.argmax(labels, 1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, 'float'))
return [train_op, accuracy]
def main():
training_images, training_labels, test_images, test_labels = load_dataset()
# plt.imshow(training_images[:,:,0], cmap='gray')
# plt.show()
N = training_labels.size
Nt = test_labels.size
perm_train = np.random.permutation(N)
training_labels = training_labels[perm_train]
training_images = training_images[perm_train, :, :] / 255.0
training_images = np.expand_dims(training_images, -1)
print(training_images.shape)
test_images = test_images / 255.0
test_images = np.expand_dims(test_images, -1)
# pdb.set_trace()
training_labels = to_categorical(training_labels, NUM_CLASSES)
test_labels = to_categorical(test_labels, NUM_CLASSES)
BATCH_SIZE = 32*8
WIDTH, HEIGHT = 28, 28
epochs = 5
# Defiining the placeholders
input_data = tf.placeholder(dtype=tf.float32, shape=[None, HEIGHT, WIDTH, 1], name='data')
input_labels = tf.placeholder(dtype=tf.float32, shape=[None, NUM_CLASSES], name='labels')
do_rate = tf.placeholder(dtype=tf.float32, name='dropout_rate')
# pdb.set_trace()
'''
with tf.name_scope('conv1'):
with tf.variable_scope('conv1'):
W_conv1 = tf.get_variable('w', [3,3,1,32])
b_conv1 = tf.get_variable('b', [32])
conv1 = tf.nn.conv2d(input=input_data, filter=W_conv1, strides=[1,1,1,1], padding='SAME')
relu1 = tf.nn.relu(conv1 + b_conv1)
with tf.name_scope('pool1'):
pool1 = tf.nn.max_pool(value=relu1, ksize=[1,2,2,1], strides=[1,2,2,1], padding='SAME')
with tf.name_scope('conv2'):
with tf.variable_scope('conv2'):
W_conv2 = tf.get_variable('w', [3,3,32,32])
b_conv2 = tf.get_variable('b', [32])
conv2 = tf.nn.conv2d(input=pool1, filter=W_conv2, strides=[1,1,1,1], padding='VALID')
relu2 = tf.nn.relu(conv2 + b_conv2)
with tf.name_scope('pool2'):
pool2 = tf.nn.max_pool(value=relu2, ksize=[1,2,2,1], strides=[1,2,2,1], padding='SAME')
with tf.name_scope('dense1'):
with tf.variable_scope('dense1'):
W_dense1 = tf.get_variable('w', [6*6*32,128])
b_dense1 = tf.get_variable('b', 128)
flat = tf.reshape(pool2, [-1,6*6*32], name='reshape')
dense1= tf.matmul(flat, W_dense1)
relu3 = tf.nn.relu(dense1 + b_dense1)
with tf.name_scope('dropout'):
dropout = tf.nn.dropout(relu3, do_rate)
with tf.name_scope('output'):
with tf.variable_scope('output'):
W_out = tf.get_variable('w', [128,NUM_CLASSES])
b_out = tf.get_variable('b', [NUM_CLASSES])
output = tf.matmul(dropout, W_out) + b_out
'''
print('-------------------------------------------------------')
""" Using Keras layers instead """
#input_layer = Input(shape=(HEIGHT, WIDTH, 1), name='input_layer')
Kcnn1 = Conv2D(filters=32, kernel_size=3, strides=(1,1), padding='same', activation='relu')(input_data)
Kmaxpool = MaxPooling2D(pool_size=2)(Kcnn1)
"""
with tf.name_scope('conv2'):
with tf.variable_scope('conv2'):
W_conv2 = tf.get_variable('w', [3,3,32,32])
b_conv2 = tf.get_variable('b', [32])
conv2 = tf.nn.conv2d(input=Kmaxpool, filter=W_conv2, strides=[1,1,1,1], padding='VALID')
Kcnn2 = tf.nn.relu(conv2 + b_conv2)
"""
Kcnn2 = Conv2D(filters=32, kernel_size=3, strides=(1,1), padding='valid', activation='relu')(Kmaxpool)
Kmaxpool = MaxPooling2D(pool_size=2)(Kcnn2)
Kflat = Flatten()(Kmaxpool)
Kdense1 = Dense(units=128, activation='relu')(Kflat)
Kdropout = Dropout(.5)(Kdense1)
output = Dense(units=NUM_CLASSES, activation='linear')(Kdropout)
""" The rest of the code is almost the same as in pure_tf_mnist.py,
except for the feed_dict, where instead of do_rate in tensorflow,
we need to provide keras specific dropout tensor 'learning_phase'
in the backend of Keras. """
print('-------------------------------------------------------')
print('\n\n')
print('-------------------------------------------------------')
print('--------------- Trainable parameters ------------------')
print('-------------------------------------------------------')
total_parameters = 0
for v in tf.trainable_variables():
shape = v.get_shape()
print(shape)
#pdb.set_trace()
params = 1
for dim in shape:
params *= dim.value
total_parameters += params
print('total_parameters = {}'.format(total_parameters))
print('-------------------------------------------------------\n\n')
loss = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(labels=input_labels, logits=output, name='loss'))
train_op = tf.train.AdamOptimizer(1e-4).minimize(loss)
accuracy = tf.cast(tf.equal(tf.argmax(input_labels, 1), tf.argmax(output, 1)), tf.float32)
# Training:
sess = tf.Session()
sess.run(tf.global_variables_initializer())
writer = tf.summary.FileWriter('graph', sess.graph)
for i in range(epochs):
steps = (int)(np.ceil(float(N)/float(BATCH_SIZE)))
total_l = 0
total_acc = 0
for step in range(steps):
x_in, y_in = get_batch(step, BATCH_SIZE, training_images, training_labels)
l, acc, _ = sess.run([loss, accuracy, train_op], {input_data:x_in, input_labels:y_in, learning_phase():1})#do_rate:0.5})
total_l += l
total_acc += np.sum(acc)
#pdb.set_trace()
total_acc /= np.float32(N)
print("Epoch {}: Training loss = {}, Training accuracy = {}".format(i,total_l,total_acc))
# Test:
total_acc = 0
steps = (int)(np.ceil(float(Nt)/float(BATCH_SIZE)))
for step in range(steps):
x_in, y_in = get_batch(step, BATCH_SIZE, test_images, test_labels)
acc = sess.run([accuracy], {input_data:x_in, input_labels:y_in, learning_phase():0})#do_rate:1})
total_acc += np.sum(acc)
total_acc /= np.float32(Nt)
print('\n--------------------------\n')
print("Test accuracy = {}".format(total_acc))
sess.close()
writer.close()
Y_train = np_utils.to_categorical(y_train, 10)
Y_test = np_utils.to_categorical(y_test, 10)
# Model
model = Sequential()
#defaultformat: (samples, rows, col
model.add(
Convolution2D(32,
kernel_size=(3, 3),
strides=(1, 1),
activation='relu',
input_shape=(28, 28, 1)))
model.add(
Convolution2D(32, kernel_size=(3, 3), strides=(1, 1), activation='relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Dropout(0.25))
model.add(Flatten())
model.add(Dense(128, activation='relu'))
model.add(Dropout(0.5))
model.add(Dense(10, activation='softmax'))
model.summary()
model.compile(loss='categorical_crossentropy',
optimizer='adam',
metrics=['accuracy'])
model.fit(X_train, Y_train, batch_size=32, epochs=10, verbose=1)
score = model.evaluate(X_test, Y_test, verbose=0)
def SSD300(input_shape, num_classes=21):
"""SSD300 architecture.
# Arguments
input_shape: Shape of the input image,
expected to be either (300, 300, 3) or (3, 300, 300)(not tested).
num_classes: Number of classes including background.
# References
https://arxiv.org/abs/1512.02325
"""
net = {}
# Block 1
input_tensor = input_tensor = Input(shape=input_shape)
img_size = (input_shape[1], input_shape[0])
net['input'] = input_tensor
net['conv1_1'] = Convolution2D(64, (3, 3),
activation='relu',
padding='same',
name='conv1_1')(net['input'])
net['conv1_2'] = Convolution2D(64, (3, 3),
activation='relu',
padding='same',
name='conv1_2')(net['conv1_1'])
net['pool1'] = MaxPooling2D((2, 2),
strides=(2, 2),
padding='same',
name='pool1')(net['conv1_2'])
# Block 2
net['conv2_1'] = Convolution2D(128, (3, 3),
activation='relu',
padding='same',
name='conv2_1')(net['pool1'])
net['conv2_2'] = Convolution2D(128, (3, 3),
activation='relu',
padding='same',
name='conv2_2')(net['conv2_1'])
net['pool2'] = MaxPooling2D((2, 2),
strides=(2, 2),
padding='same',
name='pool2')(net['conv2_2'])
# Block 3
net['conv3_1'] = Convolution2D(256, (3, 3),
activation='relu',
padding='same',
name='conv3_1')(net['pool2'])
net['conv3_2'] = Convolution2D(256, (3, 3),
activation='relu',
padding='same',
name='conv3_2')(net['conv3_1'])
net['conv3_3'] = Convolution2D(256, (3, 3),
activation='relu',
padding='same',
name='conv3_3')(net['conv3_2'])
net['pool3'] = MaxPooling2D((2, 2),
strides=(2, 2),
padding='same',
name='pool3')(net['conv3_3'])
# Block 4
net['conv4_1'] = Convolution2D(512, (3, 3),
activation='relu',
padding='same',
name='conv4_1')(net['pool3'])
net['conv4_2'] = Convolution2D(512, (3, 3),
activation='relu',
padding='same',
name='conv4_2')(net['conv4_1'])
net['conv4_3'] = Convolution2D(512, (3, 3),
activation='relu',
padding='same',
name='conv4_3')(net['conv4_2'])
net['pool4'] = MaxPooling2D((2, 2),
strides=(2, 2),
padding='same',
name='pool4')(net['conv4_3'])
# Block 5
net['conv5_1'] = Convolution2D(512, (3, 3),
activation='relu',
padding='same',
name='conv5_1')(net['pool4'])
net['conv5_2'] = Convolution2D(512, (3, 3),
activation='relu',
padding='same',
name='conv5_2')(net['conv5_1'])
net['conv5_3'] = Convolution2D(512, (3, 3),
activation='relu',
padding='same',
name='conv5_3')(net['conv5_2'])
net['pool5'] = MaxPooling2D((3, 3),
strides=(1, 1),
padding='same',
name='pool5')(net['conv5_3'])
# FC6
net['fc6'] = Convolution2D(1024, (3, 3),
dilation_rate=(6, 6),
activation='relu',
padding='same',
name='fc6')(net['pool5'])
# x = Dropout(0.5, name='drop6')(x)
# FC7
net['fc7'] = Convolution2D(1024, (1, 1),
activation='relu',
padding='same',
name='fc7')(net['fc6'])
# x = Dropout(0.5, name='drop7')(x)
# Block 6
net['conv6_1'] = Convolution2D(256, (1, 1),
activation='relu',
padding='same',
name='conv6_1')(net['fc7'])
net['conv6_2'] = Convolution2D(512, (3, 3),
strides=(2, 2),
activation='relu',
padding='same',
name='conv6_2')(net['conv6_1'])
# Block 7
net['conv7_1'] = Convolution2D(128, (1, 1),
activation='relu',
padding='same',
name='conv7_1')(net['conv6_2'])
net['conv7_2'] = ZeroPadding2D()(net['conv7_1'])
net['conv7_2'] = Convolution2D(256, (3, 3),
strides=(2, 2),
activation='relu',
padding='valid',
name='conv7_2')(net['conv7_2'])
# Block 8
net['conv8_1'] = Convolution2D(128, (1, 1),
activation='relu',
padding='same',
name='conv8_1')(net['conv7_2'])
net['conv8_2'] = Convolution2D(256, (3, 3),
strides=(2, 2),
activation='relu',
padding='same',
name='conv8_2')(net['conv8_1'])
# Last Pool
net['pool6'] = GlobalAveragePooling2D(name='pool6')(net['conv8_2'])
# Prediction from conv4_3
net['conv4_3_norm'] = Normalize(20, name='conv4_3_norm')(net['conv4_3'])
num_priors = 3
x = Convolution2D(num_priors * 4, (3, 3),
padding='same',
name='conv4_3_norm_mbox_loc')(net['conv4_3_norm'])
net['conv4_3_norm_mbox_loc'] = x
flatten = Flatten(name='conv4_3_norm_mbox_loc_flat')
net['conv4_3_norm_mbox_loc_flat'] = flatten(net['conv4_3_norm_mbox_loc'])
name = 'conv4_3_norm_mbox_conf'
if num_classes != 21:
name += '_{}'.format(num_classes)
x = Convolution2D(num_priors * num_classes, (3, 3),
padding='same',
name=name)(net['conv4_3_norm'])
net['conv4_3_norm_mbox_conf'] = x
flatten = Flatten(name='conv4_3_norm_mbox_conf_flat')
net['conv4_3_norm_mbox_conf_flat'] = flatten(net['conv4_3_norm_mbox_conf'])
priorbox = PriorBox(img_size,
30.0,
aspect_ratios=[2],
variances=[0.1, 0.1, 0.2, 0.2],
name='conv4_3_norm_mbox_priorbox')
net['conv4_3_norm_mbox_priorbox'] = priorbox(net['conv4_3_norm'])
# Prediction from fc7
num_priors = 6
net['fc7_mbox_loc'] = Convolution2D(num_priors * 4, (3, 3),
padding='same',
name='fc7_mbox_loc')(net['fc7'])
flatten = Flatten(name='fc7_mbox_loc_flat')
net['fc7_mbox_loc_flat'] = flatten(net['fc7_mbox_loc'])
name = 'fc7_mbox_conf'
if num_classes != 21:
name += '_{}'.format(num_classes)
net['fc7_mbox_conf'] = Convolution2D(num_priors * num_classes, (3, 3),
padding='same',
name=name)(net['fc7'])
flatten = Flatten(name='fc7_mbox_conf_flat')
net['fc7_mbox_conf_flat'] = flatten(net['fc7_mbox_conf'])
priorbox = PriorBox(img_size,
60.0,
max_size=114.0,
aspect_ratios=[2, 3],
variances=[0.1, 0.1, 0.2, 0.2],
name='fc7_mbox_priorbox')
net['fc7_mbox_priorbox'] = priorbox(net['fc7'])
# Prediction from conv6_2
num_priors = 6
x = Convolution2D(num_priors * 4, (3, 3),
padding='same',
name='conv6_2_mbox_loc')(net['conv6_2'])
net['conv6_2_mbox_loc'] = x
flatten = Flatten(name='conv6_2_mbox_loc_flat')
net['conv6_2_mbox_loc_flat'] = flatten(net['conv6_2_mbox_loc'])
name = 'conv6_2_mbox_conf'
if num_classes != 21:
name += '_{}'.format(num_classes)
x = Convolution2D(num_priors * num_classes, (3, 3),
padding='same',
name=name)(net['conv6_2'])
net['conv6_2_mbox_conf'] = x
flatten = Flatten(name='conv6_2_mbox_conf_flat')
net['conv6_2_mbox_conf_flat'] = flatten(net['conv6_2_mbox_conf'])
priorbox = PriorBox(img_size,
114.0,
max_size=168.0,
aspect_ratios=[2, 3],
variances=[0.1, 0.1, 0.2, 0.2],
name='conv6_2_mbox_priorbox')
net['conv6_2_mbox_priorbox'] = priorbox(net['conv6_2'])
# Prediction from conv7_2
num_priors = 6
x = Convolution2D(num_priors * 4, (3, 3),
padding='same',
name='conv7_2_mbox_loc')(net['conv7_2'])
net['conv7_2_mbox_loc'] = x
flatten = Flatten(name='conv7_2_mbox_loc_flat')
net['conv7_2_mbox_loc_flat'] = flatten(net['conv7_2_mbox_loc'])
name = 'conv7_2_mbox_conf'
if num_classes != 21:
name += '_{}'.format(num_classes)
x = Convolution2D(num_priors * num_classes, (3, 3),
padding='same',
name=name)(net['conv7_2'])
net['conv7_2_mbox_conf'] = x
flatten = Flatten(name='conv7_2_mbox_conf_flat')
net['conv7_2_mbox_conf_flat'] = flatten(net['conv7_2_mbox_conf'])
priorbox = PriorBox(img_size,
168.0,
max_size=222.0,
aspect_ratios=[2, 3],
variances=[0.1, 0.1, 0.2, 0.2],
name='conv7_2_mbox_priorbox')
net['conv7_2_mbox_priorbox'] = priorbox(net['conv7_2'])
# Prediction from conv8_2
num_priors = 6
x = Convolution2D(num_priors * 4, (3, 3),
padding='same',
name='conv8_2_mbox_loc')(net['conv8_2'])
net['conv8_2_mbox_loc'] = x
flatten = Flatten(name='conv8_2_mbox_loc_flat')
net['conv8_2_mbox_loc_flat'] = flatten(net['conv8_2_mbox_loc'])
name = 'conv8_2_mbox_conf'
if num_classes != 21:
name += '_{}'.format(num_classes)
x = Convolution2D(num_priors * num_classes, (3, 3),
padding='same',
name=name)(net['conv8_2'])
net['conv8_2_mbox_conf'] = x
flatten = Flatten(name='conv8_2_mbox_conf_flat')
net['conv8_2_mbox_conf_flat'] = flatten(net['conv8_2_mbox_conf'])
priorbox = PriorBox(img_size,
222.0,
max_size=276.0,
aspect_ratios=[2, 3],
variances=[0.1, 0.1, 0.2, 0.2],
name='conv8_2_mbox_priorbox')
net['conv8_2_mbox_priorbox'] = priorbox(net['conv8_2'])
# Prediction from pool6
num_priors = 6
x = Dense(num_priors * 4, name='pool6_mbox_loc_flat')(net['pool6'])
net['pool6_mbox_loc_flat'] = x
name = 'pool6_mbox_conf_flat'
if num_classes != 21:
name += '_{}'.format(num_classes)
x = Dense(num_priors * num_classes, name=name)(net['pool6'])
net['pool6_mbox_conf_flat'] = x
priorbox = PriorBox(img_size,
276.0,
max_size=330.0,
aspect_ratios=[2, 3],
variances=[0.1, 0.1, 0.2, 0.2],
name='pool6_mbox_priorbox')
target_shape = (1, 1, 256)
net['pool6_reshaped'] = Reshape(target_shape,
name='pool6_reshaped')(net['pool6'])
net['pool6_mbox_priorbox'] = priorbox(net['pool6_reshaped'])
# Gather all predictions
net['mbox_loc'] = concatenate([
net['conv4_3_norm_mbox_loc_flat'], net['fc7_mbox_loc_flat'],
net['conv6_2_mbox_loc_flat'], net['conv7_2_mbox_loc_flat'],
net['conv8_2_mbox_loc_flat'], net['pool6_mbox_loc_flat']
],
axis=1,
name='mbox_loc')
net['mbox_conf'] = concatenate([
net['conv4_3_norm_mbox_conf_flat'], net['fc7_mbox_conf_flat'],
net['conv6_2_mbox_conf_flat'], net['conv7_2_mbox_conf_flat'],
net['conv8_2_mbox_conf_flat'], net['pool6_mbox_conf_flat']
],
axis=1,
name='mbox_conf')
net['mbox_priorbox'] = concatenate([
net['conv4_3_norm_mbox_priorbox'], net['fc7_mbox_priorbox'],
net['conv6_2_mbox_priorbox'], net['conv7_2_mbox_priorbox'],
net['conv8_2_mbox_priorbox'], net['pool6_mbox_priorbox']
],
axis=1,
name='mbox_priorbox')
num_boxes = K.int_shape(net['mbox_loc'])[-1] // 4
net['mbox_loc'] = Reshape((num_boxes, 4),
name='mbox_loc_final')(net['mbox_loc'])
net['mbox_conf'] = Reshape((num_boxes, num_classes),
name='mbox_conf_logits')(net['mbox_conf'])
net['mbox_conf'] = Activation('softmax',
name='mbox_conf_final')(net['mbox_conf'])
net['predictions'] = concatenate(
[net['mbox_loc'], net['mbox_conf'], net['mbox_priorbox']],
axis=2,
#axis = 0,
name='predictions')
model = Model(net['input'], net['predictions'])
return model
def ResNet50(include_top=True,
weights='imagenet',
input_tensor=None,
input_shape=None,
pooling=None,
classes=1000):
"""Instantiates the ResNet50 architecture.
Optionally loads weights pre-trained
on ImageNet. Note that when using TensorFlow,
for best performance you should set
`image_data_format="channels_last"` in your Keras config
at ~/.keras/keras.json.
The model and the weights are compatible with both
TensorFlow and Theano. The data format
convention used by the model is the one
specified in your Keras config file.
# Arguments
include_top: whether to include the fully-connected
layer at the top of the network.
weights: one of `None` (random initialization)
or "imagenet" (pre-training on ImageNet).
input_tensor: optional Keras tensor (i.e. output of `layers.Input()`)
to use as image input for the model.
input_shape: optional shape tuple, only to be specified
if `include_top` is False (otherwise the input shape
has to be `(224, 224, 3)` (with `channels_last` data format)
or `(3, 224, 244)` (with `channels_first` data format).
It should have exactly 3 inputs channels,
and width and height should be no smaller than 197.
E.g. `(200, 200, 3)` would be one valid value.
pooling: Optional pooling mode for feature extraction
when `include_top` is `False`.
- `None` means that the output of the model will be
the 4D tensor output of the
last convolutional layer.
- `avg` means that global average pooling
will be applied to the output of the
last convolutional layer, and thus
the output of the model will be a 2D tensor.
- `max` means that global max pooling will
be applied.
classes: optional number of classes to classify images
into, only to be specified if `include_top` is True, and
if no `weights` argument is specified.
# Returns
A Keras model instance.
# Raises
ValueError: in case of invalid argument for `weights`,
or invalid input shape.
"""
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')
# Determine proper input shape
input_shape = _obtain_input_shape(input_shape,
default_size=224,
min_size=197,
data_format=K.image_data_format(),
include_top=include_top)
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 = ZeroPadding2D((3, 3))(img_input)
x = Conv2D(64, (7, 7), strides=(2, 2), name='conv1')(x)
x = BatchNormalization(axis=bn_axis, name='bn_conv1')(x)
x = Activation('relu')(x)
x = MaxPooling2D((3, 3), strides=(2, 2))(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')
x = AveragePooling2D((7, 7), name='avg_pool')(x)
if include_top:
x = Flatten()(x)
x = Dense(classes, activation='softmax', name='fc1000')(x)
else:
if pooling == 'avg':
x = GlobalAveragePooling2D()(x)
elif pooling == 'max':
x = GlobalMaxPooling2D()(x)
# 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 = WEIGHTS_PATH
else:
weights_path = WEIGHTS_PATH_NO_TOP
model.load_weights(weights_path)
if K.backend() == 'theano':
layer_utils.convert_all_kernels_in_model(model)
if K.image_data_format() == 'channels_first':
if include_top:
maxpool = model.get_layer(name='avg_pool')
shape = maxpool.output_shape[1:]
dense = model.get_layer(name='fc1000')
layer_utils.convert_dense_weights_data_format(
dense, shape, 'channels_first')
if K.backend() == 'tensorflow':
warnings.warn('You are using the TensorFlow backend, yet you '
'are using the Theano '
'image data format convention '
'(`image_data_format="channels_first"`). '
'For best performance, set '
'`image_data_format="channels_last"` in '
'your Keras config '
'at ~/.keras/keras.json.')
return model
def Xception(include_top=True,
weights='imagenet',
input_tensor=None,
input_shape=None,
pooling=None,
classes=1000):
"""Instantiates the Xception architecture.
Optionally loads weights pre-trained
on ImageNet. This model is available for TensorFlow only,
and can only be used with inputs following the TensorFlow
data format `(width, height, channels)`.
You should set `image_data_format="channels_last"` in your Keras config
located at ~/.keras/keras.json.
Note that the default input image size for this model is 299x299.
Arguments:
include_top: whether to include the fully-connected
layer at the top of the network.
weights: one of `None` (random initialization)
or "imagenet" (pre-training on ImageNet).
input_tensor: optional Keras tensor (i.e. output of `layers.Input()`)
to use as image input for the model.
input_shape: optional shape tuple, only to be specified
if `include_top` is False (otherwise the input shape
has to be `(299, 299, 3)`.
It should have exactly 3 input channels,
and width and height should be no smaller than 71.
E.g. `(150, 150, 3)` would be one valid value.
pooling: Optional pooling mode for feature extraction
when `include_top` is `False`.
- `None` means that the output of the model will be
the 4D tensor output of the
last convolutional layer.
- `avg` means that global average pooling
will be applied to the output of the
last convolutional layer, and thus
the output of the model will be a 2D tensor.
- `max` means that global max pooling will
be applied.
classes: optional number of classes to classify images
into, only to be specified if `include_top` is True, and
if no `weights` argument is specified.
Returns:
A Keras model instance.
Raises:
ValueError: in case of invalid argument for `weights`,
or invalid input shape.
RuntimeError: If attempting to run this model with a
backend that does not support separable convolutions.
"""
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 K.backend() != 'tensorflow':
raise RuntimeError('The Xception model is only available with '
'the TensorFlow backend.')
if K.image_data_format() != 'channels_last':
logging.warning(
'The Xception model is only available for the '
'input data format "channels_last" '
'(width, height, channels). '
'However your settings specify the default '
'data format "channels_first" (channels, width, height). '
'You should set `image_data_format="channels_last"` in your Keras '
'config located at ~/.keras/keras.json. '
'The model being returned right now will expect inputs '
'to follow the "channels_last" data format.')
K.set_image_data_format('channels_last')
old_data_format = 'channels_first'
else:
old_data_format = None
# Determine proper input shape
input_shape = _obtain_input_shape(input_shape,
default_size=299,
min_size=71,
data_format=K.image_data_format(),
require_flatten=False,
weights=weights)
if input_tensor is None:
img_input = Input(shape=input_shape)
else:
img_input = Input(tensor=input_tensor, shape=input_shape)
x = Conv2D(32, (3, 3), strides=(2, 2), use_bias=False,
name='block1_conv1')(img_input)
x = BatchNormalization(name='block1_conv1_bn')(x)
x = Activation('relu', name='block1_conv1_act')(x)
x = Conv2D(64, (3, 3), use_bias=False, name='block1_conv2')(x)
x = BatchNormalization(name='block1_conv2_bn')(x)
x = Activation('relu', name='block1_conv2_act')(x)
residual = Conv2D(128, (1, 1),
strides=(2, 2),
padding='same',
use_bias=False)(x)
residual = BatchNormalization()(residual)
x = SeparableConv2D(128, (3, 3),
padding='same',
use_bias=False,
name='block2_sepconv1')(x)
x = BatchNormalization(name='block2_sepconv1_bn')(x)
x = Activation('relu', name='block2_sepconv2_act')(x)
x = SeparableConv2D(128, (3, 3),
padding='same',
use_bias=False,
name='block2_sepconv2')(x)
x = BatchNormalization(name='block2_sepconv2_bn')(x)
x = MaxPooling2D((3, 3),
strides=(2, 2),
padding='same',
name='block2_pool')(x)
x = layers.add([x, residual])
residual = Conv2D(256, (1, 1),
strides=(2, 2),
padding='same',
use_bias=False)(x)
residual = BatchNormalization()(residual)
x = Activation('relu', name='block3_sepconv1_act')(x)
x = SeparableConv2D(256, (3, 3),
padding='same',
use_bias=False,
name='block3_sepconv1')(x)
x = BatchNormalization(name='block3_sepconv1_bn')(x)
x = Activation('relu', name='block3_sepconv2_act')(x)
x = SeparableConv2D(256, (3, 3),
padding='same',
use_bias=False,
name='block3_sepconv2')(x)
x = BatchNormalization(name='block3_sepconv2_bn')(x)
x = MaxPooling2D((3, 3),
strides=(2, 2),
padding='same',
name='block3_pool')(x)
x = layers.add([x, residual])
residual = Conv2D(728, (1, 1),
strides=(2, 2),
padding='same',
use_bias=False)(x)
residual = BatchNormalization()(residual)
x = Activation('relu', name='block4_sepconv1_act')(x)
x = SeparableConv2D(728, (3, 3),
padding='same',
use_bias=False,
name='block4_sepconv1')(x)
x = BatchNormalization(name='block4_sepconv1_bn')(x)
x = Activation('relu', name='block4_sepconv2_act')(x)
x = SeparableConv2D(728, (3, 3),
padding='same',
use_bias=False,
name='block4_sepconv2')(x)
x = BatchNormalization(name='block4_sepconv2_bn')(x)
x = MaxPooling2D((3, 3),
strides=(2, 2),
padding='same',
name='block4_pool')(x)
x = layers.add([x, residual])
for i in range(8):
residual = x
prefix = 'block' + str(i + 5)
x = Activation('relu', name=prefix + '_sepconv1_act')(x)
x = SeparableConv2D(728, (3, 3),
padding='same',
use_bias=False,
name=prefix + '_sepconv1')(x)
x = BatchNormalization(name=prefix + '_sepconv1_bn')(x)
x = Activation('relu', name=prefix + '_sepconv2_act')(x)
x = SeparableConv2D(728, (3, 3),
padding='same',
use_bias=False,
name=prefix + '_sepconv2')(x)
x = BatchNormalization(name=prefix + '_sepconv2_bn')(x)
x = Activation('relu', name=prefix + '_sepconv3_act')(x)
x = SeparableConv2D(728, (3, 3),
padding='same',
use_bias=False,
name=prefix + '_sepconv3')(x)
x = BatchNormalization(name=prefix + '_sepconv3_bn')(x)
x = layers.add([x, residual])
residual = Conv2D(1024, (1, 1),
strides=(2, 2),
padding='same',
use_bias=False)(x)
residual = BatchNormalization()(residual)
x = Activation('relu', name='block13_sepconv1_act')(x)
x = SeparableConv2D(728, (3, 3),
padding='same',
use_bias=False,
name='block13_sepconv1')(x)
x = BatchNormalization(name='block13_sepconv1_bn')(x)
x = Activation('relu', name='block13_sepconv2_act')(x)
x = SeparableConv2D(1024, (3, 3),
padding='same',
use_bias=False,
name='block13_sepconv2')(x)
x = BatchNormalization(name='block13_sepconv2_bn')(x)
x = MaxPooling2D((3, 3),
strides=(2, 2),
padding='same',
name='block13_pool')(x)
x = layers.add([x, residual])
x = SeparableConv2D(1536, (3, 3),
padding='same',
use_bias=False,
name='block14_sepconv1')(x)
x = BatchNormalization(name='block14_sepconv1_bn')(x)
x = Activation('relu', name='block14_sepconv1_act')(x)
x = SeparableConv2D(2048, (3, 3),
padding='same',
use_bias=False,
name='block14_sepconv2')(x)
x = BatchNormalization(name='block14_sepconv2_bn')(x)
x = Activation('relu', name='block14_sepconv2_act')(x)
if include_top:
x = GlobalAveragePooling2D(name='avg_pool')(x)
x = Dense(classes, activation='softmax', name='predictions')(x)
else:
if pooling == 'avg':
x = GlobalAveragePooling2D()(x)
elif pooling == 'max':
x = GlobalMaxPooling2D()(x)
# 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='xception')
# load weights
if weights == 'imagenet':
if include_top:
weights_path = get_file(
'xception_weights_tf_dim_ordering_tf_kernels.h5',
TF_WEIGHTS_PATH,
cache_subdir='models')
else:
weights_path = get_file(
'xception_weights_tf_dim_ordering_tf_kernels_notop.h5',
TF_WEIGHTS_PATH_NO_TOP,
cache_subdir='models')
model.load_weights(weights_path)
if old_data_format:
K.set_image_data_format(old_data_format)
return model
def main():
training_images, training_labels, test_images, test_labels = load_dataset()
# plt.imshow(training_images[:,:,0], cmap='gray')
# plt.show()
perm_train = np.random.permutation(training_labels.size)
training_labels = training_labels[perm_train]
training_images = training_images[perm_train, :, :] / 255.0
training_images = np.expand_dims(training_images, -1)
print(training_images.shape)
test_images = test_images / 255.0
test_images = np.expand_dims(test_images, -1)
# pdb.set_trace()
# training_labels = to_categorical(training_labels, NUM_CLASSES)
# test_labels = to_categorical(test_labels, NUM_CLASSES)
BATCH_SIZE = 32 * 8
WIDTH, HEIGHT = 28, 28
# Defiining the network
input_layer = Input(shape=(HEIGHT, WIDTH, 1), name='input_layer')
cnn1 = Conv2D(filters=32,
kernel_size=3,
strides=(1, 1),
padding='same',
activation='relu')(input_layer)
maxpool = MaxPooling2D(pool_size=2)(cnn1)
cnn2 = Conv2D(filters=32,
kernel_size=3,
strides=(1, 1),
padding='valid',
activation='relu')(maxpool)
maxpool = MaxPooling2D(pool_size=2)(cnn2)
flat = Flatten()(maxpool)
dense1 = Dense(units=128, activation='relu')(flat)
dropout = Dropout(.5)(dense1)
output_layer = Dense(units=NUM_CLASSES, activation='softmax')(dropout)
model = Model(inputs=input_layer, outputs=output_layer)
model.compile(optimizer=tf.train.AdamOptimizer(),
loss='sparse_categorical_crossentropy',
metrics=['accuracy'])
# pdb.set_trace()
print(model.summary())
model.fit(x=training_images,
y=training_labels,
batch_size=BATCH_SIZE,
epochs=30,
verbose=1,
validation_data=(test_images, test_labels))
accuracy = model.evaluate(x=test_images,
y=test_labels,
batch_size=BATCH_SIZE)
print('test score = {}'.format(accuracy))
def ResNet50(include_top=True,
weights='imagenet',
input_tensor=None,
input_shape=None,
pooling=None,
classes=1000):
"""Instantiates the ResNet50 architecture.
Optionally loads weights pre-trained
on ImageNet. Note that when using TensorFlow,
for best performance you should set
`image_data_format="channels_last"` in your Keras config
at ~/.keras/keras.json.
The model and the weights are compatible with both
TensorFlow and Theano. The data format
convention used by the model is the one
specified in your Keras config file.
Arguments:
include_top: whether to include the fully-connected
layer at the top of the network.
weights: one of `None` (random initialization)
or "imagenet" (pre-training on ImageNet).
input_tensor: optional Keras tensor (i.e. output of `layers.Input()`)
to use as image input for the model.
input_shape: optional shape tuple, only to be specified
if `include_top` is False (otherwise the input shape
has to be `(224, 224, 3)` (with `channels_last` data format)
or `(3, 224, 224)` (with `channels_first` data format).
It should have exactly 3 inputs channels,
and width and height should be no smaller than 197.
E.g. `(200, 200, 3)` would be one valid value.
pooling: Optional pooling mode for feature extraction
when `include_top` is `False`.
- `None` means that the output of the model will be
the 4D tensor output of the
last convolutional layer.
- `avg` means that global average pooling
will be applied to the output of the
last convolutional layer, and thus
the output of the model will be a 2D tensor.
- `max` means that global max pooling will
be applied.
classes: optional number of classes to classify images
into, only to be specified if `include_top` is True, and
if no `weights` argument is specified.
Returns:
A Keras model instance.
Raises:
ValueError: in case of invalid argument for `weights`,
or invalid input shape.
"""
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')
# Determine proper input shape
input_shape = _obtain_input_shape(
input_shape,
default_size=224,
min_size=197,
data_format=K.image_data_format(),
include_top=include_top)
if input_tensor is None:
img_input = Input(shape=input_shape)
else:
img_input = Input(tensor=input_tensor, shape=input_shape)
if K.image_data_format() == 'channels_last':
bn_axis = 3
else:
bn_axis = 1
x = ZeroPadding2D((3, 3))(img_input)
x = Conv2D(64, (7, 7), strides=(2, 2), name='conv1')(x)
x = BatchNormalization(axis=bn_axis, name='bn_conv1')(x)
x = Activation('relu')(x)
x = MaxPooling2D((3, 3), strides=(2, 2))(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')
x0 = x
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, x0], 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 = "./saved_model/resnet50_weights_tf_dim_ordering_tf_kernels_notop.h5"
model.load_weights(weights_path)
return model
def InceptionV3(include_top=True,
weights='imagenet',
input_tensor=None,
input_shape=None,
pooling=None,
classes=1000):
"""Instantiates the Inception v3 architecture.
Optionally loads weights pre-trained
on ImageNet. Note that when using TensorFlow,
for best performance you should set
`image_data_format="channels_last"` in your Keras config
at ~/.keras/keras.json.
The model and the weights are compatible with both
TensorFlow and Theano. The data format
convention used by the model is the one
specified in your Keras config file.
Note that the default input image size for this model is 299x299.
Arguments:
include_top: whether to include the fully-connected
layer at the top of the network.
weights: one of `None` (random initialization)
or "imagenet" (pre-training on ImageNet).
input_tensor: optional Keras tensor (i.e. output of `layers.Input()`)
to use as image input for the model.
input_shape: optional shape tuple, only to be specified
if `include_top` is False (otherwise the input shape
has to be `(299, 299, 3)` (with `channels_last` data format)
or `(3, 299, 299)` (with `channels_first` data format).
It should have exactly 3 input channels,
and width and height should be no smaller than 139.
E.g. `(150, 150, 3)` would be one valid value.
pooling: Optional pooling mode for feature extraction
when `include_top` is `False`.
- `None` means that the output of the model will be
the 4D tensor output of the
last convolutional layer.
- `avg` means that global average pooling
will be applied to the output of the
last convolutional layer, and thus
the output of the model will be a 2D tensor.
- `max` means that global max pooling will
be applied.
classes: optional number of classes to classify images
into, only to be specified if `include_top` is True, and
if no `weights` argument is specified.
Returns:
A Keras model instance.
Raises:
ValueError: in case of invalid argument for `weights`,
or invalid input shape.
"""
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')
# Determine proper input shape
input_shape = _obtain_input_shape(
input_shape,
default_size=299,
min_size=139,
data_format=K.image_data_format(),
require_flatten=False,
weights=weights)
if input_tensor is None:
img_input = Input(shape=input_shape)
else:
img_input = Input(tensor=input_tensor, shape=input_shape)
if K.image_data_format() == 'channels_first':
channel_axis = 1
else:
channel_axis = 3
x = conv2d_bn(img_input, 32, 3, 3, strides=(2, 2), padding='valid')
x = conv2d_bn(x, 32, 3, 3, padding='valid')
x = conv2d_bn(x, 64, 3, 3)
x = MaxPooling2D((3, 3), strides=(2, 2))(x)
x = conv2d_bn(x, 80, 1, 1, padding='valid')
x = conv2d_bn(x, 192, 3, 3, padding='valid')
x = MaxPooling2D((3, 3), strides=(2, 2))(x)
# mixed 0, 1, 2: 35 x 35 x 256
branch1x1 = conv2d_bn(x, 64, 1, 1)
branch5x5 = conv2d_bn(x, 48, 1, 1)
branch5x5 = conv2d_bn(branch5x5, 64, 5, 5)
branch3x3dbl = conv2d_bn(x, 64, 1, 1)
branch3x3dbl = conv2d_bn(branch3x3dbl, 96, 3, 3)
branch3x3dbl = conv2d_bn(branch3x3dbl, 96, 3, 3)
branch_pool = AveragePooling2D((3, 3), strides=(1, 1), padding='same')(x)
branch_pool = conv2d_bn(branch_pool, 32, 1, 1)
x = layers.concatenate(
[branch1x1, branch5x5, branch3x3dbl, branch_pool],
axis=channel_axis,
name='mixed0')
# mixed 1: 35 x 35 x 256
branch1x1 = conv2d_bn(x, 64, 1, 1)
branch5x5 = conv2d_bn(x, 48, 1, 1)
branch5x5 = conv2d_bn(branch5x5, 64, 5, 5)
branch3x3dbl = conv2d_bn(x, 64, 1, 1)
branch3x3dbl = conv2d_bn(branch3x3dbl, 96, 3, 3)
branch3x3dbl = conv2d_bn(branch3x3dbl, 96, 3, 3)
branch_pool = AveragePooling2D((3, 3), strides=(1, 1), padding='same')(x)
branch_pool = conv2d_bn(branch_pool, 64, 1, 1)
x = layers.concatenate(
[branch1x1, branch5x5, branch3x3dbl, branch_pool],
axis=channel_axis,
name='mixed1')
# mixed 2: 35 x 35 x 256
branch1x1 = conv2d_bn(x, 64, 1, 1)
branch5x5 = conv2d_bn(x, 48, 1, 1)
branch5x5 = conv2d_bn(branch5x5, 64, 5, 5)
branch3x3dbl = conv2d_bn(x, 64, 1, 1)
branch3x3dbl = conv2d_bn(branch3x3dbl, 96, 3, 3)
branch3x3dbl = conv2d_bn(branch3x3dbl, 96, 3, 3)
branch_pool = AveragePooling2D((3, 3), strides=(1, 1), padding='same')(x)
branch_pool = conv2d_bn(branch_pool, 64, 1, 1)
x = layers.concatenate(
[branch1x1, branch5x5, branch3x3dbl, branch_pool],
axis=channel_axis,
name='mixed2')
# mixed 3: 17 x 17 x 768
branch3x3 = conv2d_bn(x, 384, 3, 3, strides=(2, 2), padding='valid')
branch3x3dbl = conv2d_bn(x, 64, 1, 1)
branch3x3dbl = conv2d_bn(branch3x3dbl, 96, 3, 3)
branch3x3dbl = conv2d_bn(
branch3x3dbl, 96, 3, 3, strides=(2, 2), padding='valid')
branch_pool = MaxPooling2D((3, 3), strides=(2, 2))(x)
x = layers.concatenate(
[branch3x3, branch3x3dbl, branch_pool], axis=channel_axis, name='mixed3')
# mixed 4: 17 x 17 x 768
branch1x1 = conv2d_bn(x, 192, 1, 1)
branch7x7 = conv2d_bn(x, 128, 1, 1)
branch7x7 = conv2d_bn(branch7x7, 128, 1, 7)
branch7x7 = conv2d_bn(branch7x7, 192, 7, 1)
branch7x7dbl = conv2d_bn(x, 128, 1, 1)
branch7x7dbl = conv2d_bn(branch7x7dbl, 128, 7, 1)
branch7x7dbl = conv2d_bn(branch7x7dbl, 128, 1, 7)
branch7x7dbl = conv2d_bn(branch7x7dbl, 128, 7, 1)
branch7x7dbl = conv2d_bn(branch7x7dbl, 192, 1, 7)
branch_pool = AveragePooling2D((3, 3), strides=(1, 1), padding='same')(x)
branch_pool = conv2d_bn(branch_pool, 192, 1, 1)
x = layers.concatenate(
[branch1x1, branch7x7, branch7x7dbl, branch_pool],
axis=channel_axis,
name='mixed4')
# mixed 5, 6: 17 x 17 x 768
for i in range(2):
branch1x1 = conv2d_bn(x, 192, 1, 1)
branch7x7 = conv2d_bn(x, 160, 1, 1)
branch7x7 = conv2d_bn(branch7x7, 160, 1, 7)
branch7x7 = conv2d_bn(branch7x7, 192, 7, 1)
branch7x7dbl = conv2d_bn(x, 160, 1, 1)
branch7x7dbl = conv2d_bn(branch7x7dbl, 160, 7, 1)
branch7x7dbl = conv2d_bn(branch7x7dbl, 160, 1, 7)
branch7x7dbl = conv2d_bn(branch7x7dbl, 160, 7, 1)
branch7x7dbl = conv2d_bn(branch7x7dbl, 192, 1, 7)
branch_pool = AveragePooling2D((3, 3), strides=(1, 1), padding='same')(x)
branch_pool = conv2d_bn(branch_pool, 192, 1, 1)
x = layers.concatenate(
[branch1x1, branch7x7, branch7x7dbl, branch_pool],
axis=channel_axis,
name='mixed' + str(5 + i))
# mixed 7: 17 x 17 x 768
branch1x1 = conv2d_bn(x, 192, 1, 1)
branch7x7 = conv2d_bn(x, 192, 1, 1)
branch7x7 = conv2d_bn(branch7x7, 192, 1, 7)
branch7x7 = conv2d_bn(branch7x7, 192, 7, 1)
branch7x7dbl = conv2d_bn(x, 192, 1, 1)
branch7x7dbl = conv2d_bn(branch7x7dbl, 192, 7, 1)
branch7x7dbl = conv2d_bn(branch7x7dbl, 192, 1, 7)
branch7x7dbl = conv2d_bn(branch7x7dbl, 192, 7, 1)
branch7x7dbl = conv2d_bn(branch7x7dbl, 192, 1, 7)
branch_pool = AveragePooling2D((3, 3), strides=(1, 1), padding='same')(x)
branch_pool = conv2d_bn(branch_pool, 192, 1, 1)
x = layers.concatenate(
[branch1x1, branch7x7, branch7x7dbl, branch_pool],
axis=channel_axis,
name='mixed7')
# mixed 8: 8 x 8 x 1280
branch3x3 = conv2d_bn(x, 192, 1, 1)
branch3x3 = conv2d_bn(branch3x3, 320, 3, 3, strides=(2, 2), padding='valid')
branch7x7x3 = conv2d_bn(x, 192, 1, 1)
branch7x7x3 = conv2d_bn(branch7x7x3, 192, 1, 7)
branch7x7x3 = conv2d_bn(branch7x7x3, 192, 7, 1)
branch7x7x3 = conv2d_bn(
branch7x7x3, 192, 3, 3, strides=(2, 2), padding='valid')
branch_pool = MaxPooling2D((3, 3), strides=(2, 2))(x)
x = layers.concatenate(
[branch3x3, branch7x7x3, branch_pool], axis=channel_axis, name='mixed8')
# mixed 9: 8 x 8 x 2048
for i in range(2):
branch1x1 = conv2d_bn(x, 320, 1, 1)
branch3x3 = conv2d_bn(x, 384, 1, 1)
branch3x3_1 = conv2d_bn(branch3x3, 384, 1, 3)
branch3x3_2 = conv2d_bn(branch3x3, 384, 3, 1)
branch3x3 = layers.concatenate(
[branch3x3_1, branch3x3_2], axis=channel_axis, name='mixed9_' + str(i))
branch3x3dbl = conv2d_bn(x, 448, 1, 1)
branch3x3dbl = conv2d_bn(branch3x3dbl, 384, 3, 3)
branch3x3dbl_1 = conv2d_bn(branch3x3dbl, 384, 1, 3)
branch3x3dbl_2 = conv2d_bn(branch3x3dbl, 384, 3, 1)
branch3x3dbl = layers.concatenate(
[branch3x3dbl_1, branch3x3dbl_2], axis=channel_axis)
branch_pool = AveragePooling2D((3, 3), strides=(1, 1), padding='same')(x)
branch_pool = conv2d_bn(branch_pool, 192, 1, 1)
x = layers.concatenate(
[branch1x1, branch3x3, branch3x3dbl, branch_pool],
axis=channel_axis,
name='mixed' + str(9 + i))
if include_top:
# Classification block
x = GlobalAveragePooling2D(name='avg_pool')(x)
x = Dense(classes, activation='softmax', name='predictions')(x)
else:
if pooling == 'avg':
x = GlobalAveragePooling2D()(x)
elif pooling == 'max':
x = GlobalMaxPooling2D()(x)
# 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='inception_v3')
# load weights
if weights == 'imagenet':
if include_top:
weights_path = get_file(
'inception_v3_weights_tf_dim_ordering_tf_kernels.h5',
WEIGHTS_PATH,
cache_subdir='models',
md5_hash='9a0d58056eeedaa3f26cb7ebd46da564')
else:
weights_path = get_file(
'inception_v3_weights_tf_dim_ordering_tf_kernels_notop.h5',
WEIGHTS_PATH_NO_TOP,
cache_subdir='models',
md5_hash='bcbd6486424b2319ff4ef7d526e38f63')
model.load_weights(weights_path)
return model
def InceptionResNetV2(include_top=True,
weights='imagenet',
input_tensor=None,
input_shape=None,
pooling=None,
classes=1000):
"""Instantiates the Inception-ResNet v2 architecture.
Optionally loads weights pre-trained on ImageNet.
Note that when using TensorFlow, for best performance you should
set `"image_data_format": "channels_last"` in your Keras config
at `~/.keras/keras.json`.
The model and the weights are compatible with TensorFlow, Theano and
CNTK backends. The data format convention used by the model is
the one specified in your Keras config file.
Note that the default input image size for this model is 299x299, instead
of 224x224 as in the VGG16 and ResNet models. Also, the input preprocessing
function is different (i.e., do not use `imagenet_utils.preprocess_input()`
with this model. Use `preprocess_input()` defined in this module instead).
# Arguments
include_top: whether to include the fully-connected
layer at the top of the network.
weights: one of `None` (random initialization)
or `'imagenet'` (pre-training on ImageNet).
input_tensor: optional Keras tensor (i.e. output of `layers.Input()`)
to use as image input for the model.
input_shape: optional shape tuple, only to be specified
if `include_top` is `False` (otherwise the input shape
has to be `(299, 299, 3)` (with `'channels_last'` data format)
or `(3, 299, 299)` (with `'channels_first'` data format).
It should have exactly 3 inputs channels,
and width and height should be no smaller than 139.
E.g. `(150, 150, 3)` would be one valid value.
pooling: Optional pooling mode for feature extraction
when `include_top` is `False`.
- `None` means that the output of the model will be
the 4D tensor output of the last convolutional layer.
- `'avg'` means that global average pooling
will be applied to the output of the
last convolutional layer, and thus
the output of the model will be a 2D tensor.
- `'max'` means that global max pooling will be applied.
classes: optional number of classes to classify images
into, only to be specified if `include_top` is `True`, and
if no `weights` argument is specified.
# Returns
A Keras `Model` instance.
# Raises
ValueError: in case of invalid argument for `weights`,
or invalid input shape.
"""
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')
# Determine proper input shape
input_shape = _obtain_input_shape(input_shape,
default_size=299,
min_size=139,
data_format=K.image_data_format(),
require_flatten=False,
weights=weights)
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
# Stem block: 35 x 35 x 192
x = conv2d_bn(img_input, 32, 3, strides=2, padding='valid')
x = conv2d_bn(x, 32, 3, padding='valid')
x = conv2d_bn(x, 64, 3)
x = MaxPooling2D(3, strides=2)(x)
x = conv2d_bn(x, 80, 1, padding='valid')
x = conv2d_bn(x, 192, 3, padding='valid')
x = MaxPooling2D(3, strides=2)(x)
# Mixed 5b (Inception-A block): 35 x 35 x 320
branch_0 = conv2d_bn(x, 96, 1)
branch_1 = conv2d_bn(x, 48, 1)
branch_1 = conv2d_bn(branch_1, 64, 5)
branch_2 = conv2d_bn(x, 64, 1)
branch_2 = conv2d_bn(branch_2, 96, 3)
branch_2 = conv2d_bn(branch_2, 96, 3)
branch_pool = AveragePooling2D(3, strides=1, padding='same')(x)
branch_pool = conv2d_bn(branch_pool, 64, 1)
branches = [branch_0, branch_1, branch_2, branch_pool]
channel_axis = 1 if K.image_data_format() == 'channels_first' else 3
x = Concatenate(axis=channel_axis, name='mixed_5b')(branches)
# 10x block35 (Inception-ResNet-A block): 35 x 35 x 320
for block_idx in range(1, 11):
x = inception_resnet_block(x,
scale=0.17,
block_type='block35',
block_idx=block_idx)
# Mixed 6a (Reduction-A block): 17 x 17 x 1088
branch_0 = conv2d_bn(x, 384, 3, strides=2, padding='valid')
branch_1 = conv2d_bn(x, 256, 1)
branch_1 = conv2d_bn(branch_1, 256, 3)
branch_1 = conv2d_bn(branch_1, 384, 3, strides=2, padding='valid')
branch_pool = MaxPooling2D(3, strides=2, padding='valid')(x)
branches = [branch_0, branch_1, branch_pool]
x = Concatenate(axis=channel_axis, name='mixed_6a')(branches)
# 20x block17 (Inception-ResNet-B block): 17 x 17 x 1088
for block_idx in range(1, 21):
x = inception_resnet_block(x,
scale=0.1,
block_type='block17',
block_idx=block_idx)
# Mixed 7a (Reduction-B block): 8 x 8 x 2080
branch_0 = conv2d_bn(x, 256, 1)
branch_0 = conv2d_bn(branch_0, 384, 3, strides=2, padding='valid')
branch_1 = conv2d_bn(x, 256, 1)
branch_1 = conv2d_bn(branch_1, 288, 3, strides=2, padding='valid')
branch_2 = conv2d_bn(x, 256, 1)
branch_2 = conv2d_bn(branch_2, 288, 3)
branch_2 = conv2d_bn(branch_2, 320, 3, strides=2, padding='valid')
branch_pool = MaxPooling2D(3, strides=2, padding='valid')(x)
branches = [branch_0, branch_1, branch_2, branch_pool]
x = Concatenate(axis=channel_axis, name='mixed_7a')(branches)
# 10x block8 (Inception-ResNet-C block): 8 x 8 x 2080
for block_idx in range(1, 10):
x = inception_resnet_block(x,
scale=0.2,
block_type='block8',
block_idx=block_idx)
x = inception_resnet_block(x,
scale=1.,
activation=None,
block_type='block8',
block_idx=10)
# Final convolution block: 8 x 8 x 1536
x = conv2d_bn(x, 1536, 1, name='conv_7b')
if include_top:
# Classification block
x = GlobalAveragePooling2D(name='avg_pool')(x)
x = Dense(classes, activation='softmax', name='predictions')(x)
else:
if pooling == 'avg':
x = GlobalAveragePooling2D()(x)
elif pooling == 'max':
x = GlobalMaxPooling2D()(x)
# 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='inception_resnet_v2')
# Load weights
if weights == 'imagenet':
if K.image_data_format() == 'channels_first':
if K.backend() == 'tensorflow':
warnings.warn('You are using the TensorFlow backend, yet you '
'are using the Theano '
'image data format convention '
'(`image_data_format="channels_first"`). '
'For best performance, set '
'`image_data_format="channels_last"` in '
'your Keras config '
'at ~/.keras/keras.json.')
if include_top:
weights_filename = 'inception_resnet_v2_weights_tf_dim_ordering_tf_kernels.h5'
weights_path = get_file(
weights_filename,
BASE_WEIGHT_URL + weights_filename,
cache_subdir='models',
file_hash='e693bd0210a403b3192acc6073ad2e96')
else:
weights_filename = 'inception_resnet_v2_weights_tf_dim_ordering_tf_kernels_notop.h5'
weights_path = get_file(
weights_filename,
BASE_WEIGHT_URL + weights_filename,
cache_subdir='models',
file_hash='d19885ff4a710c122648d3b5c3b684e4')
model.load_weights(weights_path)
return model
def VGG16(include_top=True,
weights='imagenet',
input_tensor=None,
input_shape=None,
pooling=None,
classes=1000):
"""Instantiates the VGG16 architecture.
Optionally loads weights pre-trained
on ImageNet. Note that when using TensorFlow,
for best performance you should set
`image_data_format="channels_last"` in your Keras config
at ~/.keras/keras.json.
The model and the weights are compatible with both
TensorFlow and Theano. The data format
convention used by the model is the one
specified in your Keras config file.
Arguments:
include_top: whether to include the 3 fully-connected
layers at the top of the network.
weights: one of `None` (random initialization)
or "imagenet" (pre-training on ImageNet).
input_tensor: optional Keras tensor (i.e. output of `layers.Input()`)
to use as image input for the model.
input_shape: optional shape tuple, only to be specified
if `include_top` is False (otherwise the input shape
has to be `(224, 224, 3)` (with `channels_last` data format)
or `(3, 224, 224)` (with `channels_first` data format).
It should have exactly 3 inputs channels,
and width and height should be no smaller than 48.
E.g. `(200, 200, 3)` would be one valid value.
pooling: Optional pooling mode for feature extraction
when `include_top` is `False`.
- `None` means that the output of the model will be
the 4D tensor output of the
last convolutional layer.
- `avg` means that global average pooling
will be applied to the output of the
last convolutional layer, and thus
the output of the model will be a 2D tensor.
- `max` means that global max pooling will
be applied.
classes: optional number of classes to classify images
into, only to be specified if `include_top` is True, and
if no `weights` argument is specified.
Returns:
A Keras model instance.
Raises:
ValueError: in case of invalid argument for `weights`,
or invalid input shape.
"""
### how many weights option can we be allowed
if weights not in {'imagenet', None}:
raise ValueError('The `weights` argument should be either '
'`None` (random initialization) or `imagenet` '
'(pre-training on ImageNet).')
### if use imagenet weights and add last 3 dense layers, then class should be 1000
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')
### set input shape : (224, 224, 3)
# default input shape for VGG16 model, designed for imagenet dataset
input_shape = _obtain_input_shape(
input_shape, # if set must be a tuple of 3 integers (50, 50, 3)
default_size=224, # if input_shape set, here must be None
min_size=48, # 48, but freely change it to your need
data_format=K.image_data_format(
), # 'channels_first' or 'channels_last'
include_top=include_top
) # True, then must use 224 or False to be other number
### Create input tensor: real tensor or container?
if input_tensor is None:
# create input tensor placeholder
img_input = Input(shape=input_shape)
else:
img_input = Input(tensor=input_tensor, shape=input_shape)
# Block 1
x = Conv2D(64, (3, 3),
activation='relu',
padding='same',
name='block1_conv1')(img_input)
## how to access weights of each layer
block1_conv1 = x
block1_conv1_bias = block1_conv1.graph._collections['trainable_variables'][
-1] # bias
block1_conv1_kernel = block1_conv1.graph._collections[
'trainable_variables'][-2] # kernel
x = Conv2D(64, (3, 3),
activation='relu',
padding='same',
name='block1_conv2')(x)
block1_conv2 = x
block1_conv2_bias = block1_conv2.graph._collections['trainable_variables'][
-1] # bias
block1_conv2_kernel = block1_conv2.graph._collections[
'trainable_variables'][-2] # kernel
x = MaxPooling2D((2, 2), strides=(2, 2), name='block1_pool')(x)
block1_pool = x
# access trainable_variables or weights with biases
block1_pool.graph._collections['variables'][-1] # bias
block1_pool.graph._collections['variables'][-2] # kernel
# Block 2
x = Conv2D(128, (3, 3),
activation='relu',
padding='same',
name='block2_conv1')(x)
block2_conv1 = x
x = Conv2D(128, (3, 3),
activation='relu',
padding='same',
name='block2_conv2')(x)
block2_conv2 = x
x = MaxPooling2D((2, 2), strides=(2, 2), name='block2_pool')(x)
block2_pool = x
# Block 3
x = Conv2D(256, (3, 3),
activation='relu',
padding='same',
name='block3_conv1')(x)
block3_conv1 = x
x = Conv2D(256, (3, 3),
activation='relu',
padding='same',
name='block3_conv2')(x)
block3_conv2 = x
x = Conv2D(256, (3, 3),
activation='relu',
padding='same',
name='block3_conv3')(x)
block3_conv3 = x
x = MaxPooling2D((2, 2), strides=(2, 2), name='block3_pool')(x)
block3_pool = x
# Block 4
x = Conv2D(512, (3, 3),
activation='relu',
padding='same',
name='block4_conv1')(x)
block4_conv1 = x
x = Conv2D(512, (3, 3),
activation='relu',
padding='same',
name='block4_conv2')(x)
block4_conv2 = x
x = Conv2D(512, (3, 3),
activation='relu',
padding='same',
name='block4_conv3')(x)
block4_conv3 = x
x = MaxPooling2D((2, 2), strides=(2, 2), name='block4_pool')(x)
block4_pool = x
# Block 5
x = Conv2D(512, (3, 3),
activation='relu',
padding='same',
name='block5_conv1')(x)
block5_conv1 = x
x = Conv2D(512, (3, 3),
activation='relu',
padding='same',
name='block5_conv2')(x)
block5_conv2 = x
x = Conv2D(512, (3, 3),
activation='relu',
padding='same',
name='block5_conv3')(x)
block5_conv3 = x
x = MaxPooling2D((2, 2), strides=(2, 2), name='block5_pool')(x)
block5_pool = x
if include_top:
# Classification block
x = Flatten(name='flatten')(x)
flatten = x
x = Dense(4096, activation='relu', name='fc1')(x)
fc1 = x
x = Dense(4096, activation='relu', name='fc2')(x)
fc2 = x
x = Dense(classes, activation='softmax', name='predictions')(x)
predictions = x
else:
if pooling == 'avg':
x = GlobalAveragePooling2D()(x)
elif pooling == 'max':
x = GlobalMaxPooling2D()(x)
# 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='vgg16')
# load weights
if weights == 'imagenet':
if include_top:
weights_path = get_file(
'vgg16_weights_tf_dim_ordering_tf_kernels.h5',
WEIGHTS_PATH,
cache_subdir='models')
else:
weights_path = get_file(
'vgg16_weights_tf_dim_ordering_tf_kernels_notop.h5',
WEIGHTS_PATH_NO_TOP,
cache_subdir='models')
model.load_weights(weights_path)
if K.backend() == 'theano':
layer_utils.convert_all_kernels_in_model(model)
if K.image_data_format() == 'channels_first':
if include_top:
maxpool = model.get_layer(name='block5_pool')
shape = maxpool.output_shape[1:]
dense = model.get_layer(name='fc1')
layer_utils.convert_dense_weights_data_format(
dense, shape, 'channels_first')
return model
(x_train, _), (x_test, _) = mnist.load_data()
x_train = x_train.astype('float32') / 255.
x_test = x_test.astype('float32') / 255.
x_train = np.reshape(x_train, ((x_train.shape[0],) + shape_ord))
x_test = np.reshape(x_test, ((x_test.shape[0],) + shape_ord))
input_img = Input(shape=(28, 28, 1))
x = Conv2D(16, (3, 3), activation='relu', padding='same')(input_img)
x = MaxPooling2D((2, 2), padding='same')(x)
x = Conv2D(8, (3, 3), activation='relu', padding='same')(x)
x = MaxPooling2D((2, 2), padding='same')(x)
x = Conv2D(8, (3, 3), activation='relu', padding='same')(x)
encoded = MaxPooling2D((2, 2), padding='same')(x)
# at this point the representation is (4, 4, 8) i.e. 128-dimensional
x = Conv2D(8, (3, 3), activation='relu', padding='same')(encoded)
x = UpSampling2D((2, 2))(x)
x = Conv2D(8, (3, 3), activation='relu', padding='same')(x)
x = UpSampling2D((2, 2))(x)
x = Conv2D(16, (3, 3), activation='relu')(x)
x = UpSampling2D((2, 2))(x)
decoded = Conv2D(1, (3, 3), activation='sigmoid', padding='same')(x)
def create_AlexNet(num_fc_neurons,
dropout_rate,
num_classes=24,
img_height=224,
img_width=224,
include_loc='all',
activation='softmax'):
weight_decay = 0.0005
kernel_regularizer = regularizers.l2(weight_decay)
bias_regularizer = regularizers.l2(weight_decay)
# build a convolutional model
base_model = Sequential()
base_model.add(
Conv2D(96, (11, 11),
strides=(4, 4),
padding='valid',
activation='relu',
kernel_regularizer=kernel_regularizer,
bias_regularizer=bias_regularizer,
name='conv1',
input_shape=get_input_shape(img_height, img_width)))
base_model.add(LRN2D(name='lrn1'))
base_model.add(MaxPooling2D((3, 3), strides=(2, 2), name='pool1'))
base_model.add(
Conv2D(256, (5, 5),
strides=(1, 1),
padding='same',
activation='relu',
kernel_regularizer=kernel_regularizer,
bias_regularizer=bias_regularizer,
name='conv2'))
base_model.add(LRN2D(name='lrn2'))
base_model.add(MaxPooling2D((3, 3), strides=(2, 2), name='pool2'))
base_model.add(
Conv2D(384, (3, 3),
strides=(1, 1),
padding='same',
activation='relu',
kernel_regularizer=kernel_regularizer,
bias_regularizer=bias_regularizer,
name='conv3'))
base_model.add(
Conv2D(384, (3, 3),
strides=(1, 1),
padding='same',
activation='relu',
kernel_regularizer=kernel_regularizer,
bias_regularizer=bias_regularizer,
name='conv4'))
base_model.add(
Conv2D(256, (3, 3),
strides=(1, 1),
padding='same',
activation='relu',
kernel_regularizer=kernel_regularizer,
bias_regularizer=bias_regularizer,
name='conv5'))
base_model.add(MaxPooling2D((3, 3), strides=(2, 2), name='pool3'))
# build a classifier model to put on top of the convolutional model
top_model = Sequential()
top_model.add(Flatten(input_shape=base_model.output_shape[1:]))
for i in range(6, 8):
top_model.add(
Dense(num_fc_neurons,
kernel_regularizer=kernel_regularizer,
bias_regularizer=bias_regularizer,
name='fc' + str(i)))
#top_model.add(BatchNormalization(axis=1, name='fc'+str(i)+'_bn'))
top_model.add(Activation('relu', name='fc' + str(i) + '_ac'))
top_model.add(Dropout(dropout_rate))
top_model.add(
Dense(num_classes,
activation=activation,
kernel_regularizer=kernel_regularizer,
bias_regularizer=bias_regularizer,
name='predictions'))
if include_loc == 'base':
model = base_model
elif include_loc == 'top':
model = top_model
elif include_loc == 'all': # add the model on top of the convolutional base
model = Model(inputs=base_model.input,
outputs=top_model(base_model.output))
else:
raise ValueError('Only "base", "top" and "all" can be included.')
return model
""" ### Shared vision model This model re-uses the same image-processing module on two inputs, to classify whether two MNIST digits are the same digit or different digits. """ from tensorflow.contrib.keras.python.keras.layers import Conv2D, MaxPooling2D, Input, Dense, Flatten, concatenate from tensorflow.contrib.keras.python.keras.models import Model # First, define the vision modules # digit_input = Input(shape=(1, 27, 27)) digit_input = Input(shape=(27, 27, 1)) x = Conv2D(64, (3, 3))(digit_input) # padding 'valid' or 'same' affect shape x = Conv2D(64, (3, 3))(x) # padding='same', can keep image size the same x = MaxPooling2D((2, 2))(x) # downscale image size out = Flatten()(x) vision_model = Model(digit_input, out) # Then define the tell-digits-apart model # digit_a = Input(shape=(1, 27, 27)) # digit_b = Input(shape=(1, 27, 27)) digit_a = Input(shape=(27, 27, 1)) digit_b = Input(shape=(27, 27, 1)) # The vision model will be shared, weights and all out_a = vision_model(digit_a) out_b = vision_model(digit_b) concatenated = concatenate([out_a, out_b]) # cbind tensors
def main():
training_images, training_labels, test_images, test_labels = load_dataset()
# plt.imshow(training_images[:,:,0], cmap='gray')
# plt.show()
N = training_labels.size
Nt = test_labels.size
perm_train = np.random.permutation(N)
training_labels = training_labels[perm_train]
training_images = training_images[perm_train, :, :] / 255.0
training_images = np.expand_dims(training_images, -1)
print(training_images.shape)
test_images = test_images / 255.0
test_images = np.expand_dims(test_images, -1)
# pdb.set_trace()
training_labels = to_categorical(training_labels, NUM_CLASSES)
test_labels = to_categorical(test_labels, NUM_CLASSES)
BATCH_SIZE = 32 * 8
WIDTH, HEIGHT = 28, 28
epochs = 30
# Defiining the placeholders
input_data = tf.placeholder(dtype=tf.float32,
shape=[None, HEIGHT, WIDTH, 1],
name='data')
input_labels = tf.placeholder(dtype=tf.float32,
shape=[None, NUM_CLASSES],
name='labels')
do_rate = tf.placeholder(dtype=tf.float32, name='dropout_rate')
# pdb.set_trace()
with tf.name_scope('conv1'):
with tf.variable_scope('conv1'):
W_conv1 = tf.get_variable('w', [3, 3, 1, 32])
b_conv1 = tf.get_variable('b', [32])
conv1 = tf.nn.conv2d(input=input_data,
filter=W_conv1,
strides=[1, 1, 1, 1],
padding='SAME')
relu1 = tf.nn.relu(conv1 + b_conv1)
with tf.name_scope('pool1'):
pool1 = tf.nn.max_pool(value=relu1,
ksize=[1, 2, 2, 1],
strides=[1, 2, 2, 1],
padding='SAME')
with tf.name_scope('conv2'):
with tf.variable_scope('conv2'):
W_conv2 = tf.get_variable('w', [3, 3, 32, 32])
b_conv2 = tf.get_variable('b', [32])
conv2 = tf.nn.conv2d(input=pool1,
filter=W_conv2,
strides=[1, 1, 1, 1],
padding='VALID')
relu2 = tf.nn.relu(conv2 + b_conv2)
with tf.name_scope('pool2'):
pool2 = tf.nn.max_pool(value=relu2,
ksize=[1, 2, 2, 1],
strides=[1, 2, 2, 1],
padding='SAME')
with tf.name_scope('dense1'):
with tf.variable_scope('dense1'):
W_dense1 = tf.get_variable('w', [6 * 6 * 32, 128])
b_dense1 = tf.get_variable('b', 128)
flat = tf.reshape(pool2, [-1, 6 * 6 * 32], name='reshape')
dense1 = tf.matmul(flat, W_dense1)
relu3 = tf.nn.relu(dense1 + b_dense1)
with tf.name_scope('dropout'):
dropout = tf.nn.dropout(relu3, do_rate)
with tf.name_scope('output'):
with tf.variable_scope('output'):
W_out = tf.get_variable('w', [128, NUM_CLASSES])
b_out = tf.get_variable('b', [NUM_CLASSES])
output = tf.matmul(dropout, W_out) + b_out
'''
################################################################
""" Using Keras layers instead """
#input_layer = Input(shape=(HEIGHT, WIDTH, 1), name='input_layer')
Kcnn1 = Conv2D(filters=32, kernel_size=3, strides=(1,1), padding='same', activation='relu')(input_data)
Kmaxpool1 = MaxPooling2D(pool_size=2)(Kcnn1)
Kcnn2 = Conv2D(filters=32, kernel_size=3, strides=(1,1), padding='valid', activation='relu')(Kmaxpool1)
Kmaxpool2 = MaxPooling2D(pool_size=2)(Kcnn2)
Kflat = Flatten()(Kmaxpool2)
Kdense1 = Dense(units=128, activation='relu')(Kflat)
Kdropout = Dropout(.5)(Kdense1)
output = Dense(units=NUM_CLASSES, activation='softmax')(Kdropout)
""" The rest of the code is almost the same as in pure_tf_mnist.py,
except for the feed_dict, where instead of do_rate in tensorflow,
we need to provide keras specific dropout tensor 'learning_phase'
in the backend of Keras. """
################################################################
'''
print('\n\n')
print('-------------------------------------------------------')
print('--------------- Trainable parameters ------------------')
print('-------------------------------------------------------')
total_parameters = 0
for v in tf.trainable_variables():
shape = v.get_shape()
print(shape)
#pdb.set_trace()
params = 1
for dim in shape:
params *= dim.value
total_parameters += params
print('total_parameters = {}'.format(total_parameters))
print('-------------------------------------------------------\n\n')
loss = tf.reduce_mean(
tf.nn.softmax_cross_entropy_with_logits(labels=input_labels,
logits=output,
name='loss'))
train_op = tf.train.AdamOptimizer(1e-4).minimize(loss)
accuracy = tf.cast(
tf.equal(tf.argmax(input_labels, 1), tf.argmax(output, 1)), tf.float32)
print('')
print('-------------------------------------------------------')
print('---------- Starting a TF session ----------------------')
print('-------------------------------------------------------')
print('')
tf_weights = []
tf.set_random_seed(1234)
# Training:
with tf.Session() as sess:
sess.run(tf.global_variables_initializer())
writer = tf.summary.FileWriter('graph', sess.graph)
print('-------------------------------------------------------')
print('--------------- Training phase ------------------------')
print('-------------------------------------------------------')
for i in range(epochs):
steps = (int)(np.ceil(float(N) / float(BATCH_SIZE)))
total_l = 0
total_acc = 0
for step in range(steps):
x_in, y_in = get_batch(step, BATCH_SIZE, training_images,
training_labels)
l, acc, _ = sess.run([loss, accuracy, train_op], {
input_data: x_in,
input_labels: y_in,
do_rate: 0.5
})
total_l += l
total_acc += np.sum(acc)
#pdb.set_trace()
total_acc /= np.float32(N)
print(
"Epoch {}: Training loss = {}, Training accuracy = {}".format(
i, total_l, total_acc))
# Test:
total_acc = 0
steps = (int)(np.ceil(float(Nt) / float(BATCH_SIZE)))
for step in range(steps):
x_in, y_in = get_batch(step, BATCH_SIZE, test_images, test_labels)
acc = sess.run([accuracy], {
input_data: x_in,
input_labels: y_in,
do_rate: 1
})
total_acc += np.sum(acc)
total_acc /= np.float32(Nt)
print('\n-----------------------')
print("Test accuracy = {}".format(total_acc))
print('-------------------------------------------------------')
#################################################################
### Exporting the trained weights into a list of numpy vectors
for v in tf.trainable_variables():
tf_weights.append(sess.run(v))
writer.close()
print('')
print('-------------------------------------------------------')
print('---------- Starting a Keras session -------------------')
print('-------------------------------------------------------')
print('')
#################################################################
""" Building a Keras Model """
input_layer = Input(shape=(HEIGHT, WIDTH, 1), name='input_layer')
Kkcnn1 = Conv2D(filters=32,
kernel_size=3,
strides=(1, 1),
padding='same',
activation='relu')(input_layer)
Kkmaxpool1 = MaxPooling2D(pool_size=2)(Kkcnn1)
Kkcnn2 = Conv2D(filters=32,
kernel_size=3,
strides=(1, 1),
padding='valid',
activation='relu')(Kkmaxpool1)
Kkmaxpool2 = MaxPooling2D(pool_size=2)(Kkcnn2)
Kkflat = Flatten()(Kkmaxpool2)
Kkdense1 = Dense(units=128, activation='relu')(Kkflat)
Kkdropout = Dropout(.5)(Kkdense1)
output_layer = Dense(units=NUM_CLASSES, activation='softmax')(Kkdropout)
model = Model(inputs=input_layer, outputs=output_layer)
model.compile(optimizer=tf.train.AdamOptimizer(),
loss='categorical_crossentropy',
metrics=['accuracy'])
#################################################################
#################################################################
### Loarding the already trained weights, onto the keras layers
c = 0 # counter for iterating over tensorflow trainable variables
#pdb.set_trace()
for l in model.layers:
trainable_weights = l.trainable_weights
if not trainable_weights:
# empty trainable weight list in this keras layer; so move on to the next layer.
continue
len_w = len(
trainable_weights
) # e.g. for a normal conv layer, it is two: weight and bias.
l.set_weights(tf_weights[c:c + len_w])
c += len_w
accuracy = model.evaluate(x=test_images,
y=test_labels,
batch_size=BATCH_SIZE)
print('\n')
print('Keras test score = {}'.format(accuracy))
print('\n')
def VGG16(include_top=True,
weights='imagenet',
input_tensor=None,
input_shape=None,
pooling=None,
classes=1000):
"""Instantiates the VGG16 architecture.
Optionally loads weights pre-trained
on ImageNet. Note that when using TensorFlow,
for best performance you should set
`image_data_format="channels_last"` in your Keras config
at ~/.keras/keras.json.
The model and the weights are compatible with both
TensorFlow and Theano. The data format
convention used by the model is the one
specified in your Keras config file.
Arguments:
include_top: whether to include the 3 fully-connected
layers at the top of the network.
weights: one of `None` (random initialization)
or "imagenet" (pre-training on ImageNet).
input_tensor: optional Keras tensor (i.e. output of `layers.Input()`)
to use as image input for the model.
input_shape: optional shape tuple, only to be specified
if `include_top` is False (otherwise the input shape
has to be `(224, 224, 3)` (with `channels_last` data format)
or `(3, 224, 224)` (with `channels_first` data format).
It should have exactly 3 inputs channels,
and width and height should be no smaller than 48.
E.g. `(200, 200, 3)` would be one valid value.
pooling: Optional pooling mode for feature extraction
when `include_top` is `False`.
- `None` means that the output of the model will be
the 4D tensor output of the
last convolutional layer.
- `avg` means that global average pooling
will be applied to the output of the
last convolutional layer, and thus
the output of the model will be a 2D tensor.
- `max` means that global max pooling will
be applied.
classes: optional number of classes to classify images
into, only to be specified if `include_top` is True, and
if no `weights` argument is specified.
Returns:
A Keras model instance.
Raises:
ValueError: in case of invalid argument for `weights`,
or invalid input shape.
"""
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')
# Determine proper input shape
input_shape = _obtain_input_shape(input_shape,
default_size=224,
min_size=48,
data_format=K.image_data_format(),
include_top=include_top)
if input_tensor is None:
img_input = Input(shape=input_shape)
else:
img_input = Input(tensor=input_tensor, shape=input_shape)
# Block 1
x = Conv2D(64, (3, 3),
activation='relu',
padding='same',
name='block1_conv1')(img_input)
x = Conv2D(64, (3, 3),
activation='relu',
padding='same',
name='block1_conv2')(x)
x = MaxPooling2D((2, 2), strides=(2, 2), name='block1_pool')(x)
# Block 2
x = Conv2D(128, (3, 3),
activation='relu',
padding='same',
name='block2_conv1')(x)
x = Conv2D(128, (3, 3),
activation='relu',
padding='same',
name='block2_conv2')(x)
x = MaxPooling2D((2, 2), strides=(2, 2), name='block2_pool')(x)
# Block 3
x = Conv2D(256, (3, 3),
activation='relu',
padding='same',
name='block3_conv1')(x)
x = Conv2D(256, (3, 3),
activation='relu',
padding='same',
name='block3_conv2')(x)
x = Conv2D(256, (3, 3),
activation='relu',
padding='same',
name='block3_conv3')(x)
x = MaxPooling2D((2, 2), strides=(2, 2), name='block3_pool')(x)
# Block 4
x = Conv2D(512, (3, 3),
activation='relu',
padding='same',
name='block4_conv1')(x)
x = Conv2D(512, (3, 3),
activation='relu',
padding='same',
name='block4_conv2')(x)
x = Conv2D(512, (3, 3),
activation='relu',
padding='same',
name='block4_conv3')(x)
x = MaxPooling2D((2, 2), strides=(2, 2), name='block4_pool')(x)
# Block 5
x = Conv2D(512, (3, 3),
activation='relu',
padding='same',
name='block5_conv1')(x)
x = Conv2D(512, (3, 3),
activation='relu',
padding='same',
name='block5_conv2')(x)
x = Conv2D(512, (3, 3),
activation='relu',
padding='same',
name='block5_conv3')(x)
x = MaxPooling2D((2, 2), strides=(2, 2), name='block5_pool')(x)
if include_top:
# Classification block
x = Flatten(name='flatten')(x)
x = Dense(4096, activation='relu', name='fc1')(x)
x = Dense(4096, activation='relu', name='fc2')(x)
x = Dense(classes, activation='softmax', name='predictions')(x)
else:
if pooling == 'avg':
x = GlobalAveragePooling2D()(x)
elif pooling == 'max':
x = GlobalMaxPooling2D()(x)
# 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='vgg16')
# load weights
if weights == 'imagenet':
if include_top:
weights_path = get_file(
'vgg16_weights_tf_dim_ordering_tf_kernels.h5',
WEIGHTS_PATH,
cache_subdir='models')
else:
weights_path = get_file(
'vgg16_weights_tf_dim_ordering_tf_kernels_notop.h5',
WEIGHTS_PATH_NO_TOP,
cache_subdir='models')
model.load_weights(weights_path)
if K.backend() == 'theano':
layer_utils.convert_all_kernels_in_model(model)
if K.image_data_format() == 'channels_first':
if include_top:
maxpool = model.get_layer(name='block5_pool')
shape = maxpool.output_shape[1:]
dense = model.get_layer(name='fc1')
layer_utils.convert_dense_weights_data_format(
dense, shape, 'channels_first')
if K.backend() == 'tensorflow':
warnings.warn('You are using the TensorFlow backend, yet you '
'are using the Theano '
'image data format convention '
'(`image_data_format="channels_first"`). '
'For best performance, set '
'`image_data_format="channels_last"` in '
'your Keras config '
'at ~/.keras/keras.json.')
return model
def nn_base(input_tensor=None, trainable=False):
# Determine proper input shape
input_shape = (None, None, 3)
if input_tensor is None:
img_input = Input(shape=input_shape)
else:
if not is_keras_tensor(input_tensor):
img_input = Input(tensor=input_tensor, shape=input_shape)
else:
img_input = input_tensor
bn_axis = 3
x = ZeroPadding2D((3, 3))(img_input)
x = Convolution2D(64, (7, 7),
strides=(2, 2),
name='conv1',
trainable=trainable)(x)
x = FixedBatchNormalization(axis=bn_axis, name='bn_conv1')(x)
x = Activation('relu')(x)
x = MaxPooling2D((3, 3), strides=(2, 2))(x)
x = conv_block(x,
3, [64, 64, 256],
stage=2,
block='a',
strides=(1, 1),
trainable=trainable)
x = identity_block(x,
3, [64, 64, 256],
stage=2,
block='b',
trainable=trainable)
x = identity_block(x,
3, [64, 64, 256],
stage=2,
block='c',
trainable=trainable)
x = conv_block(x,
3, [128, 128, 512],
stage=3,
block='a',
trainable=trainable)
x = identity_block(x,
3, [128, 128, 512],
stage=3,
block='b',
trainable=trainable)
x = identity_block(x,
3, [128, 128, 512],
stage=3,
block='c',
trainable=trainable)
x = identity_block(x,
3, [128, 128, 512],
stage=3,
block='d',
trainable=trainable)
x = conv_block(x,
3, [256, 256, 1024],
stage=4,
block='a',
trainable=trainable)
x = identity_block(x,
3, [256, 256, 1024],
stage=4,
block='b',
trainable=trainable)
x = identity_block(x,
3, [256, 256, 1024],
stage=4,
block='c',
trainable=trainable)
x = identity_block(x,
3, [256, 256, 1024],
stage=4,
block='d',
trainable=trainable)
x = identity_block(x,
3, [256, 256, 1024],
stage=4,
block='e',
trainable=trainable)
x = identity_block(x,
3, [256, 256, 1024],
stage=4,
block='f',
trainable=trainable)
return x