def get_resnet101_datagen(self, test=False):
if (not test):
resnet101_datagen = ImageDataGenerator(
horizontal_flip=True,
shear_range=0.4,
zoom_range=0.4,
data_format=str(keras.image_data_format()),
preprocessing_function=keras.applications.resnet50.
preprocess_input)
else:
resnet101_datagen = ImageDataGenerator(data_format=str(
keras.image_data_format()),
preprocessing_function=piss)
return resnet101_datagen
def get_inception_v3_datagen(self, test_data=False):
if (not test_data):
inception_v3_train_datagen = ImageDataGenerator(
horizontal_flip=True,
shear_range=0.4,
zoom_range=0.4,
data_format=str(keras.image_data_format()),
preprocessing_functwion=keras.applications.inception_v3.
preprocess_input)
else:
inception_v3_test_datagen = ImageDataGenerator(
data_format=str(keras.image_data_format()),
preprocessing_function=keras.applications.inception_v3.
preprocess_input)
return inception_v3_train_datagen
# In[79]:
val_samples['lane'].value_counts()
# In[82]:
# dimensions of our images.
img_width, img_height = 640, 480
CROP_TOP = int(200)
CROP_BOTTOM = int(30)
nb_train_samples = nr_train_samples
nb_validation_samples = nr_val_samples
batch_size = 8
if K.image_data_format() == 'channels_first':
input_shape = (3, img_height, img_width)
else:
input_shape = (img_height, img_width, 3)
inputs = Input(shape=input_shape)
x = Cropping2D(cropping=((CROP_TOP, CROP_BOTTOM), (0, 0)),
input_shape=input_shape)(inputs)
x = GaussianNoise(0.5)(x)
x = darknet_base(x)
x = GlobalAveragePooling2D()(x)
x = Dense(3, activation='softmax')(x)
model = Model(inputs, x)
#model = load_model("models/weights.358-3.57-0.64.hdf5")
def _adjust_block(p, ip, filters, weight_decay=5e-5, id=None):
'''
Adjusts the input `p` to match the shape of the `input`
or situations where the output number of filters needs to
be changed
# Arguments:
p: input tensor which needs to be modified
ip: input tensor whose shape needs to be matched
filters: number of output filters to be matched
weight_decay: l2 regularization weight
id: string id
# Returns:
an adjusted Keras tensor
'''
channel_dim = 1 if K.image_data_format() == 'channels_first' else -1
img_dim = 2 if K.image_data_format() == 'channels_first' else -2
with K.name_scope('adjust_block'):
if p is None:
p = ip
elif p._keras_shape[img_dim] != ip._keras_shape[img_dim]:
with K.name_scope('adjust_reduction_block_%s' % id):
p = Activation('relu', name='adjust_relu_1_%s' % id)(p)
p1 = AveragePooling2D((1, 1),
strides=(2, 2),
padding='valid',
name='adjust_avg_pool_1_%s' % id)(p)
p1 = Conv2D(filters // 2, (1, 1),
padding='same',
use_bias=False,
kernel_regularizer=OrthLocalReg2D,
name='adjust_conv_1_%s' % id,
kernel_initializer='he_normal')(p1)
p2 = ZeroPadding2D(padding=((0, 1), (0, 1)))(p)
p2 = Cropping2D(cropping=((1, 0), (1, 0)))(p2)
p2 = AveragePooling2D((1, 1),
strides=(2, 2),
padding='valid',
name='adjust_avg_pool_2_%s' % id)(p2)
p2 = Conv2D(filters // 2, (1, 1),
padding='same',
use_bias=False,
kernel_regularizer=OrthLocalReg2D,
name='adjust_conv_2_%s' % id,
kernel_initializer='he_normal')(p2)
p = concatenate([p1, p2], axis=channel_dim)
p = BatchNormalization(name='adjust_bn_%s' % id)(p)
elif p._keras_shape[channel_dim] != filters:
with K.name_scope('adjust_projection_block_%s' % id):
p = Activation('relu')(p)
p = Conv2D(filters, (1, 1),
strides=(1, 1),
padding='same',
name='adjust_conv_projection_%s' % id,
use_bias=False,
kernel_regularizer=OrthLocalReg2D,
kernel_initializer='he_normal')(p)
p = BatchNormalization(name='adjust_bn_%s' % id)(p)
return p