def training():
# train_generator, validation_generator = prepare_data()
# train_generator, validation_generator, test_generator = prepare_data()
conv_network = ResNet50(include_top=False,
weights='imagenet',
input_shape=(IMG_WIDTH, IMG_HEIGHT, 3))
for layer in conv_network.layers[:-3]:
layer.trainable = False
model = Sequential()
model.add(conv_network)
# model.add(AveragePooling2D((7, 7), name='avg_pool'))
model.add(Flatten())
model.add(Dense(1024, activation='relu'))
model.add(Dropout(0.5))
model.add(Dense(10, activation='softmax'))
# model.summary()
model.compile(loss='categorical_crossentropy',
optimizer=Adam(lr=0.001),
metrics=['accuracy'])
print(neuraLint.check(model))
import neuraLint from keras.layers.core import Dense from keras import Sequential model = Sequential() model.add(Dense(10, input_dim=1, activation='relu')) model.add(Dense(10, activation='relu')) model.add(Dense(10, activation='relu')) model.add(Dense(1)) model.compile(loss='mse', optimizer='adam') print(neuraLint.check(model))
alpha,
depth_multiplier,
strides=(2, 2),
block_id=4)
x = _depthwise_conv_block(x, 256, alpha, depth_multiplier, block_id=5)
x = _depthwise_conv_block(x,
512,
alpha,
depth_multiplier,
strides=(2, 2),
block_id=6)
x = _depthwise_conv_block(x, 512, alpha, depth_multiplier, block_id=7)
x = _depthwise_conv_block(x, 512, alpha, depth_multiplier, block_id=8)
x = _depthwise_conv_block(x, 512, alpha, depth_multiplier, block_id=9)
x = _depthwise_conv_block(x, 512, alpha, depth_multiplier, block_id=10)
x = _depthwise_conv_block(x, 512, alpha, depth_multiplier, block_id=11)
x = _depthwise_conv_block(x,
1024,
alpha,
depth_multiplier,
strides=(2, 2),
block_id=12)
x = _depthwise_conv_block(x, 1024, alpha, depth_multiplier, block_id=13)
x = Model(img_input, x)
x.compile(optimizer='rmsprop',
loss='categorical_crossentropy',
metrics='accuracy')
print(neuraLint.check(x))
pooling_regions = 7
input_shape = (num_rois, 512, 7, 7)
out_roi_pool = roiPoolingConv.RoiPoolingConv(pooling_regions, num_rois)([base_layers, input_rois])
out = TimeDistributed(Flatten(name='flatten'))(out_roi_pool)
out = TimeDistributed(Dense(4096, activation='relu', name='fc1'))(out)
out = TimeDistributed(Dropout(0.5))(out)
out = TimeDistributed(Dense(4096, activation='relu', name='fc2'))(out)
out = TimeDistributed(Dropout(0.5))(out)
out_class = TimeDistributed(Dense(nb_classes, activation='softmax', kernel_initializer='zero'),
name='dense_class_{}'.format(nb_classes))(out)
# note: no regression target for bg class
out_regr = TimeDistributed(Dense(4 * (nb_classes - 1), activation='linear', kernel_initializer='zero'),
name='dense_regress_{}'.format(nb_classes))(out)
return [out_class, out_regr]
img_input = Input(shape=(100, 100, 3))
roi_input = Input(shape=(None, 4))
shared_layers = nn_base(img_input, trainable=True)
# define the RPN, built on the base layers
rpn: List[Optional[Any]] = rpn(shared_layers, 60)
# classifier = classifier(shared_layers, roi_input, 2, 5, trainable=True)
rpn = Model(img_input, rpn[:2])
print(neuraLint.check(rpn))
# model.compile(optimizer='adam', loss=dice_coef_loss, metrics=[dice_coef])
model.add(Conv2D(256, (3, 3), padding='same'))
model.add(Dropout(0.2))
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(2, 2), strides=2))
model.add(Conv2D(256, (3, 3), padding='same'))
model.add(Dropout(0.25))
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(2, 2), strides=2))
model.add(Conv2D(256, (3, 3), padding='same'))
model.add(Dropout(0.25))
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(2, 2), strides=2))
model.add(Flatten())
model.add(Dense(256))
model.add(BatchNormalization())
model.add(Activation('relu'))
model.add(Dropout(0.8))
model.add(Dense(3))
model.add(Activation('softmax'))
model.compile(loss='categorical_crossentropy',
optimizer='adam',
metrics=['accuracy'])
report = neuraLint.check(model)
print(report)