Python: Advanced Guide to Artificial Intelligence

Modeling FCN for segmentation

Import the libraries and get the shape of the input. The number of labels is defined as 6:

from .resnet50 import ResNet50nb_labels = 6img_height, img_width, _ = input_shapeinput_tensor = tf.keras.layers.Input(shape=input_shape)weights = 'imagenet'

A ResNet model pre-trained on ImageNet will be used as the base model. The following code can be used to define the base model using ResNet:

resnet50_model = ResNet50(    include_top=False, weights='imagenet', input_tensor=input_tensor)

Now we will use the following code to take the final three layers from the ResNet:

final_32 = resnet50_model.get_layer('final_32').outputfinal_16 = resnet50_model.get_layer('final_16').outputfinal_x8 = resnet50_model.get_layer('final_x8' ...