# Print out a summary of the model you created
model.summary()
# ### Congratulations! You've created your very own U-Net model architecture!
# Next, you'll check that you did everything correctly by comparing your model summary to the example model defined below.
#
# ### Double check your model
#
# To double check that you created the correct model, use a function that we've provided to create the same model, and check that the layers and the layer dimensions match!
# In[21]:
# Import predefined utilities
import util
# In[22]:
# Create a model using a predefined function
model_2 = util.unet_model_3d(depth=2,
loss_function='categorical_crossentropy',
metrics=['categorical_accuracy'])
# In[23]:
# Print out a summary of the model created by the predefined function
model_2.summary()
# #### Look at the model summary for the U-Net you created and compare it to the summary for the example model created by the predefined function you imported above.
# #### That's it for this exercise, we hope this have provided you with more insight into the network architecture you'll be working with in this week's assignment!
print(label[0, :, :, 0])
dc = soft_dice_loss(pred, label, epsilon=1)
print(f"soft dice loss: {dc.eval():.4f}")
# <a name="4"></a>
# # 4 Create and Train the model
#
# Once you've finished implementing the soft dice loss, we can create the model!
#
# We'll use the `unet_model_3d` function in `utils` which we implemented for you.
# - This creates the model architecture and compiles the model with the specified loss functions and metrics.
# In[26]:
model = util.unet_model_3d(loss_function=soft_dice_loss,
metrics=[dice_coefficient])
# In[27]:
# run this cell if you didn't run the training cell in section 4.1
base_dir = HOME_DIR + "processed/"
with open(base_dir + "config.json") as json_file:
config = json.load(json_file)
# Get generators for training and validation sets
train_generator = util.VolumeDataGenerator(config["train"],
base_dir + "train/",
batch_size=3,
dim=(160, 160, 16),
verbose=0)
valid_generator = util.VolumeDataGenerator(config["valid"],
base_dir + "valid/",