data_logging_utils.py 6.92 KB
Newer Older
1
2
3
4
5
6
7
8
9
10
11
12
13
14
"""Data Logging Functions

Description:
-------------
This folder contains several functions which, either on their own or included in larger pieces of software, perform data logging tasks.

Usage
-------------
To use content from this folder, import the functions and instantiate them as you wish to use them:

    from utils.data_logging_utils import function_name

"""

15
import os
16
import matplotlib
17
18
19
import matplotlib.pyplot as plt
import shutil
import logging
20
import numpy as np
21
22
23
24
25

# The SummaryWriter class provides a high-level API to create an event file in a given directory and add summaries and events to it.
# More here: https://tensorboardx.readthedocs.io/en/latest/tensorboard.html
from tensorboardX import SummaryWriter

26
27
import utils.data_evaluation_utils as evaluation

28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
plt.axis('scaled')

class LogWriter():

    """Log Writer class for the BrainMapper U-net.

    This class contains the pytorch implementation of the several logging functions required for the BrainMapper project.
    These functions are designed to keep track of progress during training, and also aid debugging.

    Args:
        number_of_classes (int): Number of classes
        logs_directory (str): Directory for outputing training logs
        experiment_name (str): Name of the experiment
        use_last_checkpoint (bool): Flag for loading the previous checkpoint
        labels (arr): Vector/Array of labels (if applicable)
        confusion_matrix_cmap (class): Colour Map to be used for the Conusion Matrix

    Returns:
        None

    Raises:
        None
    """

    def __init__(self, number_of_classes, logs_directory, experiment_name, use_last_checkpoint=False, labels=None, confusion_matrix_cmap= plt.cm.Blues):
        
        self.number_of_classes = number_of_classes
        training_logs_directory = os.path.join(logs_directory, experiment_name, "train")
        testing_logs_directory = os.path.join(logs_directory, experiment_name, "test")

        # If the logs directory exist, we clear their contents to allow new logs to be created
        if not use_last_checkpoint:
            if os.path.exists(training_logs_directory):
                shutil.rmtree(training_logs_directory)
            if os.path.exists(testing_logs_directory):
                shutil.rmtree(testing_logs_directory)

        self.log_writer = {
            'train': SummaryWriter(logdir= training_logs_directory),
            'test:': SummaryWriter(logdir= testing_logs_directory)
        }

        self.confusion_matrix_color_map = confusion_matrix_cmap

        self.current_iteration = 1

        self.labels = self.labels_generator(labels)

        self.logger = logging.getLogger()
        file_handler = logging.FileHandler("{}/{}.log".format(os.path.join(logs_directory, experiment_name), "console_logs"))
        self.logger.addHandler(file_handler)

80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
    def log(self, message):
        """Log function

        This function logs a message in the logger.

        Args:
            message (str): Message to be logged

        Returns:
            None

        Raises:
            None
        """

        self.logger.info(msg= message)
96

97
    def loss_per_iteration(self, loss_per_iteration, batch_index, iteration):
98
        """Log of loss / iteration
99

100
101
102
103
104
        This function records the loss for every iteration.

        Args:
            loss_per_iteration (torch.tensor): Value of loss for every iteration step
            batch_index (int): Index of current batch
105
            iteration (int): Current iteration value
106
107
108
109
110
111
112
113
114

        Returns:
            None

        Raises:
            None
        """

        print("Loss for Iteration {} is: {}".format(batch_index, loss_per_iteration))
115
        self.log_writer['train'].add_scalar(tag= 'loss / iteration', loss_per_iteration, iteration)
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140

    def loss_per_epoch(self, losses, phase, epoch):
        """Log function

        This function records the loss for every epoch.

        Args:
            losses (list): Values of all the losses recorded during the training epoch
            phase (str): Current run mode or phase
            epoch (int): Current epoch value

        Returns:
            None

        Raises:
            None
        """

        if phase == 'train':
            loss = losses[-1]
        else:
            loss = np.mean(losses)

        print("Loss for Epoch {} of {} is: {}".format(epoch, phase, loss))
        self.log_writer[phase].add_scalar(tag= 'loss / iteration', loss, epoch)
141

142
143
    # Currently, no confusion matrix is required
    # TODO: add a confusion matrix per epoch and confusion matrix plot functions if required
144

145
146
147
148
    def dice_score_per_epoch(self, phase, outputs, correct_labels, epoch):
        """Function calculating dice score for each epoch

        This function computes the dice score for each epoch.
149

150
        Args:
151
152
153
154
            phase (str): Current run mode or phase
            outputs (torch.tensor): Tensor of all the network outputs (Y-hat)
            correct_labels (torch.tensor): Output ground-truth labelled data (Y)
            epoch (int): Current epoch value
155
156

        Returns:
157
            mean_dice_score (torch.tensor): Mean dice score value
158

159
        Raises
160
161
162
            None
        """

163
164
165
166
167
168
169
        print("Dice Score is being calculated...", end='', flush= True)
        dice_score = evaluation.dice_score_calculator(outputs, correct_labels, self.number_of_classes)
        mean_dice_score = torch.mean(dice_score)
        self.plot_dice_score(dice_score, phase, plot_name='dice_score_per_epoch', title='Dice Score', epoch)
        self.log_writer[phase].add_scalar(tag= 'loss / iteration', loss, epoch)
        print("Dice Score calculated successfully")
        return mean_dice_score
170

171
172
    def plot_dice_score(self, dice_score, phase, plot_name, title, epochs):
        """Function plotting dice score for multiple epochs
173

174
        This function plots the dice score for each epoch.
175

176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
        Args:
            dice_score (torch.tensor): Dice score value for each class
            phase (str): Current run mode or phase
            plot_name (str): Caption name for later refference
            title (str): Plot title
            epoch (int): Current epoch value

        Returns:
            None

        Raises
            None
        """

        figure = matplotlib.figure.Figure() # Might add some arguments here later
        ax = figure.add_subplot(1, 1, 1)
        ax.set_xlabel(title)
        ax.xaxis.set_label_position('top')
        ax.bar(np.arange(self.number_of_classes), dice_score)
        ax.set_xticks(np.arange(self.number_of_classes))
        ax.set_xticklabels(self.labels)
        ax.xaxis.tick_bottom()

        if step:
            self.log_writer[phase].add_figure(plot_name + '/' + phase, figure, global_step= epochs)
        else:
            self.log_writer[phase].add_figure(plot_name + '/' + phase, figure)
203
204
205
206
207
208
209
210
211
212
213
214
215
216

    def plot_evaluation_box(self):
        pass

    def sample_image_per_epoch(self):
        pass

    def graph(self):
        pass

    def close(self):
        pass

    def labels_generator(self):
217
        return pass