data_logging_utils.py 8.86 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
import re
22
from textwrap import wrap
23
24
25
26
27

# 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

28
29
import utils.data_evaluation_utils as evaluation

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
80
81
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)

82
83
84
85
86
87
88
89
90
91
92
93
94
95
    def labels_generator(self, labels):
        """ Label Generator Function

        This function processess an input array of labels.

        Args:
            labels (arr): Vector/Array of labels (if applicable)

        Returns:
            label_classes (list): List of processed labels

        Raises:
            None
        """
96
97
98
99
100
101
102
103
104
105

        label_classes = []

        for label in labels:

            label_class = re.sub(r'([a-z](?=[A-Z])|[A-Z](?=[A-Z][a-z]))', r'\1 ', label)
            label_class = ['\n'.join(wrap(element, 40)) for element in label_class]
            label_classes.append(label_class)

        return label_classes
106

107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
    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)
123

124
    def loss_per_iteration(self, loss_per_iteration, batch_index, iteration):
125
        """Log of loss / iteration
126

127
128
129
130
131
        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
132
            iteration (int): Current iteration value
133
134
135
136
137
138
139
140
141

        Returns:
            None

        Raises:
            None
        """

        print("Loss for Iteration {} is: {}".format(batch_index, loss_per_iteration))
142
        self.log_writer['train'].add_scalar(tag= 'loss / iteration', loss_per_iteration, iteration)
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167

    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)
168

169
170
    # Currently, no confusion matrix is required
    # TODO: add a confusion matrix per epoch and confusion matrix plot functions if required
171

172
173
174
175
    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.
176

177
        Args:
178
179
180
181
            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
182
183

        Returns:
184
            mean_dice_score (torch.tensor): Mean dice score value
185

186
        Raises
187
188
189
            None
        """

190
191
192
193
194
195
196
        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
197

198
199
    def plot_dice_score(self, dice_score, phase, plot_name, title, epochs):
        """Function plotting dice score for multiple epochs
200

201
        This function plots the dice score for each epoch.
202

203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
        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)
230

231
    # Currently, also no need for an evaluation box plot
232

233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
    def sample_image_per_epoch(self, prediction, ground_truth, phase, epoch):
        """Function plotting mirrored images

        This function plots a predicted and a grond truth images side-by-side.

        Args:
            prediction (torch.tensor): Predicted image after passing throught the network
            ground_truth (torch.tensor): Labelled ground truth image
            phase (str): Current run mode or phase
            epoch (int): Current epoch value

        Returns:
            None

        Raises
            None
        """

        print("Sample Image is being loaded...", end='', flush= True)
        figure, ax = plt.subplots(nrows = len(prediction), ncols = 2)

        for i in range(len(prediction)):
            ax[i][0].imshow(prediction[i])
            ax[i][0].set_title("Predicted Image")
            ax[i][0].axis('off')

            ax[i][1].imshow(ground_truth[i])
            ax[i][1].set_title('Ground Truth Image')
            ax[i][1].axis('off')

        figure.set_tight_layout()
        self.log_writer[phase].add_figure('sample_prediction/'+phase, figure, epoch)

        print("Sample Image successfully loaded!")
267
268

    def close(self):
Andrei-Claudiu Roibu's avatar
Andrei-Claudiu Roibu committed
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
        """Close the log writer

        This function closes the two log writers.

        Args:
            None

        Returns:
            None

        Raises
            None
        """
        
        self.log_writer['train'].close()
        self.log_writer['test'].close()