/
eval_image_classifier.py
273 lines (232 loc) · 11.1 KB
/
eval_image_classifier.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
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
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
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
141
142
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
168
169
170
171
172
173
174
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
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
230
231
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
267
268
269
270
271
272
273
# Copyright 2016 The TensorFlow Authors. All Rights Reserved.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
# ==============================================================================
"""Generic evaluation script that evaluates a model using a given dataset."""
from __future__ import absolute_import
from __future__ import division
from __future__ import print_function
import math
import tensorflow as tf
import pickle
from datasets import dataset_factory
from nets import nets_factory
from preprocessing import preprocessing_factory
slim = tf.contrib.slim
tf.app.flags.DEFINE_integer(
'batch_size', 100, 'The number of samples in each batch.')
tf.app.flags.DEFINE_integer(
'max_num_batches', None,
'Max number of batches to evaluate by default use all.')
tf.app.flags.DEFINE_string(
'master', '', 'The address of the TensorFlow master to use.')
tf.app.flags.DEFINE_string(
'checkpoint_path', '/tmp/tfmodel/',
'The directory where the model was written to or an absolute path to a '
'checkpoint file.')
tf.app.flags.DEFINE_string(
'eval_dir', '/tmp/tfmodel/', 'Directory where the results are saved to.')
tf.app.flags.DEFINE_integer(
'num_preprocessing_threads', 4,
'The number of threads used to create the batches.')
tf.app.flags.DEFINE_string(
'dataset_name', 'imagenet', 'The name of the dataset to load.')
tf.app.flags.DEFINE_string(
'dataset_split_name', 'test', 'The name of the train/test split.')
tf.app.flags.DEFINE_string(
'dataset_dir', None, 'The directory where the dataset files are stored.')
tf.app.flags.DEFINE_integer(
'labels_offset', 0,
'An offset for the labels in the dataset. This flag is primarily used to '
'evaluate the VGG and ResNet architectures which do not use a background '
'class for the ImageNet dataset.')
tf.app.flags.DEFINE_string(
'model_name', 'inception_v3', 'The name of the architecture to evaluate.')
tf.app.flags.DEFINE_string(
'preprocessing_name', None, 'The name of the preprocessing to use. If left '
'as `None`, then the model_name flag is used.')
tf.app.flags.DEFINE_float(
'moving_average_decay', None,
'The decay to use for the moving average.'
'If left as None, then moving averages are not used.')
tf.app.flags.DEFINE_integer(
'eval_image_size', None, 'Eval image size')
tf.app.flags.DEFINE_bool(
'print_misclassified_images', False, 'Print print_misclassified_images')
FLAGS = tf.app.flags.FLAGS
def _create_local(name, shape, collections=None, validate_shape=True,
dtype=tf.float32):
"""Creates a new local variable.
Args:
name: The name of the new or existing variable.
shape: Shape of the new or existing variable.
collections: A list of collection names to which the Variable will be added.
validate_shape: Whether to validate the shape of the variable.
dtype: Data type of the variables.
Returns:
The created variable.
"""
# Make sure local variables are added to tf.GraphKeys.LOCAL_VARIABLES
collections = list(collections or [])
collections += [tf.GraphKeys.LOCAL_VARIABLES]
return tf.Variable(
initial_value=tf.zeros(shape, dtype=dtype),
name=name,
trainable=False,
collections=collections,
validate_shape=validate_shape)
# Function to aggregate confusion
def _get_streaming_metrics(prediction, label, num_classes):
with tf.name_scope("eval"):
batch_confusion = tf.confusion_matrix(label, prediction,
num_classes=num_classes,
name='batch_confusion')
confusion = _create_local('confusion_matrix',
shape=[num_classes, num_classes],
dtype=tf.int32)
# Create the update op for doing a "+=" accumulation on the batch
confusion_update = confusion.assign(confusion + batch_confusion)
# Cast counts to float so tf.summary.image renormalizes to [0,255]
confusion_image = tf.reshape(tf.cast(confusion, tf.float32),
[1, num_classes, num_classes, 1])
return confusion, confusion_update
def main(_):
if not FLAGS.dataset_dir:
raise ValueError('You must supply the dataset directory with --dataset_dir')
tf.logging.set_verbosity(tf.logging.INFO)
with tf.Graph().as_default():
tf_global_step = slim.get_or_create_global_step()
######################
# Select the dataset #
######################
dataset = dataset_factory.get_dataset(
FLAGS.dataset_name, FLAGS.dataset_split_name, FLAGS.dataset_dir)
####################
# Select the model #
####################
network_fn = nets_factory.get_network_fn(
FLAGS.model_name,
num_classes=(dataset.num_classes - FLAGS.labels_offset),
is_training=False)
##############################################################
# Create a dataset provider that loads data from the dataset #
##############################################################
provider = slim.dataset_data_provider.DatasetDataProvider(
dataset,
shuffle=False,
common_queue_capacity=2 * FLAGS.batch_size,
common_queue_min=FLAGS.batch_size)
[image, label, filename] = provider.get(['image', 'label', 'filename'])
label -= FLAGS.labels_offset
#####################################
# Select the preprocessing function #
#####################################
preprocessing_name = FLAGS.preprocessing_name or FLAGS.model_name
image_preprocessing_fn = preprocessing_factory.get_preprocessing(
preprocessing_name,
is_training=False)
eval_image_size = FLAGS.eval_image_size or network_fn.default_image_size
image = image_preprocessing_fn(image, eval_image_size, eval_image_size)
images, labels, filenames = tf.train.batch(
[image, label, filename],
batch_size=FLAGS.batch_size,
num_threads=FLAGS.num_preprocessing_threads,
capacity=5 * FLAGS.batch_size)
####################
# Define the model #
####################
logits, end_points = network_fn(images)
preprobs = end_points['Predictions']
if FLAGS.moving_average_decay:
variable_averages = tf.train.ExponentialMovingAverage(
FLAGS.moving_average_decay, tf_global_step)
variables_to_restore = variable_averages.variables_to_restore(
slim.get_model_variables())
variables_to_restore[tf_global_step.op.name] = tf_global_step
else:
variables_to_restore = slim.get_variables_to_restore()
predictions = tf.argmax(logits, 1)
labels = tf.squeeze(labels)
mislabeled = tf.not_equal(predictions, labels)
mislabeled_filenames = tf.boolean_mask(filenames, mislabeled)
original_classes = tf.boolean_mask(labels, mislabeled)
predicted_classes = tf.boolean_mask(predictions, mislabeled)
probabilities = tf.reduce_max(preprobs, 1)
names_to_values, names_to_updates = slim.metrics.aggregate_metric_map({
'Accuracy': slim.metrics.streaming_accuracy(predictions, labels),
'Recall_5': slim.metrics.streaming_recall_at_k(
logits, labels, 5),
'Mean_absolute': tf.metrics.mean_absolute_error(labels,
predictions),
'Confusion_matrix': _get_streaming_metrics(predictions, labels,
dataset.num_classes - FLAGS.labels_offset),
'mislabeled_filenames': tf.contrib.metrics.streaming_concat(mislabeled_filenames),
'original_classes': tf.contrib.metrics.streaming_concat(original_classes),
'predicted_classes': tf.contrib.metrics.streaming_concat(predicted_classes),
'probabilities': tf.contrib.metrics.streaming_concat(probabilities),
})
# Print the summaries to screen.
unnames = ['Confusion_matrix', 'mislabeled_filenames', 'original_classes', 'predicted_classes', 'probabilities']
for name, value in names_to_values.items():
if name not in unnames:
summary_name = 'eval/%s' % name
op = tf.summary.scalar(summary_name, value, collections=[])
op = tf.Print(op, [value], summary_name)
tf.add_to_collection(tf.GraphKeys.SUMMARIES, op)
# op = tf.Print(names_to_values['mislabeled_filenames'], [names_to_values['mislabeled_filenames']], 'testing', summarize=1000)
# TODO(sguada) use num_epochs=1
if FLAGS.max_num_batches:
num_batches = FLAGS.max_num_batches
else:
# This ensures that we make a single pass over all of the data.
num_batches = math.ceil(dataset.num_samples / float(FLAGS.batch_size))
if tf.gfile.IsDirectory(FLAGS.checkpoint_path):
checkpoint_path = tf.train.latest_checkpoint(FLAGS.checkpoint_path)
else:
checkpoint_path = FLAGS.checkpoint_path
tf.logging.info('Evaluating %s' % checkpoint_path)
eval_op = list(names_to_updates.values())
[
confusion_matrix,
mislabeled_filenames,
original_classes,
predicted_classes,
probabilities,
] = slim.evaluation.evaluate_once(
master=FLAGS.master,
checkpoint_path=checkpoint_path,
logdir=FLAGS.eval_dir,
num_evals=num_batches,
eval_op=eval_op,
variables_to_restore=variables_to_restore,
# session_config=session_config,
final_op=[
names_to_updates['Confusion_matrix'],
names_to_values['mislabeled_filenames'],
names_to_values['original_classes'],
names_to_values['predicted_classes'],
names_to_values['probabilities']
]
)
print(confusion_matrix)
filenames = list(mislabeled_filenames)
original = list(original_classes)
predicted = list(predicted_classes)
probabilities = list(probabilities)
with open('misclassified_images.p', 'wb') as f:
pickle.dump(list(zip(filenames, original, predicted, probabilities)), f)
if FLAGS.print_misclassified_images:
zipped = list(zip(filenames, original, predicted, probabilities))
print(zipped)
if __name__ == '__main__':
tf.app.run()