File size: 4,344 Bytes
9a393e2 |
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 |
# Copyright 2017 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.
# ==============================================================================
"""Tests for object_detection.predictors.heads.box_head."""
import tensorflow as tf
from google.protobuf import text_format
from object_detection.builders import hyperparams_builder
from object_detection.predictors.heads import box_head
from object_detection.protos import hyperparams_pb2
from object_detection.utils import test_case
class MaskRCNNBoxHeadTest(test_case.TestCase):
def _build_arg_scope_with_hyperparams(self,
op_type=hyperparams_pb2.Hyperparams.FC):
hyperparams = hyperparams_pb2.Hyperparams()
hyperparams_text_proto = """
activation: NONE
regularizer {
l2_regularizer {
}
}
initializer {
truncated_normal_initializer {
}
}
"""
text_format.Merge(hyperparams_text_proto, hyperparams)
hyperparams.op = op_type
return hyperparams_builder.build(hyperparams, is_training=True)
def test_prediction_size(self):
box_prediction_head = box_head.MaskRCNNBoxHead(
is_training=False,
num_classes=20,
fc_hyperparams_fn=self._build_arg_scope_with_hyperparams(),
use_dropout=True,
dropout_keep_prob=0.5,
box_code_size=4,
share_box_across_classes=False)
roi_pooled_features = tf.random_uniform(
[64, 7, 7, 1024], minval=-10.0, maxval=10.0, dtype=tf.float32)
prediction = box_prediction_head.predict(
features=roi_pooled_features, num_predictions_per_location=1)
self.assertAllEqual([64, 1, 20, 4], prediction.get_shape().as_list())
class ConvolutionalBoxPredictorTest(test_case.TestCase):
def _build_arg_scope_with_hyperparams(
self, op_type=hyperparams_pb2.Hyperparams.CONV):
hyperparams = hyperparams_pb2.Hyperparams()
hyperparams_text_proto = """
activation: NONE
regularizer {
l2_regularizer {
}
}
initializer {
truncated_normal_initializer {
}
}
"""
text_format.Merge(hyperparams_text_proto, hyperparams)
hyperparams.op = op_type
return hyperparams_builder.build(hyperparams, is_training=True)
def test_prediction_size(self):
box_prediction_head = box_head.ConvolutionalBoxHead(
is_training=True,
box_code_size=4,
kernel_size=3)
image_feature = tf.random_uniform(
[64, 17, 19, 1024], minval=-10.0, maxval=10.0, dtype=tf.float32)
box_encodings = box_prediction_head.predict(
features=image_feature,
num_predictions_per_location=1)
self.assertAllEqual([64, 323, 1, 4], box_encodings.get_shape().as_list())
class WeightSharedConvolutionalBoxPredictorTest(test_case.TestCase):
def _build_arg_scope_with_hyperparams(
self, op_type=hyperparams_pb2.Hyperparams.CONV):
hyperparams = hyperparams_pb2.Hyperparams()
hyperparams_text_proto = """
activation: NONE
regularizer {
l2_regularizer {
}
}
initializer {
truncated_normal_initializer {
}
}
"""
text_format.Merge(hyperparams_text_proto, hyperparams)
hyperparams.op = op_type
return hyperparams_builder.build(hyperparams, is_training=True)
def test_prediction_size(self):
box_prediction_head = box_head.WeightSharedConvolutionalBoxHead(
box_code_size=4)
image_feature = tf.random_uniform(
[64, 17, 19, 1024], minval=-10.0, maxval=10.0, dtype=tf.float32)
box_encodings = box_prediction_head.predict(
features=image_feature,
num_predictions_per_location=1)
self.assertAllEqual([64, 323, 4], box_encodings.get_shape().as_list())
if __name__ == '__main__':
tf.test.main()
|