Python nets.resnet_utils.subsample() Examples
The following are 30
code examples of nets.resnet_utils.subsample().
You can vote up the ones you like or vote down the ones you don't like,
and go to the original project or source file by following the links above each example.
You may also want to check out all available functions/classes of the module
nets.resnet_utils
, or try the search function
.
Example #1
Source File: resnet_v1_test.py From tf-pose with Apache License 2.0 | 5 votes |
def testSubsampleThreeByThree(self): x = tf.reshape(tf.to_float(tf.range(9)), [1, 3, 3, 1]) x = resnet_utils.subsample(x, 2) expected = tf.reshape(tf.constant([0, 2, 6, 8]), [1, 2, 2, 1]) with self.test_session(): self.assertAllClose(x.eval(), expected.eval())
Example #2
Source File: resnet_v2_test.py From R2CNN-Plus-Plus_Tensorflow with MIT License | 5 votes |
def testSubsampleFourByFour(self): x = tf.reshape(tf.to_float(tf.range(16)), [1, 4, 4, 1]) x = resnet_utils.subsample(x, 2) expected = tf.reshape(tf.constant([0, 2, 8, 10]), [1, 2, 2, 1]) with self.test_session(): self.assertAllClose(x.eval(), expected.eval())
Example #3
Source File: resnet_v2_test.py From R2CNN-Plus-Plus_Tensorflow with MIT License | 5 votes |
def testConv2DSameEven(self): n, n2 = 4, 2 # Input image. x = create_test_input(1, n, n, 1) # Convolution kernel. w = create_test_input(1, 3, 3, 1) w = tf.reshape(w, [3, 3, 1, 1]) tf.get_variable('Conv/weights', initializer=w) tf.get_variable('Conv/biases', initializer=tf.zeros([1])) tf.get_variable_scope().reuse_variables() y1 = slim.conv2d(x, 1, [3, 3], stride=1, scope='Conv') y1_expected = tf.to_float([[14, 28, 43, 26], [28, 48, 66, 37], [43, 66, 84, 46], [26, 37, 46, 22]]) y1_expected = tf.reshape(y1_expected, [1, n, n, 1]) y2 = resnet_utils.subsample(y1, 2) y2_expected = tf.to_float([[14, 43], [43, 84]]) y2_expected = tf.reshape(y2_expected, [1, n2, n2, 1]) y3 = resnet_utils.conv2d_same(x, 1, 3, stride=2, scope='Conv') y3_expected = y2_expected y4 = slim.conv2d(x, 1, [3, 3], stride=2, scope='Conv') y4_expected = tf.to_float([[48, 37], [37, 22]]) y4_expected = tf.reshape(y4_expected, [1, n2, n2, 1]) with self.test_session() as sess: sess.run(tf.global_variables_initializer()) self.assertAllClose(y1.eval(), y1_expected.eval()) self.assertAllClose(y2.eval(), y2_expected.eval()) self.assertAllClose(y3.eval(), y3_expected.eval()) self.assertAllClose(y4.eval(), y4_expected.eval())
Example #4
Source File: resnet_v2_test.py From R2CNN-Plus-Plus_Tensorflow with MIT License | 5 votes |
def testSubsampleThreeByThree(self): x = tf.reshape(tf.to_float(tf.range(9)), [1, 3, 3, 1]) x = resnet_utils.subsample(x, 2) expected = tf.reshape(tf.constant([0, 2, 6, 8]), [1, 2, 2, 1]) with self.test_session(): self.assertAllClose(x.eval(), expected.eval())
Example #5
Source File: resnet_v1_test.py From R2CNN-Plus-Plus_Tensorflow with MIT License | 5 votes |
def testConv2DSameOdd(self): n, n2 = 5, 3 # Input image. x = create_test_input(1, n, n, 1) # Convolution kernel. w = create_test_input(1, 3, 3, 1) w = tf.reshape(w, [3, 3, 1, 1]) tf.get_variable('Conv/weights', initializer=w) tf.get_variable('Conv/biases', initializer=tf.zeros([1])) tf.get_variable_scope().reuse_variables() y1 = slim.conv2d(x, 1, [3, 3], stride=1, scope='Conv') y1_expected = tf.to_float([[14, 28, 43, 58, 34], [28, 48, 66, 84, 46], [43, 66, 84, 102, 55], [58, 84, 102, 120, 64], [34, 46, 55, 64, 30]]) y1_expected = tf.reshape(y1_expected, [1, n, n, 1]) y2 = resnet_utils.subsample(y1, 2) y2_expected = tf.to_float([[14, 43, 34], [43, 84, 55], [34, 55, 30]]) y2_expected = tf.reshape(y2_expected, [1, n2, n2, 1]) y3 = resnet_utils.conv2d_same(x, 1, 3, stride=2, scope='Conv') y3_expected = y2_expected y4 = slim.conv2d(x, 1, [3, 3], stride=2, scope='Conv') y4_expected = y2_expected with self.test_session() as sess: sess.run(tf.global_variables_initializer()) self.assertAllClose(y1.eval(), y1_expected.eval()) self.assertAllClose(y2.eval(), y2_expected.eval()) self.assertAllClose(y3.eval(), y3_expected.eval()) self.assertAllClose(y4.eval(), y4_expected.eval())
Example #6
Source File: resnet_v1_test.py From R2CNN-Plus-Plus_Tensorflow with MIT License | 5 votes |
def testAtrousFullyConvolutionalValues(self): """Verify dense feature extraction with atrous convolution.""" nominal_stride = 32 for output_stride in [4, 8, 16, 32, None]: with slim.arg_scope(resnet_utils.resnet_arg_scope()): with tf.Graph().as_default(): with self.test_session() as sess: tf.set_random_seed(0) inputs = create_test_input(2, 81, 81, 3) # Dense feature extraction followed by subsampling. output, _ = self._resnet_small(inputs, None, is_training=False, global_pool=False, output_stride=output_stride) if output_stride is None: factor = 1 else: factor = nominal_stride // output_stride output = resnet_utils.subsample(output, factor) # Make the two networks use the same weights. tf.get_variable_scope().reuse_variables() # Feature extraction at the nominal network rate. expected, _ = self._resnet_small(inputs, None, is_training=False, global_pool=False) sess.run(tf.global_variables_initializer()) self.assertAllClose(output.eval(), expected.eval(), atol=1e-4, rtol=1e-4)
Example #7
Source File: resnet_v2_test.py From R3Det_Tensorflow with MIT License | 5 votes |
def testSubsampleThreeByThree(self): x = tf.reshape(tf.to_float(tf.range(9)), [1, 3, 3, 1]) x = resnet_utils.subsample(x, 2) expected = tf.reshape(tf.constant([0, 2, 6, 8]), [1, 2, 2, 1]) with self.test_session(): self.assertAllClose(x.eval(), expected.eval())
Example #8
Source File: resnet_v2_test.py From R3Det_Tensorflow with MIT License | 5 votes |
def testSubsampleFourByFour(self): x = tf.reshape(tf.to_float(tf.range(16)), [1, 4, 4, 1]) x = resnet_utils.subsample(x, 2) expected = tf.reshape(tf.constant([0, 2, 8, 10]), [1, 2, 2, 1]) with self.test_session(): self.assertAllClose(x.eval(), expected.eval())
Example #9
Source File: resnet_v2_test.py From R3Det_Tensorflow with MIT License | 5 votes |
def testConv2DSameEven(self): n, n2 = 4, 2 # Input image. x = create_test_input(1, n, n, 1) # Convolution kernel. w = create_test_input(1, 3, 3, 1) w = tf.reshape(w, [3, 3, 1, 1]) tf.get_variable('Conv/weights', initializer=w) tf.get_variable('Conv/biases', initializer=tf.zeros([1])) tf.get_variable_scope().reuse_variables() y1 = slim.conv2d(x, 1, [3, 3], stride=1, scope='Conv') y1_expected = tf.to_float([[14, 28, 43, 26], [28, 48, 66, 37], [43, 66, 84, 46], [26, 37, 46, 22]]) y1_expected = tf.reshape(y1_expected, [1, n, n, 1]) y2 = resnet_utils.subsample(y1, 2) y2_expected = tf.to_float([[14, 43], [43, 84]]) y2_expected = tf.reshape(y2_expected, [1, n2, n2, 1]) y3 = resnet_utils.conv2d_same(x, 1, 3, stride=2, scope='Conv') y3_expected = y2_expected y4 = slim.conv2d(x, 1, [3, 3], stride=2, scope='Conv') y4_expected = tf.to_float([[48, 37], [37, 22]]) y4_expected = tf.reshape(y4_expected, [1, n2, n2, 1]) with self.test_session() as sess: sess.run(tf.global_variables_initializer()) self.assertAllClose(y1.eval(), y1_expected.eval()) self.assertAllClose(y2.eval(), y2_expected.eval()) self.assertAllClose(y3.eval(), y3_expected.eval()) self.assertAllClose(y4.eval(), y4_expected.eval())
Example #10
Source File: resnet_v2_test.py From R3Det_Tensorflow with MIT License | 5 votes |
def testConv2DSameOdd(self): n, n2 = 5, 3 # Input image. x = create_test_input(1, n, n, 1) # Convolution kernel. w = create_test_input(1, 3, 3, 1) w = tf.reshape(w, [3, 3, 1, 1]) tf.get_variable('Conv/weights', initializer=w) tf.get_variable('Conv/biases', initializer=tf.zeros([1])) tf.get_variable_scope().reuse_variables() y1 = slim.conv2d(x, 1, [3, 3], stride=1, scope='Conv') y1_expected = tf.to_float([[14, 28, 43, 58, 34], [28, 48, 66, 84, 46], [43, 66, 84, 102, 55], [58, 84, 102, 120, 64], [34, 46, 55, 64, 30]]) y1_expected = tf.reshape(y1_expected, [1, n, n, 1]) y2 = resnet_utils.subsample(y1, 2) y2_expected = tf.to_float([[14, 43, 34], [43, 84, 55], [34, 55, 30]]) y2_expected = tf.reshape(y2_expected, [1, n2, n2, 1]) y3 = resnet_utils.conv2d_same(x, 1, 3, stride=2, scope='Conv') y3_expected = y2_expected y4 = slim.conv2d(x, 1, [3, 3], stride=2, scope='Conv') y4_expected = y2_expected with self.test_session() as sess: sess.run(tf.global_variables_initializer()) self.assertAllClose(y1.eval(), y1_expected.eval()) self.assertAllClose(y2.eval(), y2_expected.eval()) self.assertAllClose(y3.eval(), y3_expected.eval()) self.assertAllClose(y4.eval(), y4_expected.eval())
Example #11
Source File: resnet_v2_test.py From R3Det_Tensorflow with MIT License | 5 votes |
def testAtrousFullyConvolutionalValues(self): """Verify dense feature extraction with atrous convolution.""" nominal_stride = 32 for output_stride in [4, 8, 16, 32, None]: with slim.arg_scope(resnet_utils.resnet_arg_scope()): with tf.Graph().as_default(): with self.test_session() as sess: tf.set_random_seed(0) inputs = create_test_input(2, 81, 81, 3) # Dense feature extraction followed by subsampling. output, _ = self._resnet_small(inputs, None, is_training=False, global_pool=False, output_stride=output_stride) if output_stride is None: factor = 1 else: factor = nominal_stride // output_stride output = resnet_utils.subsample(output, factor) # Make the two networks use the same weights. tf.get_variable_scope().reuse_variables() # Feature extraction at the nominal network rate. expected, _ = self._resnet_small(inputs, None, is_training=False, global_pool=False) sess.run(tf.global_variables_initializer()) self.assertAllClose(output.eval(), expected.eval(), atol=1e-4, rtol=1e-4)
Example #12
Source File: resnet_v1_test.py From R3Det_Tensorflow with MIT License | 5 votes |
def testSubsampleThreeByThree(self): x = tf.reshape(tf.to_float(tf.range(9)), [1, 3, 3, 1]) x = resnet_utils.subsample(x, 2) expected = tf.reshape(tf.constant([0, 2, 6, 8]), [1, 2, 2, 1]) with self.test_session(): self.assertAllClose(x.eval(), expected.eval())
Example #13
Source File: resnet_v1_test.py From R2CNN-Plus-Plus_Tensorflow with MIT License | 5 votes |
def testConv2DSameEven(self): n, n2 = 4, 2 # Input image. x = create_test_input(1, n, n, 1) # Convolution kernel. w = create_test_input(1, 3, 3, 1) w = tf.reshape(w, [3, 3, 1, 1]) tf.get_variable('Conv/weights', initializer=w) tf.get_variable('Conv/biases', initializer=tf.zeros([1])) tf.get_variable_scope().reuse_variables() y1 = slim.conv2d(x, 1, [3, 3], stride=1, scope='Conv') y1_expected = tf.to_float([[14, 28, 43, 26], [28, 48, 66, 37], [43, 66, 84, 46], [26, 37, 46, 22]]) y1_expected = tf.reshape(y1_expected, [1, n, n, 1]) y2 = resnet_utils.subsample(y1, 2) y2_expected = tf.to_float([[14, 43], [43, 84]]) y2_expected = tf.reshape(y2_expected, [1, n2, n2, 1]) y3 = resnet_utils.conv2d_same(x, 1, 3, stride=2, scope='Conv') y3_expected = y2_expected y4 = slim.conv2d(x, 1, [3, 3], stride=2, scope='Conv') y4_expected = tf.to_float([[48, 37], [37, 22]]) y4_expected = tf.reshape(y4_expected, [1, n2, n2, 1]) with self.test_session() as sess: sess.run(tf.global_variables_initializer()) self.assertAllClose(y1.eval(), y1_expected.eval()) self.assertAllClose(y2.eval(), y2_expected.eval()) self.assertAllClose(y3.eval(), y3_expected.eval()) self.assertAllClose(y4.eval(), y4_expected.eval())
Example #14
Source File: resnet_v1_test.py From tf-pose with Apache License 2.0 | 5 votes |
def testConv2DSameEven(self): n, n2 = 4, 2 # Input image. x = create_test_input(1, n, n, 1) # Convolution kernel. w = create_test_input(1, 3, 3, 1) w = tf.reshape(w, [3, 3, 1, 1]) tf.get_variable('Conv/weights', initializer=w) tf.get_variable('Conv/biases', initializer=tf.zeros([1])) tf.get_variable_scope().reuse_variables() y1 = slim.conv2d(x, 1, [3, 3], stride=1, scope='Conv') y1_expected = tf.to_float([[14, 28, 43, 26], [28, 48, 66, 37], [43, 66, 84, 46], [26, 37, 46, 22]]) y1_expected = tf.reshape(y1_expected, [1, n, n, 1]) y2 = resnet_utils.subsample(y1, 2) y2_expected = tf.to_float([[14, 43], [43, 84]]) y2_expected = tf.reshape(y2_expected, [1, n2, n2, 1]) y3 = resnet_utils.conv2d_same(x, 1, 3, stride=2, scope='Conv') y3_expected = y2_expected y4 = slim.conv2d(x, 1, [3, 3], stride=2, scope='Conv') y4_expected = tf.to_float([[48, 37], [37, 22]]) y4_expected = tf.reshape(y4_expected, [1, n2, n2, 1]) with self.test_session() as sess: sess.run(tf.global_variables_initializer()) self.assertAllClose(y1.eval(), y1_expected.eval()) self.assertAllClose(y2.eval(), y2_expected.eval()) self.assertAllClose(y3.eval(), y3_expected.eval()) self.assertAllClose(y4.eval(), y4_expected.eval())
Example #15
Source File: resnet_v1_test.py From tf-pose with Apache License 2.0 | 5 votes |
def testSubsampleFourByFour(self): x = tf.reshape(tf.to_float(tf.range(16)), [1, 4, 4, 1]) x = resnet_utils.subsample(x, 2) expected = tf.reshape(tf.constant([0, 2, 8, 10]), [1, 2, 2, 1]) with self.test_session(): self.assertAllClose(x.eval(), expected.eval())
Example #16
Source File: resnet_v1_test.py From tf-pose with Apache License 2.0 | 5 votes |
def testConv2DSameOdd(self): n, n2 = 5, 3 # Input image. x = create_test_input(1, n, n, 1) # Convolution kernel. w = create_test_input(1, 3, 3, 1) w = tf.reshape(w, [3, 3, 1, 1]) tf.get_variable('Conv/weights', initializer=w) tf.get_variable('Conv/biases', initializer=tf.zeros([1])) tf.get_variable_scope().reuse_variables() y1 = slim.conv2d(x, 1, [3, 3], stride=1, scope='Conv') y1_expected = tf.to_float([[14, 28, 43, 58, 34], [28, 48, 66, 84, 46], [43, 66, 84, 102, 55], [58, 84, 102, 120, 64], [34, 46, 55, 64, 30]]) y1_expected = tf.reshape(y1_expected, [1, n, n, 1]) y2 = resnet_utils.subsample(y1, 2) y2_expected = tf.to_float([[14, 43, 34], [43, 84, 55], [34, 55, 30]]) y2_expected = tf.reshape(y2_expected, [1, n2, n2, 1]) y3 = resnet_utils.conv2d_same(x, 1, 3, stride=2, scope='Conv') y3_expected = y2_expected y4 = slim.conv2d(x, 1, [3, 3], stride=2, scope='Conv') y4_expected = y2_expected with self.test_session() as sess: sess.run(tf.global_variables_initializer()) self.assertAllClose(y1.eval(), y1_expected.eval()) self.assertAllClose(y2.eval(), y2_expected.eval()) self.assertAllClose(y3.eval(), y3_expected.eval()) self.assertAllClose(y4.eval(), y4_expected.eval())
Example #17
Source File: resnet_v2_test.py From tf-pose with Apache License 2.0 | 5 votes |
def testAtrousFullyConvolutionalValues(self): """Verify dense feature extraction with atrous convolution.""" nominal_stride = 32 for output_stride in [4, 8, 16, 32, None]: with slim.arg_scope(resnet_utils.resnet_arg_scope()): with tf.Graph().as_default(): with self.test_session() as sess: tf.set_random_seed(0) inputs = create_test_input(2, 81, 81, 3) # Dense feature extraction followed by subsampling. output, _ = self._resnet_small(inputs, None, is_training=False, global_pool=False, output_stride=output_stride) if output_stride is None: factor = 1 else: factor = nominal_stride // output_stride output = resnet_utils.subsample(output, factor) # Make the two networks use the same weights. tf.get_variable_scope().reuse_variables() # Feature extraction at the nominal network rate. expected, _ = self._resnet_small(inputs, None, is_training=False, global_pool=False) sess.run(tf.global_variables_initializer()) self.assertAllClose(output.eval(), expected.eval(), atol=1e-4, rtol=1e-4)
Example #18
Source File: resnet_v2_test.py From tf-pose with Apache License 2.0 | 5 votes |
def testConv2DSameOdd(self): n, n2 = 5, 3 # Input image. x = create_test_input(1, n, n, 1) # Convolution kernel. w = create_test_input(1, 3, 3, 1) w = tf.reshape(w, [3, 3, 1, 1]) tf.get_variable('Conv/weights', initializer=w) tf.get_variable('Conv/biases', initializer=tf.zeros([1])) tf.get_variable_scope().reuse_variables() y1 = slim.conv2d(x, 1, [3, 3], stride=1, scope='Conv') y1_expected = tf.to_float([[14, 28, 43, 58, 34], [28, 48, 66, 84, 46], [43, 66, 84, 102, 55], [58, 84, 102, 120, 64], [34, 46, 55, 64, 30]]) y1_expected = tf.reshape(y1_expected, [1, n, n, 1]) y2 = resnet_utils.subsample(y1, 2) y2_expected = tf.to_float([[14, 43, 34], [43, 84, 55], [34, 55, 30]]) y2_expected = tf.reshape(y2_expected, [1, n2, n2, 1]) y3 = resnet_utils.conv2d_same(x, 1, 3, stride=2, scope='Conv') y3_expected = y2_expected y4 = slim.conv2d(x, 1, [3, 3], stride=2, scope='Conv') y4_expected = y2_expected with self.test_session() as sess: sess.run(tf.global_variables_initializer()) self.assertAllClose(y1.eval(), y1_expected.eval()) self.assertAllClose(y2.eval(), y2_expected.eval()) self.assertAllClose(y3.eval(), y3_expected.eval()) self.assertAllClose(y4.eval(), y4_expected.eval())
Example #19
Source File: resnet_v2_test.py From tf-pose with Apache License 2.0 | 5 votes |
def testConv2DSameEven(self): n, n2 = 4, 2 # Input image. x = create_test_input(1, n, n, 1) # Convolution kernel. w = create_test_input(1, 3, 3, 1) w = tf.reshape(w, [3, 3, 1, 1]) tf.get_variable('Conv/weights', initializer=w) tf.get_variable('Conv/biases', initializer=tf.zeros([1])) tf.get_variable_scope().reuse_variables() y1 = slim.conv2d(x, 1, [3, 3], stride=1, scope='Conv') y1_expected = tf.to_float([[14, 28, 43, 26], [28, 48, 66, 37], [43, 66, 84, 46], [26, 37, 46, 22]]) y1_expected = tf.reshape(y1_expected, [1, n, n, 1]) y2 = resnet_utils.subsample(y1, 2) y2_expected = tf.to_float([[14, 43], [43, 84]]) y2_expected = tf.reshape(y2_expected, [1, n2, n2, 1]) y3 = resnet_utils.conv2d_same(x, 1, 3, stride=2, scope='Conv') y3_expected = y2_expected y4 = slim.conv2d(x, 1, [3, 3], stride=2, scope='Conv') y4_expected = tf.to_float([[48, 37], [37, 22]]) y4_expected = tf.reshape(y4_expected, [1, n2, n2, 1]) with self.test_session() as sess: sess.run(tf.global_variables_initializer()) self.assertAllClose(y1.eval(), y1_expected.eval()) self.assertAllClose(y2.eval(), y2_expected.eval()) self.assertAllClose(y3.eval(), y3_expected.eval()) self.assertAllClose(y4.eval(), y4_expected.eval())
Example #20
Source File: resnet_v2_test.py From tf-pose with Apache License 2.0 | 5 votes |
def testSubsampleFourByFour(self): x = tf.reshape(tf.to_float(tf.range(16)), [1, 4, 4, 1]) x = resnet_utils.subsample(x, 2) expected = tf.reshape(tf.constant([0, 2, 8, 10]), [1, 2, 2, 1]) with self.test_session(): self.assertAllClose(x.eval(), expected.eval())
Example #21
Source File: resnet_v2_test.py From tf-pose with Apache License 2.0 | 5 votes |
def testSubsampleThreeByThree(self): x = tf.reshape(tf.to_float(tf.range(9)), [1, 3, 3, 1]) x = resnet_utils.subsample(x, 2) expected = tf.reshape(tf.constant([0, 2, 6, 8]), [1, 2, 2, 1]) with self.test_session(): self.assertAllClose(x.eval(), expected.eval())
Example #22
Source File: resnet_v1_test.py From R2CNN_Faster-RCNN_Tensorflow with MIT License | 5 votes |
def testAtrousFullyConvolutionalValues(self): """Verify dense feature extraction with atrous convolution.""" nominal_stride = 32 for output_stride in [4, 8, 16, 32, None]: with slim.arg_scope(resnet_utils.resnet_arg_scope()): with tf.Graph().as_default(): with self.test_session() as sess: tf.set_random_seed(0) inputs = create_test_input(2, 81, 81, 3) # Dense feature extraction followed by subsampling. output, _ = self._resnet_small(inputs, None, is_training=False, global_pool=False, output_stride=output_stride) if output_stride is None: factor = 1 else: factor = nominal_stride // output_stride output = resnet_utils.subsample(output, factor) # Make the two networks use the same weights. tf.get_variable_scope().reuse_variables() # Feature extraction at the nominal network rate. expected, _ = self._resnet_small(inputs, None, is_training=False, global_pool=False) sess.run(tf.global_variables_initializer()) self.assertAllClose(output.eval(), expected.eval(), atol=1e-4, rtol=1e-4)
Example #23
Source File: resnet_v1_test.py From R2CNN_Faster-RCNN_Tensorflow with MIT License | 5 votes |
def testConv2DSameOdd(self): n, n2 = 5, 3 # Input image. x = create_test_input(1, n, n, 1) # Convolution kernel. w = create_test_input(1, 3, 3, 1) w = tf.reshape(w, [3, 3, 1, 1]) tf.get_variable('Conv/weights', initializer=w) tf.get_variable('Conv/biases', initializer=tf.zeros([1])) tf.get_variable_scope().reuse_variables() y1 = slim.conv2d(x, 1, [3, 3], stride=1, scope='Conv') y1_expected = tf.to_float([[14, 28, 43, 58, 34], [28, 48, 66, 84, 46], [43, 66, 84, 102, 55], [58, 84, 102, 120, 64], [34, 46, 55, 64, 30]]) y1_expected = tf.reshape(y1_expected, [1, n, n, 1]) y2 = resnet_utils.subsample(y1, 2) y2_expected = tf.to_float([[14, 43, 34], [43, 84, 55], [34, 55, 30]]) y2_expected = tf.reshape(y2_expected, [1, n2, n2, 1]) y3 = resnet_utils.conv2d_same(x, 1, 3, stride=2, scope='Conv') y3_expected = y2_expected y4 = slim.conv2d(x, 1, [3, 3], stride=2, scope='Conv') y4_expected = y2_expected with self.test_session() as sess: sess.run(tf.global_variables_initializer()) self.assertAllClose(y1.eval(), y1_expected.eval()) self.assertAllClose(y2.eval(), y2_expected.eval()) self.assertAllClose(y3.eval(), y3_expected.eval()) self.assertAllClose(y4.eval(), y4_expected.eval())
Example #24
Source File: resnet_v1_test.py From R2CNN_Faster-RCNN_Tensorflow with MIT License | 5 votes |
def testConv2DSameEven(self): n, n2 = 4, 2 # Input image. x = create_test_input(1, n, n, 1) # Convolution kernel. w = create_test_input(1, 3, 3, 1) w = tf.reshape(w, [3, 3, 1, 1]) tf.get_variable('Conv/weights', initializer=w) tf.get_variable('Conv/biases', initializer=tf.zeros([1])) tf.get_variable_scope().reuse_variables() y1 = slim.conv2d(x, 1, [3, 3], stride=1, scope='Conv') y1_expected = tf.to_float([[14, 28, 43, 26], [28, 48, 66, 37], [43, 66, 84, 46], [26, 37, 46, 22]]) y1_expected = tf.reshape(y1_expected, [1, n, n, 1]) y2 = resnet_utils.subsample(y1, 2) y2_expected = tf.to_float([[14, 43], [43, 84]]) y2_expected = tf.reshape(y2_expected, [1, n2, n2, 1]) y3 = resnet_utils.conv2d_same(x, 1, 3, stride=2, scope='Conv') y3_expected = y2_expected y4 = slim.conv2d(x, 1, [3, 3], stride=2, scope='Conv') y4_expected = tf.to_float([[48, 37], [37, 22]]) y4_expected = tf.reshape(y4_expected, [1, n2, n2, 1]) with self.test_session() as sess: sess.run(tf.global_variables_initializer()) self.assertAllClose(y1.eval(), y1_expected.eval()) self.assertAllClose(y2.eval(), y2_expected.eval()) self.assertAllClose(y3.eval(), y3_expected.eval()) self.assertAllClose(y4.eval(), y4_expected.eval())
Example #25
Source File: resnet_v1_test.py From R2CNN_Faster-RCNN_Tensorflow with MIT License | 5 votes |
def testSubsampleFourByFour(self): x = tf.reshape(tf.to_float(tf.range(16)), [1, 4, 4, 1]) x = resnet_utils.subsample(x, 2) expected = tf.reshape(tf.constant([0, 2, 8, 10]), [1, 2, 2, 1]) with self.test_session(): self.assertAllClose(x.eval(), expected.eval())
Example #26
Source File: resnet_v1_test.py From R2CNN_Faster-RCNN_Tensorflow with MIT License | 5 votes |
def testSubsampleThreeByThree(self): x = tf.reshape(tf.to_float(tf.range(9)), [1, 3, 3, 1]) x = resnet_utils.subsample(x, 2) expected = tf.reshape(tf.constant([0, 2, 6, 8]), [1, 2, 2, 1]) with self.test_session(): self.assertAllClose(x.eval(), expected.eval())
Example #27
Source File: resnet_v2_test.py From R2CNN_Faster-RCNN_Tensorflow with MIT License | 5 votes |
def testAtrousFullyConvolutionalValues(self): """Verify dense feature extraction with atrous convolution.""" nominal_stride = 32 for output_stride in [4, 8, 16, 32, None]: with slim.arg_scope(resnet_utils.resnet_arg_scope()): with tf.Graph().as_default(): with self.test_session() as sess: tf.set_random_seed(0) inputs = create_test_input(2, 81, 81, 3) # Dense feature extraction followed by subsampling. output, _ = self._resnet_small(inputs, None, is_training=False, global_pool=False, output_stride=output_stride) if output_stride is None: factor = 1 else: factor = nominal_stride // output_stride output = resnet_utils.subsample(output, factor) # Make the two networks use the same weights. tf.get_variable_scope().reuse_variables() # Feature extraction at the nominal network rate. expected, _ = self._resnet_small(inputs, None, is_training=False, global_pool=False) sess.run(tf.global_variables_initializer()) self.assertAllClose(output.eval(), expected.eval(), atol=1e-4, rtol=1e-4)
Example #28
Source File: resnet_v2_test.py From R2CNN_Faster-RCNN_Tensorflow with MIT License | 5 votes |
def testConv2DSameOdd(self): n, n2 = 5, 3 # Input image. x = create_test_input(1, n, n, 1) # Convolution kernel. w = create_test_input(1, 3, 3, 1) w = tf.reshape(w, [3, 3, 1, 1]) tf.get_variable('Conv/weights', initializer=w) tf.get_variable('Conv/biases', initializer=tf.zeros([1])) tf.get_variable_scope().reuse_variables() y1 = slim.conv2d(x, 1, [3, 3], stride=1, scope='Conv') y1_expected = tf.to_float([[14, 28, 43, 58, 34], [28, 48, 66, 84, 46], [43, 66, 84, 102, 55], [58, 84, 102, 120, 64], [34, 46, 55, 64, 30]]) y1_expected = tf.reshape(y1_expected, [1, n, n, 1]) y2 = resnet_utils.subsample(y1, 2) y2_expected = tf.to_float([[14, 43, 34], [43, 84, 55], [34, 55, 30]]) y2_expected = tf.reshape(y2_expected, [1, n2, n2, 1]) y3 = resnet_utils.conv2d_same(x, 1, 3, stride=2, scope='Conv') y3_expected = y2_expected y4 = slim.conv2d(x, 1, [3, 3], stride=2, scope='Conv') y4_expected = y2_expected with self.test_session() as sess: sess.run(tf.global_variables_initializer()) self.assertAllClose(y1.eval(), y1_expected.eval()) self.assertAllClose(y2.eval(), y2_expected.eval()) self.assertAllClose(y3.eval(), y3_expected.eval()) self.assertAllClose(y4.eval(), y4_expected.eval())
Example #29
Source File: resnet_v2_test.py From R2CNN_Faster-RCNN_Tensorflow with MIT License | 5 votes |
def testConv2DSameEven(self): n, n2 = 4, 2 # Input image. x = create_test_input(1, n, n, 1) # Convolution kernel. w = create_test_input(1, 3, 3, 1) w = tf.reshape(w, [3, 3, 1, 1]) tf.get_variable('Conv/weights', initializer=w) tf.get_variable('Conv/biases', initializer=tf.zeros([1])) tf.get_variable_scope().reuse_variables() y1 = slim.conv2d(x, 1, [3, 3], stride=1, scope='Conv') y1_expected = tf.to_float([[14, 28, 43, 26], [28, 48, 66, 37], [43, 66, 84, 46], [26, 37, 46, 22]]) y1_expected = tf.reshape(y1_expected, [1, n, n, 1]) y2 = resnet_utils.subsample(y1, 2) y2_expected = tf.to_float([[14, 43], [43, 84]]) y2_expected = tf.reshape(y2_expected, [1, n2, n2, 1]) y3 = resnet_utils.conv2d_same(x, 1, 3, stride=2, scope='Conv') y3_expected = y2_expected y4 = slim.conv2d(x, 1, [3, 3], stride=2, scope='Conv') y4_expected = tf.to_float([[48, 37], [37, 22]]) y4_expected = tf.reshape(y4_expected, [1, n2, n2, 1]) with self.test_session() as sess: sess.run(tf.global_variables_initializer()) self.assertAllClose(y1.eval(), y1_expected.eval()) self.assertAllClose(y2.eval(), y2_expected.eval()) self.assertAllClose(y3.eval(), y3_expected.eval()) self.assertAllClose(y4.eval(), y4_expected.eval())
Example #30
Source File: resnet_v2_test.py From R2CNN_Faster-RCNN_Tensorflow with MIT License | 5 votes |
def testSubsampleThreeByThree(self): x = tf.reshape(tf.to_float(tf.range(9)), [1, 3, 3, 1]) x = resnet_utils.subsample(x, 2) expected = tf.reshape(tf.constant([0, 2, 6, 8]), [1, 2, 2, 1]) with self.test_session(): self.assertAllClose(x.eval(), expected.eval())