Python object_detection.utils.ops.nearest_neighbor_upsampling() Examples
The following are 30
code examples of object_detection.utils.ops.nearest_neighbor_upsampling().
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
object_detection.utils.ops
, or try the search function
.
.
Example #1
| Source File: exporter_test.py From multilabel-image-classification-tensorflow with MIT License | 6 votes |
|
def test_rewrite_nn_resize_op(self):
g = tf.Graph()
with g.as_default():
x = array_ops.placeholder(dtypes.float32, shape=(8, 10, 10, 8))
y = array_ops.placeholder(dtypes.float32, shape=(8, 20, 20, 8))
s = ops.nearest_neighbor_upsampling(x, 2)
t = s + y
exporter.rewrite_nn_resize_op()
resize_op_found = False
for op in g.get_operations():
if op.type == 'ResizeNearestNeighbor':
resize_op_found = True
self.assertEqual(op.inputs[0], x)
self.assertEqual(op.outputs[0].consumers()[0], t.op)
break
self.assertTrue(resize_op_found)
Example #2
| Source File: exporter_test.py From vehicle_counting_tensorflow with MIT License | 6 votes |
|
def test_rewrite_nn_resize_op(self):
g = tf.Graph()
with g.as_default():
x = array_ops.placeholder(dtypes.float32, shape=(8, 10, 10, 8))
y = array_ops.placeholder(dtypes.float32, shape=(8, 20, 20, 8))
s = ops.nearest_neighbor_upsampling(x, 2)
t = s + y
exporter.rewrite_nn_resize_op()
resize_op_found = False
for op in g.get_operations():
if op.type == 'ResizeNearestNeighbor':
resize_op_found = True
self.assertEqual(op.inputs[0], x)
self.assertEqual(op.outputs[0].consumers()[0], t.op)
break
self.assertTrue(resize_op_found)
Example #3
| Source File: exporter_tf1_test.py From models with Apache License 2.0 | 6 votes |
|
def test_rewrite_nn_resize_op_quantized_odd_size(self):
g = tf.Graph()
with g.as_default():
x = array_ops.placeholder(dtypes.float32, shape=(8, 10, 10, 8))
x_conv = slim.conv2d(x, 8, 1)
s = ops.nearest_neighbor_upsampling(x_conv, 2)
t = s[:, :19, :19, :]
graph_rewriter_config = graph_rewriter_pb2.GraphRewriter()
graph_rewriter_config.quantization.delay = 500000
graph_rewriter_fn = graph_rewriter_builder.build(
graph_rewriter_config, is_training=False)
graph_rewriter_fn()
exporter.rewrite_nn_resize_op(is_quantized=True)
resize_op_found = False
for op in g.get_operations():
if op.type == 'ResizeNearestNeighbor':
resize_op_found = True
self.assertEqual(op.inputs[0].op.type, 'FakeQuantWithMinMaxVars')
self.assertEqual(op.outputs[0].consumers()[0], t.op)
break
self.assertTrue(resize_op_found)
Example #4
| Source File: exporter_tf1_test.py From models with Apache License 2.0 | 6 votes |
|
def test_rewrite_nn_resize_op_odd_size(self):
g = tf.Graph()
with g.as_default():
x = array_ops.placeholder(dtypes.float32, shape=(8, 10, 10, 8))
s = ops.nearest_neighbor_upsampling(x, 2)
t = s[:, :19, :19, :]
exporter.rewrite_nn_resize_op()
resize_op_found = False
for op in g.get_operations():
if op.type == 'ResizeNearestNeighbor':
resize_op_found = True
self.assertEqual(op.inputs[0], x)
self.assertEqual(op.outputs[0].consumers()[0], t.op)
break
self.assertTrue(resize_op_found)
Example #5
| Source File: exporter_tf1_test.py From models with Apache License 2.0 | 6 votes |
|
def test_rewrite_nn_resize_op(self):
g = tf.Graph()
with g.as_default():
x = array_ops.placeholder(dtypes.float32, shape=(8, 10, 10, 8))
y = array_ops.placeholder(dtypes.float32, shape=(8, 20, 20, 8))
s = ops.nearest_neighbor_upsampling(x, 2)
t = s + y
exporter.rewrite_nn_resize_op()
resize_op_found = False
for op in g.get_operations():
if op.type == 'ResizeNearestNeighbor':
resize_op_found = True
self.assertEqual(op.inputs[0], x)
self.assertEqual(op.outputs[0].consumers()[0], t.op)
break
self.assertTrue(resize_op_found)
Example #6
| Source File: exporter_test.py From MAX-Object-Detector with Apache License 2.0 | 6 votes |
|
def test_rewrite_nn_resize_op(self):
g = tf.Graph()
with g.as_default():
x = array_ops.placeholder(dtypes.float32, shape=(8, 10, 10, 8))
y = array_ops.placeholder(dtypes.float32, shape=(8, 20, 20, 8))
s = ops.nearest_neighbor_upsampling(x, 2)
t = s + y
exporter.rewrite_nn_resize_op()
resize_op_found = False
for op in g.get_operations():
if op.type == 'ResizeNearestNeighbor':
resize_op_found = True
self.assertEqual(op.inputs[0], x)
self.assertEqual(op.outputs[0].consumers()[0], t.op)
break
self.assertTrue(resize_op_found)
Example #7
| Source File: exporter_test.py From g-tensorflow-models with Apache License 2.0 | 6 votes |
|
def test_rewrite_nn_resize_op(self):
g = tf.Graph()
with g.as_default():
x = array_ops.placeholder(dtypes.float32, shape=(8, 10, 10, 8))
y = array_ops.placeholder(dtypes.float32, shape=(8, 20, 20, 8))
s = ops.nearest_neighbor_upsampling(x, 2)
t = s + y
exporter.rewrite_nn_resize_op()
resize_op_found = False
for op in g.get_operations():
if op.type == 'ResizeNearestNeighbor':
resize_op_found = True
self.assertEqual(op.inputs[0], x)
self.assertEqual(op.outputs[0].consumers()[0], t.op)
break
self.assertTrue(resize_op_found)
Example #8
| Source File: bifpn_utils.py From models with Apache License 2.0 | 5 votes |
|
def create_upsample_feature_map_ops(scale, use_native_resize_op, name):
"""Creates Keras layers for upsampling feature maps.
Args:
scale: Int. The scale factor by which to upsample input feature maps. For
example, in the case of a typical feature map pyramid, the scale factor
between level_i and level_i-1 is 2.
use_native_resize_op: If True, uses tf.image.resize_nearest_neighbor op for
the upsampling process instead of reshape and broadcasting implementation.
name: String. The name used to prefix the constructed layers.
Returns:
A list of Keras layers which will upsample input feature maps by the
desired scale factor.
"""
layers = []
if use_native_resize_op:
def resize_nearest_neighbor(image):
image_shape = shape_utils.combined_static_and_dynamic_shape(image)
return tf.image.resize_nearest_neighbor(
image, [image_shape[1] * scale, image_shape[2] * scale])
layers.append(
tf.keras.layers.Lambda(
resize_nearest_neighbor,
name=name + 'nearest_neighbor_upsampling_x{}'.format(scale)))
else:
def nearest_neighbor_upsampling(image):
return ops.nearest_neighbor_upsampling(image, scale=scale)
layers.append(
tf.keras.layers.Lambda(
nearest_neighbor_upsampling,
name=name + 'nearest_neighbor_upsampling_x{}'.format(scale)))
return layers
Example #9
| Source File: ops_test.py From AniSeg with Apache License 2.0 | 5 votes |
|
def test_upsampling(self):
def graph_fn(inputs):
custom_op_output = ops.nearest_neighbor_upsampling(inputs, scale=2)
return custom_op_output
inputs = np.reshape(np.arange(4).astype(np.float32), [1, 2, 2, 1])
custom_op_output = self.execute(graph_fn, [inputs])
expected_output = [[[[0], [0], [1], [1]],
[[0], [0], [1], [1]],
[[2], [2], [3], [3]],
[[2], [2], [3], [3]]]]
self.assertAllClose(custom_op_output, expected_output)
Example #10
| Source File: ops_test.py From MAX-Object-Detector with Apache License 2.0 | 5 votes |
|
def test_upsampling_with_single_scale(self):
def graph_fn(inputs):
custom_op_output = ops.nearest_neighbor_upsampling(inputs, scale=2)
return custom_op_output
inputs = np.reshape(np.arange(4).astype(np.float32), [1, 2, 2, 1])
custom_op_output = self.execute(graph_fn, [inputs])
expected_output = [[[[0], [0], [1], [1]],
[[0], [0], [1], [1]],
[[2], [2], [3], [3]],
[[2], [2], [3], [3]]]]
self.assertAllClose(custom_op_output, expected_output)
Example #11
| Source File: ops_test.py From vehicle_counting_tensorflow with MIT License | 5 votes |
|
def test_upsampling_with_single_scale(self):
def graph_fn(inputs):
custom_op_output = ops.nearest_neighbor_upsampling(inputs, scale=2)
return custom_op_output
inputs = np.reshape(np.arange(4).astype(np.float32), [1, 2, 2, 1])
custom_op_output = self.execute(graph_fn, [inputs])
expected_output = [[[[0], [0], [1], [1]],
[[0], [0], [1], [1]],
[[2], [2], [3], [3]],
[[2], [2], [3], [3]]]]
self.assertAllClose(custom_op_output, expected_output)
Example #12
| Source File: exporter_test.py From MAX-Object-Detector with Apache License 2.0 | 5 votes |
|
def test_rewrite_nn_resize_op_quantized(self):
g = tf.Graph()
with g.as_default():
x = array_ops.placeholder(dtypes.float32, shape=(8, 10, 10, 8))
x_conv = tf.contrib.slim.conv2d(x, 8, 1)
y = array_ops.placeholder(dtypes.float32, shape=(8, 20, 20, 8))
s = ops.nearest_neighbor_upsampling(x_conv, 2)
t = s + y
graph_rewriter_config = graph_rewriter_pb2.GraphRewriter()
graph_rewriter_config.quantization.delay = 500000
graph_rewriter_fn = graph_rewriter_builder.build(
graph_rewriter_config, is_training=False)
graph_rewriter_fn()
exporter.rewrite_nn_resize_op(is_quantized=True)
resize_op_found = False
for op in g.get_operations():
if op.type == 'ResizeNearestNeighbor':
resize_op_found = True
self.assertEqual(op.inputs[0].op.type, 'FakeQuantWithMinMaxVars')
self.assertEqual(op.outputs[0].consumers()[0], t.op)
break
self.assertTrue(resize_op_found)
Example #13
| Source File: ops_test.py From open-solution-googleai-object-detection with MIT License | 5 votes |
|
def test_upsampling(self):
def graph_fn(inputs):
custom_op_output = ops.nearest_neighbor_upsampling(inputs, scale=2)
return custom_op_output
inputs = np.reshape(np.arange(4).astype(np.float32), [1, 2, 2, 1])
custom_op_output = self.execute(graph_fn, [inputs])
expected_output = [[[[0], [0], [1], [1]],
[[0], [0], [1], [1]],
[[2], [2], [3], [3]],
[[2], [2], [3], [3]]]]
self.assertAllClose(custom_op_output, expected_output)
Example #14
| Source File: ops_test.py From g-tensorflow-models with Apache License 2.0 | 5 votes |
|
def test_upsampling_with_single_scale(self):
def graph_fn(inputs):
custom_op_output = ops.nearest_neighbor_upsampling(inputs, scale=2)
return custom_op_output
inputs = np.reshape(np.arange(4).astype(np.float32), [1, 2, 2, 1])
custom_op_output = self.execute(graph_fn, [inputs])
expected_output = [[[[0], [0], [1], [1]],
[[0], [0], [1], [1]],
[[2], [2], [3], [3]],
[[2], [2], [3], [3]]]]
self.assertAllClose(custom_op_output, expected_output)
Example #15
| Source File: ops_test.py From g-tensorflow-models with Apache License 2.0 | 5 votes |
|
def test_upsampling_with_separate_height_width_scales(self):
def graph_fn(inputs):
custom_op_output = ops.nearest_neighbor_upsampling(inputs,
height_scale=2,
width_scale=3)
return custom_op_output
inputs = np.reshape(np.arange(4).astype(np.float32), [1, 2, 2, 1])
custom_op_output = self.execute(graph_fn, [inputs])
expected_output = [[[[0], [0], [0], [1], [1], [1]],
[[0], [0], [0], [1], [1], [1]],
[[2], [2], [2], [3], [3], [3]],
[[2], [2], [2], [3], [3], [3]]]]
self.assertAllClose(custom_op_output, expected_output)
Example #16
| Source File: exporter_test.py From g-tensorflow-models with Apache License 2.0 | 5 votes |
|
def test_rewrite_nn_resize_op_quantized(self):
g = tf.Graph()
with g.as_default():
x = array_ops.placeholder(dtypes.float32, shape=(8, 10, 10, 8))
x_conv = tf.contrib.slim.conv2d(x, 8, 1)
y = array_ops.placeholder(dtypes.float32, shape=(8, 20, 20, 8))
s = ops.nearest_neighbor_upsampling(x_conv, 2)
t = s + y
graph_rewriter_config = graph_rewriter_pb2.GraphRewriter()
graph_rewriter_config.quantization.delay = 500000
graph_rewriter_fn = graph_rewriter_builder.build(
graph_rewriter_config, is_training=False)
graph_rewriter_fn()
exporter.rewrite_nn_resize_op(is_quantized=True)
resize_op_found = False
for op in g.get_operations():
if op.type == 'ResizeNearestNeighbor':
resize_op_found = True
self.assertEqual(op.inputs[0].op.type, 'FakeQuantWithMinMaxVars')
self.assertEqual(op.outputs[0].consumers()[0], t.op)
break
self.assertTrue(resize_op_found)
Example #17
| Source File: ops_test.py From MAX-Object-Detector with Apache License 2.0 | 5 votes |
|
def test_upsampling_with_separate_height_width_scales(self):
def graph_fn(inputs):
custom_op_output = ops.nearest_neighbor_upsampling(inputs,
height_scale=2,
width_scale=3)
return custom_op_output
inputs = np.reshape(np.arange(4).astype(np.float32), [1, 2, 2, 1])
custom_op_output = self.execute(graph_fn, [inputs])
expected_output = [[[[0], [0], [0], [1], [1], [1]],
[[0], [0], [0], [1], [1], [1]],
[[2], [2], [2], [3], [3], [3]],
[[2], [2], [2], [3], [3], [3]]]]
self.assertAllClose(custom_op_output, expected_output)
Example #18
| Source File: ops_test.py From models with Apache License 2.0 | 5 votes |
|
def test_upsampling_with_single_scale(self):
def graph_fn(inputs):
custom_op_output = ops.nearest_neighbor_upsampling(inputs, scale=2)
return custom_op_output
inputs = np.reshape(np.arange(4).astype(np.float32), [1, 2, 2, 1])
custom_op_output = self.execute(graph_fn, [inputs])
expected_output = [[[[0], [0], [1], [1]],
[[0], [0], [1], [1]],
[[2], [2], [3], [3]],
[[2], [2], [3], [3]]]]
self.assertAllClose(custom_op_output, expected_output)
Example #19
| Source File: ops_test.py From models with Apache License 2.0 | 5 votes |
|
def test_upsampling_with_separate_height_width_scales(self):
def graph_fn(inputs):
custom_op_output = ops.nearest_neighbor_upsampling(inputs,
height_scale=2,
width_scale=3)
return custom_op_output
inputs = np.reshape(np.arange(4).astype(np.float32), [1, 2, 2, 1])
custom_op_output = self.execute(graph_fn, [inputs])
expected_output = [[[[0], [0], [0], [1], [1], [1]],
[[0], [0], [0], [1], [1], [1]],
[[2], [2], [2], [3], [3], [3]],
[[2], [2], [2], [3], [3], [3]]]]
self.assertAllClose(custom_op_output, expected_output)
Example #20
| Source File: ops_test.py From multilabel-image-classification-tensorflow with MIT License | 5 votes |
|
def test_upsampling_with_single_scale(self):
def graph_fn(inputs):
custom_op_output = ops.nearest_neighbor_upsampling(inputs, scale=2)
return custom_op_output
inputs = np.reshape(np.arange(4).astype(np.float32), [1, 2, 2, 1])
custom_op_output = self.execute(graph_fn, [inputs])
expected_output = [[[[0], [0], [1], [1]],
[[0], [0], [1], [1]],
[[2], [2], [3], [3]],
[[2], [2], [3], [3]]]]
self.assertAllClose(custom_op_output, expected_output)
Example #21
| Source File: ops_test.py From multilabel-image-classification-tensorflow with MIT License | 5 votes |
|
def test_upsampling_with_separate_height_width_scales(self):
def graph_fn(inputs):
custom_op_output = ops.nearest_neighbor_upsampling(inputs,
height_scale=2,
width_scale=3)
return custom_op_output
inputs = np.reshape(np.arange(4).astype(np.float32), [1, 2, 2, 1])
custom_op_output = self.execute(graph_fn, [inputs])
expected_output = [[[[0], [0], [0], [1], [1], [1]],
[[0], [0], [0], [1], [1], [1]],
[[2], [2], [2], [3], [3], [3]],
[[2], [2], [2], [3], [3], [3]]]]
self.assertAllClose(custom_op_output, expected_output)
Example #22
| Source File: exporter_test.py From multilabel-image-classification-tensorflow with MIT License | 5 votes |
|
def test_rewrite_nn_resize_op_quantized(self):
g = tf.Graph()
with g.as_default():
x = array_ops.placeholder(dtypes.float32, shape=(8, 10, 10, 8))
x_conv = tf.contrib.slim.conv2d(x, 8, 1)
y = array_ops.placeholder(dtypes.float32, shape=(8, 20, 20, 8))
s = ops.nearest_neighbor_upsampling(x_conv, 2)
t = s + y
graph_rewriter_config = graph_rewriter_pb2.GraphRewriter()
graph_rewriter_config.quantization.delay = 500000
graph_rewriter_fn = graph_rewriter_builder.build(
graph_rewriter_config, is_training=False)
graph_rewriter_fn()
exporter.rewrite_nn_resize_op(is_quantized=True)
resize_op_found = False
for op in g.get_operations():
if op.type == 'ResizeNearestNeighbor':
resize_op_found = True
self.assertEqual(op.inputs[0].op.type, 'FakeQuantWithMinMaxVars')
self.assertEqual(op.outputs[0].consumers()[0], t.op)
break
self.assertTrue(resize_op_found)
Example #23
| Source File: ops_test.py From ros_people_object_detection_tensorflow with Apache License 2.0 | 5 votes |
|
def test_upsampling(self):
def graph_fn(inputs):
custom_op_output = ops.nearest_neighbor_upsampling(inputs, scale=2)
return custom_op_output
inputs = np.reshape(np.arange(4).astype(np.float32), [1, 2, 2, 1])
custom_op_output = self.execute(graph_fn, [inputs])
expected_output = [[[[0], [0], [1], [1]],
[[0], [0], [1], [1]],
[[2], [2], [3], [3]],
[[2], [2], [3], [3]]]]
self.assertAllClose(custom_op_output, expected_output)
Example #24
| Source File: ops_test.py From Person-Detection-and-Tracking with MIT License | 5 votes |
|
def test_upsampling(self):
def graph_fn(inputs):
custom_op_output = ops.nearest_neighbor_upsampling(inputs, scale=2)
return custom_op_output
inputs = np.reshape(np.arange(4).astype(np.float32), [1, 2, 2, 1])
custom_op_output = self.execute(graph_fn, [inputs])
expected_output = [[[[0], [0], [1], [1]],
[[0], [0], [1], [1]],
[[2], [2], [3], [3]],
[[2], [2], [3], [3]]]]
self.assertAllClose(custom_op_output, expected_output)
Example #25
| Source File: ops_test.py From Traffic-Rule-Violation-Detection-System with MIT License | 5 votes |
|
def test_upsampling(self):
def graph_fn(inputs):
custom_op_output = ops.nearest_neighbor_upsampling(inputs, scale=2)
tf_op_output = tf.image.resize_images(
inputs, [4, 4], method=tf.image.ResizeMethod.NEAREST_NEIGHBOR)
return (custom_op_output, tf_op_output)
inputs = np.reshape(np.arange(2**4), [2, 2, 2, 2])
(custom_op_output, tf_op_output) = self.execute(graph_fn, [inputs])
self.assertAllClose(custom_op_output, tf_op_output)
Example #26
| Source File: ops_test.py From monopsr with MIT License | 5 votes |
|
def test_upsampling(self):
def graph_fn(inputs):
custom_op_output = ops.nearest_neighbor_upsampling(inputs, scale=2)
return custom_op_output
inputs = np.reshape(np.arange(4).astype(np.float32), [1, 2, 2, 1])
custom_op_output = self.execute(graph_fn, [inputs])
expected_output = [[[[0], [0], [1], [1]],
[[0], [0], [1], [1]],
[[2], [2], [3], [3]],
[[2], [2], [3], [3]]]]
self.assertAllClose(custom_op_output, expected_output)
Example #27
| Source File: ops_test.py From Gun-Detector with Apache License 2.0 | 5 votes |
|
def test_upsampling(self):
def graph_fn(inputs):
custom_op_output = ops.nearest_neighbor_upsampling(inputs, scale=2)
return custom_op_output
inputs = np.reshape(np.arange(4).astype(np.float32), [1, 2, 2, 1])
custom_op_output = self.execute(graph_fn, [inputs])
expected_output = [[[[0], [0], [1], [1]],
[[0], [0], [1], [1]],
[[2], [2], [3], [3]],
[[2], [2], [3], [3]]]]
self.assertAllClose(custom_op_output, expected_output)
Example #28
| Source File: ops_test.py From ros_tensorflow with Apache License 2.0 | 5 votes |
|
def test_upsampling(self):
def graph_fn(inputs):
custom_op_output = ops.nearest_neighbor_upsampling(inputs, scale=2)
return custom_op_output
inputs = np.reshape(np.arange(4).astype(np.float32), [1, 2, 2, 1])
custom_op_output = self.execute(graph_fn, [inputs])
expected_output = [[[[0], [0], [1], [1]],
[[0], [0], [1], [1]],
[[2], [2], [3], [3]],
[[2], [2], [3], [3]]]]
self.assertAllClose(custom_op_output, expected_output)
Example #29
| Source File: exporter_test.py From vehicle_counting_tensorflow with MIT License | 5 votes |
|
def test_rewrite_nn_resize_op_quantized(self):
g = tf.Graph()
with g.as_default():
x = array_ops.placeholder(dtypes.float32, shape=(8, 10, 10, 8))
x_conv = tf.contrib.slim.conv2d(x, 8, 1)
y = array_ops.placeholder(dtypes.float32, shape=(8, 20, 20, 8))
s = ops.nearest_neighbor_upsampling(x_conv, 2)
t = s + y
graph_rewriter_config = graph_rewriter_pb2.GraphRewriter()
graph_rewriter_config.quantization.delay = 500000
graph_rewriter_fn = graph_rewriter_builder.build(
graph_rewriter_config, is_training=False)
graph_rewriter_fn()
exporter.rewrite_nn_resize_op(is_quantized=True)
resize_op_found = False
for op in g.get_operations():
if op.type == 'ResizeNearestNeighbor':
resize_op_found = True
self.assertEqual(op.inputs[0].op.type, 'FakeQuantWithMinMaxVars')
self.assertEqual(op.outputs[0].consumers()[0], t.op)
break
self.assertTrue(resize_op_found)
Example #30
| Source File: ops_test.py From BMW-TensorFlow-Training-GUI with Apache License 2.0 | 5 votes |
|
def test_upsampling(self):
def graph_fn(inputs):
custom_op_output = ops.nearest_neighbor_upsampling(inputs, scale=2)
return custom_op_output
inputs = np.reshape(np.arange(4).astype(np.float32), [1, 2, 2, 1])
custom_op_output = self.execute(graph_fn, [inputs])
expected_output = [[[[0], [0], [1], [1]],
[[0], [0], [1], [1]],
[[2], [2], [3], [3]],
[[2], [2], [3], [3]]]]
self.assertAllClose(custom_op_output, expected_output)
