Skip to content

GitLab

Commit 763bee61 authored by Fan Yang's avatar Fan Yang Committed by A. Unique TensorFlower
Browse files

Internal change 

PiperOrigin-RevId: 410609558
parent 10048a7c
Hide whitespace changes
Inline Side-by-side
Showing with 249 additions and 277 deletions
official/vision/beta/dataloaders/tf_example_decoder_test.py
View file @ 763bee61
...@@ -14,24 +14,13 @@ ...@@ -14,24 +14,13 @@
"""Tests for tf_example_decoder.py.""" """Tests for tf_example_decoder.py."""
import io
# Import libraries # Import libraries
from absl.testing import parameterized from absl.testing import parameterized
import numpy as np import numpy as np
from PIL import Image
import tensorflow as tf import tensorflow as tf
from official.vision.beta.dataloaders import tf_example_decoder from official.vision.beta.dataloaders import tf_example_decoder
from official.vision.beta.dataloaders import tfexample_utils
DUMP_SOURCE_ID = b'123'
def _encode_image(image_array, fmt):
image = Image.fromarray(image_array)
with io.BytesIO() as output:
image.save(output, format=fmt)
return output.getvalue()
class TfExampleDecoderTest(tf.test.TestCase, parameterized.TestCase): class TfExampleDecoderTest(tf.test.TestCase, parameterized.TestCase):
...@@ -52,73 +41,11 @@ class TfExampleDecoderTest(tf.test.TestCase, parameterized.TestCase): ...@@ -52,73 +41,11 @@ class TfExampleDecoderTest(tf.test.TestCase, parameterized.TestCase):
decoder = tf_example_decoder.TfExampleDecoder( decoder = tf_example_decoder.TfExampleDecoder(
include_mask=True, regenerate_source_id=regenerate_source_id) include_mask=True, regenerate_source_id=regenerate_source_id)
image = _encode_image( serialized_example = tfexample_utils.create_detection_test_example(
np.uint8(np.random.rand(image_height, image_width, 3) * 255), image_height=image_height,
fmt='JPEG') image_width=image_width,
if num_instances == 0: image_channel=3,
xmins = [] num_instances=num_instances).SerializeToString()
xmaxs = []
ymins = []
ymaxs = []
labels = []
areas = []
is_crowds = []
masks = []
else:
xmins = list(np.random.rand(num_instances))
xmaxs = list(np.random.rand(num_instances))
ymins = list(np.random.rand(num_instances))
ymaxs = list(np.random.rand(num_instances))
labels = list(np.random.randint(100, size=num_instances))
areas = [(xmax - xmin) * (ymax - ymin) * image_height * image_width
for xmin, xmax, ymin, ymax in zip(xmins, xmaxs, ymins, ymaxs)]
is_crowds = [0] * num_instances
masks = []
for _ in range(num_instances):
mask = _encode_image(
np.uint8(np.random.rand(image_height, image_width) * 255),
fmt='PNG')
masks.append(mask)
serialized_example = tf.train.Example(
features=tf.train.Features(
feature={
'image/encoded': (
tf.train.Feature(
bytes_list=tf.train.BytesList(value=[image]))),
'image/source_id': (
tf.train.Feature(
bytes_list=tf.train.BytesList(value=[DUMP_SOURCE_ID]))),
'image/height': (
tf.train.Feature(
int64_list=tf.train.Int64List(value=[image_height]))),
'image/width': (
tf.train.Feature(
int64_list=tf.train.Int64List(value=[image_width]))),
'image/object/bbox/xmin': (
tf.train.Feature(
float_list=tf.train.FloatList(value=xmins))),
'image/object/bbox/xmax': (
tf.train.Feature(
float_list=tf.train.FloatList(value=xmaxs))),
'image/object/bbox/ymin': (
tf.train.Feature(
float_list=tf.train.FloatList(value=ymins))),
'image/object/bbox/ymax': (
tf.train.Feature(
float_list=tf.train.FloatList(value=ymaxs))),
'image/object/class/label': (
tf.train.Feature(
int64_list=tf.train.Int64List(value=labels))),
'image/object/is_crowd': (
tf.train.Feature(
int64_list=tf.train.Int64List(value=is_crowds))),
'image/object/area': (
tf.train.Feature(
float_list=tf.train.FloatList(value=areas))),
'image/object/mask': (
tf.train.Feature(
bytes_list=tf.train.BytesList(value=masks))),
})).SerializeToString()
decoded_tensors = decoder.decode( decoded_tensors = decoder.decode(
tf.convert_to_tensor(value=serialized_example)) tf.convert_to_tensor(value=serialized_example))
...@@ -127,7 +54,7 @@ class TfExampleDecoderTest(tf.test.TestCase, parameterized.TestCase): ...@@ -127,7 +54,7 @@ class TfExampleDecoderTest(tf.test.TestCase, parameterized.TestCase):
self.assertAllEqual( self.assertAllEqual(
(image_height, image_width, 3), results['image'].shape) (image_height, image_width, 3), results['image'].shape)
if not regenerate_source_id: if not regenerate_source_id:
self.assertEqual(DUMP_SOURCE_ID, results['source_id']) self.assertEqual(tfexample_utils.DUMP_SOURCE_ID, results['source_id'])
self.assertEqual(image_height, results['height']) self.assertEqual(image_height, results['height'])
self.assertEqual(image_width, results['width']) self.assertEqual(image_width, results['width'])
self.assertAllEqual( self.assertAllEqual(
...@@ -151,7 +78,7 @@ class TfExampleDecoderTest(tf.test.TestCase, parameterized.TestCase): ...@@ -151,7 +78,7 @@ class TfExampleDecoderTest(tf.test.TestCase, parameterized.TestCase):
[[0, 0, 0], [255, 255, 255], [255, 255, 255], [0, 0, 0]], [[0, 0, 0], [255, 255, 255], [255, 255, 255], [0, 0, 0]],
[[0, 0, 0], [255, 255, 255], [255, 255, 255], [0, 0, 0]], [[0, 0, 0], [255, 255, 255], [255, 255, 255], [0, 0, 0]],
[[0, 0, 0], [0, 0, 0], [0, 0, 0], [0, 0, 0]]] [[0, 0, 0], [0, 0, 0], [0, 0, 0], [0, 0, 0]]]
image = _encode_image(np.uint8(image_content), fmt='PNG') image = tfexample_utils.encode_image(np.uint8(image_content), fmt='PNG')
image_height = 4 image_height = 4
image_width = 4 image_width = 4
num_instances = 2 num_instances = 2
...@@ -172,46 +99,38 @@ class TfExampleDecoderTest(tf.test.TestCase, parameterized.TestCase): ...@@ -172,46 +99,38 @@ class TfExampleDecoderTest(tf.test.TestCase, parameterized.TestCase):
[0, 255, 255, 255], [0, 255, 255, 255],
[0, 255, 255, 255], [0, 255, 255, 255],
[0, 255, 255, 255]]] [0, 255, 255, 255]]]
masks = [_encode_image(np.uint8(m), fmt='PNG') for m in list(mask_content)] masks = [
tfexample_utils.encode_image(np.uint8(m), fmt='PNG')
for m in list(mask_content)
]
serialized_example = tf.train.Example( serialized_example = tf.train.Example(
features=tf.train.Features( features=tf.train.Features(
feature={ feature={
'image/encoded': ( 'image/encoded': (tf.train.Feature(
tf.train.Feature( bytes_list=tf.train.BytesList(value=[image]))),
bytes_list=tf.train.BytesList(value=[image]))), 'image/source_id': (tf.train.Feature(
'image/source_id': ( bytes_list=tf.train.BytesList(
tf.train.Feature( value=[tfexample_utils.DUMP_SOURCE_ID]))),
bytes_list=tf.train.BytesList(value=[DUMP_SOURCE_ID]))), 'image/height': (tf.train.Feature(
'image/height': ( int64_list=tf.train.Int64List(value=[image_height]))),
tf.train.Feature( 'image/width': (tf.train.Feature(
int64_list=tf.train.Int64List(value=[image_height]))), int64_list=tf.train.Int64List(value=[image_width]))),
'image/width': ( 'image/object/bbox/xmin': (tf.train.Feature(
tf.train.Feature( float_list=tf.train.FloatList(value=xmins))),
int64_list=tf.train.Int64List(value=[image_width]))), 'image/object/bbox/xmax': (tf.train.Feature(
'image/object/bbox/xmin': ( float_list=tf.train.FloatList(value=xmaxs))),
tf.train.Feature( 'image/object/bbox/ymin': (tf.train.Feature(
float_list=tf.train.FloatList(value=xmins))), float_list=tf.train.FloatList(value=ymins))),
'image/object/bbox/xmax': ( 'image/object/bbox/ymax': (tf.train.Feature(
tf.train.Feature( float_list=tf.train.FloatList(value=ymaxs))),
float_list=tf.train.FloatList(value=xmaxs))), 'image/object/class/label': (tf.train.Feature(
'image/object/bbox/ymin': ( int64_list=tf.train.Int64List(value=labels))),
tf.train.Feature( 'image/object/is_crowd': (tf.train.Feature(
float_list=tf.train.FloatList(value=ymins))), int64_list=tf.train.Int64List(value=is_crowds))),
'image/object/bbox/ymax': ( 'image/object/area': (tf.train.Feature(
tf.train.Feature( float_list=tf.train.FloatList(value=areas))),
float_list=tf.train.FloatList(value=ymaxs))), 'image/object/mask': (tf.train.Feature(
'image/object/class/label': ( bytes_list=tf.train.BytesList(value=masks))),
tf.train.Feature(
int64_list=tf.train.Int64List(value=labels))),
'image/object/is_crowd': (
tf.train.Feature(
int64_list=tf.train.Int64List(value=is_crowds))),
'image/object/area': (
tf.train.Feature(
float_list=tf.train.FloatList(value=areas))),
'image/object/mask': (
tf.train.Feature(
bytes_list=tf.train.BytesList(value=masks))),
})).SerializeToString() })).SerializeToString()
decoded_tensors = decoder.decode( decoded_tensors = decoder.decode(
tf.convert_to_tensor(value=serialized_example)) tf.convert_to_tensor(value=serialized_example))
...@@ -221,7 +140,7 @@ class TfExampleDecoderTest(tf.test.TestCase, parameterized.TestCase): ...@@ -221,7 +140,7 @@ class TfExampleDecoderTest(tf.test.TestCase, parameterized.TestCase):
self.assertAllEqual( self.assertAllEqual(
(image_height, image_width, 3), results['image'].shape) (image_height, image_width, 3), results['image'].shape)
self.assertAllEqual(image_content, results['image']) self.assertAllEqual(image_content, results['image'])
self.assertEqual(DUMP_SOURCE_ID, results['source_id']) self.assertEqual(tfexample_utils.DUMP_SOURCE_ID, results['source_id'])
self.assertEqual(image_height, results['height']) self.assertEqual(image_height, results['height'])
self.assertEqual(image_width, results['width']) self.assertEqual(image_width, results['width'])
self.assertAllEqual( self.assertAllEqual(
...@@ -259,7 +178,7 @@ class TfExampleDecoderTest(tf.test.TestCase, parameterized.TestCase): ...@@ -259,7 +178,7 @@ class TfExampleDecoderTest(tf.test.TestCase, parameterized.TestCase):
[[0, 0, 0], [255, 255, 255], [255, 255, 255], [0, 0, 0]], [[0, 0, 0], [255, 255, 255], [255, 255, 255], [0, 0, 0]],
[[0, 0, 0], [255, 255, 255], [255, 255, 255], [0, 0, 0]], [[0, 0, 0], [255, 255, 255], [255, 255, 255], [0, 0, 0]],
[[0, 0, 0], [0, 0, 0], [0, 0, 0], [0, 0, 0]]] [[0, 0, 0], [0, 0, 0], [0, 0, 0], [0, 0, 0]]]
image = _encode_image(np.uint8(image_content), fmt='PNG') image = tfexample_utils.encode_image(np.uint8(image_content), fmt='PNG')
image_height = 4 image_height = 4
image_width = 4 image_width = 4
num_instances = 2 num_instances = 2
...@@ -276,40 +195,34 @@ class TfExampleDecoderTest(tf.test.TestCase, parameterized.TestCase): ...@@ -276,40 +195,34 @@ class TfExampleDecoderTest(tf.test.TestCase, parameterized.TestCase):
[0, 255, 255, 255], [0, 255, 255, 255],
[0, 255, 255, 255], [0, 255, 255, 255],
[0, 255, 255, 255]]] [0, 255, 255, 255]]]
masks = [_encode_image(np.uint8(m), fmt='PNG') for m in list(mask_content)] masks = [
tfexample_utils.encode_image(np.uint8(m), fmt='PNG')
for m in list(mask_content)
]
serialized_example = tf.train.Example( serialized_example = tf.train.Example(
features=tf.train.Features( features=tf.train.Features(
feature={ feature={
'image/encoded': ( 'image/encoded': (tf.train.Feature(
tf.train.Feature( bytes_list=tf.train.BytesList(value=[image]))),
bytes_list=tf.train.BytesList(value=[image]))), 'image/source_id': (tf.train.Feature(
'image/source_id': ( bytes_list=tf.train.BytesList(
tf.train.Feature( value=[tfexample_utils.DUMP_SOURCE_ID]))),
bytes_list=tf.train.BytesList(value=[DUMP_SOURCE_ID]))), 'image/height': (tf.train.Feature(
'image/height': ( int64_list=tf.train.Int64List(value=[image_height]))),
tf.train.Feature( 'image/width': (tf.train.Feature(
int64_list=tf.train.Int64List(value=[image_height]))), int64_list=tf.train.Int64List(value=[image_width]))),
'image/width': ( 'image/object/bbox/xmin': (tf.train.Feature(
tf.train.Feature( float_list=tf.train.FloatList(value=xmins))),
int64_list=tf.train.Int64List(value=[image_width]))), 'image/object/bbox/xmax': (tf.train.Feature(
'image/object/bbox/xmin': ( float_list=tf.train.FloatList(value=xmaxs))),
tf.train.Feature( 'image/object/bbox/ymin': (tf.train.Feature(
float_list=tf.train.FloatList(value=xmins))), float_list=tf.train.FloatList(value=ymins))),
'image/object/bbox/xmax': ( 'image/object/bbox/ymax': (tf.train.Feature(
tf.train.Feature( float_list=tf.train.FloatList(value=ymaxs))),
float_list=tf.train.FloatList(value=xmaxs))), 'image/object/class/label': (tf.train.Feature(
'image/object/bbox/ymin': ( int64_list=tf.train.Int64List(value=labels))),
tf.train.Feature( 'image/object/mask': (tf.train.Feature(
float_list=tf.train.FloatList(value=ymins))), bytes_list=tf.train.BytesList(value=masks))),
'image/object/bbox/ymax': (
tf.train.Feature(
float_list=tf.train.FloatList(value=ymaxs))),
'image/object/class/label': (
tf.train.Feature(
int64_list=tf.train.Int64List(value=labels))),
'image/object/mask': (
tf.train.Feature(
bytes_list=tf.train.BytesList(value=masks))),
})).SerializeToString() })).SerializeToString()
decoded_tensors = decoder.decode( decoded_tensors = decoder.decode(
tf.convert_to_tensor(serialized_example)) tf.convert_to_tensor(serialized_example))
...@@ -318,7 +231,7 @@ class TfExampleDecoderTest(tf.test.TestCase, parameterized.TestCase): ...@@ -318,7 +231,7 @@ class TfExampleDecoderTest(tf.test.TestCase, parameterized.TestCase):
self.assertAllEqual( self.assertAllEqual(
(image_height, image_width, 3), results['image'].shape) (image_height, image_width, 3), results['image'].shape)
self.assertAllEqual(image_content, results['image']) self.assertAllEqual(image_content, results['image'])
self.assertEqual(DUMP_SOURCE_ID, results['source_id']) self.assertEqual(tfexample_utils.DUMP_SOURCE_ID, results['source_id'])
self.assertEqual(image_height, results['height']) self.assertEqual(image_height, results['height'])
self.assertEqual(image_width, results['width']) self.assertEqual(image_width, results['width'])
self.assertAllEqual( self.assertAllEqual(
......
official/vision/beta/dataloaders/tf_example_label_map_decoder_test.py
View file @ 763bee61
...@@ -14,28 +14,19 @@ ...@@ -14,28 +14,19 @@
"""Tests for tf_example_label_map_decoder.py.""" """Tests for tf_example_label_map_decoder.py."""
import io
import os import os
# Import libraries # Import libraries
from absl.testing import parameterized from absl.testing import parameterized
import numpy as np import numpy as np
from PIL import Image
import tensorflow as tf import tensorflow as tf
from official.vision.beta.dataloaders import tf_example_label_map_decoder from official.vision.beta.dataloaders import tf_example_label_map_decoder
from official.vision.beta.dataloaders import tfexample_utils
DUMP_SOURCE_ID = b'123'
LABEL_MAP_CSV_CONTENT = '0,class_0\n1,class_1\n2,class_2' LABEL_MAP_CSV_CONTENT = '0,class_0\n1,class_1\n2,class_2'
def _encode_image(image_array, fmt):
image = Image.fromarray(image_array)
with io.BytesIO() as output:
image.save(output, format=fmt)
return output.getvalue()
class TfExampleDecoderLabelMapTest(tf.test.TestCase, parameterized.TestCase): class TfExampleDecoderLabelMapTest(tf.test.TestCase, parameterized.TestCase):
@parameterized.parameters( @parameterized.parameters(
...@@ -56,74 +47,11 @@ class TfExampleDecoderLabelMapTest(tf.test.TestCase, parameterized.TestCase): ...@@ -56,74 +47,11 @@ class TfExampleDecoderLabelMapTest(tf.test.TestCase, parameterized.TestCase):
decoder = tf_example_label_map_decoder.TfExampleDecoderLabelMap( decoder = tf_example_label_map_decoder.TfExampleDecoderLabelMap(
label_map_path, include_mask=True) label_map_path, include_mask=True)
image = _encode_image( serialized_example = tfexample_utils.create_detection_test_example(
np.uint8(np.random.rand(image_height, image_width, 3) * 255), image_height=image_height,
fmt='JPEG') image_width=image_width,
if num_instances == 0: image_channel=3,
xmins = [] num_instances=num_instances).SerializeToString()
xmaxs = []
ymins = []
ymaxs = []
labels = []
areas = []
is_crowds = []
masks = []
else:
xmins = list(np.random.rand(num_instances))
xmaxs = list(np.random.rand(num_instances))
ymins = list(np.random.rand(num_instances))
ymaxs = list(np.random.rand(num_instances))
labels = list(np.random.randint(100, size=num_instances))
areas = [(xmax - xmin) * (ymax - ymin) * image_height * image_width
for xmin, xmax, ymin, ymax in zip(xmins, xmaxs, ymins, ymaxs)]
is_crowds = [0] * num_instances
masks = []
labels = [b'class_1'] * num_instances
for _ in range(num_instances):
mask = _encode_image(
np.uint8(np.random.rand(image_height, image_width) * 255),
fmt='PNG')
masks.append(mask)
serialized_example = tf.train.Example(
features=tf.train.Features(
feature={
'image/encoded': (
tf.train.Feature(
bytes_list=tf.train.BytesList(value=[image]))),
'image/source_id': (
tf.train.Feature(
bytes_list=tf.train.BytesList(value=[DUMP_SOURCE_ID]))),
'image/height': (
tf.train.Feature(
int64_list=tf.train.Int64List(value=[image_height]))),
'image/width': (
tf.train.Feature(
int64_list=tf.train.Int64List(value=[image_width]))),
'image/object/bbox/xmin': (
tf.train.Feature(
float_list=tf.train.FloatList(value=xmins))),
'image/object/bbox/xmax': (
tf.train.Feature(
float_list=tf.train.FloatList(value=xmaxs))),
'image/object/bbox/ymin': (
tf.train.Feature(
float_list=tf.train.FloatList(value=ymins))),
'image/object/bbox/ymax': (
tf.train.Feature(
float_list=tf.train.FloatList(value=ymaxs))),
'image/object/class/text': (
tf.train.Feature(
bytes_list=tf.train.BytesList(value=labels))),
'image/object/is_crowd': (
tf.train.Feature(
int64_list=tf.train.Int64List(value=is_crowds))),
'image/object/area': (
tf.train.Feature(
float_list=tf.train.FloatList(value=areas))),
'image/object/mask': (
tf.train.Feature(
bytes_list=tf.train.BytesList(value=masks))),
})).SerializeToString()
decoded_tensors = decoder.decode( decoded_tensors = decoder.decode(
tf.convert_to_tensor(value=serialized_example)) tf.convert_to_tensor(value=serialized_example))
...@@ -131,7 +59,7 @@ class TfExampleDecoderLabelMapTest(tf.test.TestCase, parameterized.TestCase): ...@@ -131,7 +59,7 @@ class TfExampleDecoderLabelMapTest(tf.test.TestCase, parameterized.TestCase):
self.assertAllEqual( self.assertAllEqual(
(image_height, image_width, 3), results['image'].shape) (image_height, image_width, 3), results['image'].shape)
self.assertEqual(DUMP_SOURCE_ID, results['source_id']) self.assertEqual(tfexample_utils.DUMP_SOURCE_ID, results['source_id'])
self.assertEqual(image_height, results['height']) self.assertEqual(image_height, results['height'])
self.assertEqual(image_width, results['width']) self.assertEqual(image_width, results['width'])
self.assertAllEqual( self.assertAllEqual(
...@@ -162,7 +90,7 @@ class TfExampleDecoderLabelMapTest(tf.test.TestCase, parameterized.TestCase): ...@@ -162,7 +90,7 @@ class TfExampleDecoderLabelMapTest(tf.test.TestCase, parameterized.TestCase):
[[0, 0, 0], [255, 255, 255], [255, 255, 255], [0, 0, 0]], [[0, 0, 0], [255, 255, 255], [255, 255, 255], [0, 0, 0]],
[[0, 0, 0], [255, 255, 255], [255, 255, 255], [0, 0, 0]], [[0, 0, 0], [255, 255, 255], [255, 255, 255], [0, 0, 0]],
[[0, 0, 0], [0, 0, 0], [0, 0, 0], [0, 0, 0]]] [[0, 0, 0], [0, 0, 0], [0, 0, 0], [0, 0, 0]]]
image = _encode_image(np.uint8(image_content), fmt='PNG') image = tfexample_utils.encode_image(np.uint8(image_content), fmt='PNG')
image_height = 4 image_height = 4
image_width = 4 image_width = 4
num_instances = 2 num_instances = 2
...@@ -183,46 +111,38 @@ class TfExampleDecoderLabelMapTest(tf.test.TestCase, parameterized.TestCase): ...@@ -183,46 +111,38 @@ class TfExampleDecoderLabelMapTest(tf.test.TestCase, parameterized.TestCase):
[0, 255, 255, 255], [0, 255, 255, 255],
[0, 255, 255, 255], [0, 255, 255, 255],
[0, 255, 255, 255]]] [0, 255, 255, 255]]]
masks = [_encode_image(np.uint8(m), fmt='PNG') for m in list(mask_content)] masks = [
tfexample_utils.encode_image(np.uint8(m), fmt='PNG')
for m in list(mask_content)
]
serialized_example = tf.train.Example( serialized_example = tf.train.Example(
features=tf.train.Features( features=tf.train.Features(
feature={ feature={
'image/encoded': ( 'image/encoded': (tf.train.Feature(
tf.train.Feature( bytes_list=tf.train.BytesList(value=[image]))),
bytes_list=tf.train.BytesList(value=[image]))), 'image/source_id': (tf.train.Feature(
'image/source_id': ( bytes_list=tf.train.BytesList(
tf.train.Feature( value=[tfexample_utils.DUMP_SOURCE_ID]))),
bytes_list=tf.train.BytesList(value=[DUMP_SOURCE_ID]))), 'image/height': (tf.train.Feature(
'image/height': ( int64_list=tf.train.Int64List(value=[image_height]))),
tf.train.Feature( 'image/width': (tf.train.Feature(
int64_list=tf.train.Int64List(value=[image_height]))), int64_list=tf.train.Int64List(value=[image_width]))),
'image/width': ( 'image/object/bbox/xmin': (tf.train.Feature(
tf.train.Feature( float_list=tf.train.FloatList(value=xmins))),
int64_list=tf.train.Int64List(value=[image_width]))), 'image/object/bbox/xmax': (tf.train.Feature(
'image/object/bbox/xmin': ( float_list=tf.train.FloatList(value=xmaxs))),
tf.train.Feature( 'image/object/bbox/ymin': (tf.train.Feature(
float_list=tf.train.FloatList(value=xmins))), float_list=tf.train.FloatList(value=ymins))),
'image/object/bbox/xmax': ( 'image/object/bbox/ymax': (tf.train.Feature(
tf.train.Feature( float_list=tf.train.FloatList(value=ymaxs))),
float_list=tf.train.FloatList(value=xmaxs))), 'image/object/class/text': (tf.train.Feature(
'image/object/bbox/ymin': ( bytes_list=tf.train.BytesList(value=labels))),
tf.train.Feature( 'image/object/is_crowd': (tf.train.Feature(
float_list=tf.train.FloatList(value=ymins))), int64_list=tf.train.Int64List(value=is_crowds))),
'image/object/bbox/ymax': ( 'image/object/area': (tf.train.Feature(
tf.train.Feature( float_list=tf.train.FloatList(value=areas))),
float_list=tf.train.FloatList(value=ymaxs))), 'image/object/mask': (tf.train.Feature(
'image/object/class/text': ( bytes_list=tf.train.BytesList(value=masks))),
tf.train.Feature(
bytes_list=tf.train.BytesList(value=labels))),
'image/object/is_crowd': (
tf.train.Feature(
int64_list=tf.train.Int64List(value=is_crowds))),
'image/object/area': (
tf.train.Feature(
float_list=tf.train.FloatList(value=areas))),
'image/object/mask': (
tf.train.Feature(
bytes_list=tf.train.BytesList(value=masks))),
})).SerializeToString() })).SerializeToString()
decoded_tensors = decoder.decode( decoded_tensors = decoder.decode(
tf.convert_to_tensor(value=serialized_example)) tf.convert_to_tensor(value=serialized_example))
...@@ -232,7 +152,7 @@ class TfExampleDecoderLabelMapTest(tf.test.TestCase, parameterized.TestCase): ...@@ -232,7 +152,7 @@ class TfExampleDecoderLabelMapTest(tf.test.TestCase, parameterized.TestCase):
self.assertAllEqual( self.assertAllEqual(
(image_height, image_width, 3), results['image'].shape) (image_height, image_width, 3), results['image'].shape)
self.assertAllEqual(image_content, results['image']) self.assertAllEqual(image_content, results['image'])
self.assertEqual(DUMP_SOURCE_ID, results['source_id']) self.assertEqual(tfexample_utils.DUMP_SOURCE_ID, results['source_id'])
self.assertEqual(image_height, results['height']) self.assertEqual(image_height, results['height'])
self.assertEqual(image_width, results['width']) self.assertEqual(image_width, results['width'])
self.assertAllEqual( self.assertAllEqual(
......
official/vision/beta/dataloaders/tfds_factory_test.py
View file @ 763bee61
...@@ -23,6 +23,22 @@ from official.vision.beta.dataloaders import tfds_factory ...@@ -23,6 +23,22 @@ from official.vision.beta.dataloaders import tfds_factory
class TFDSFactoryTest(tf.test.TestCase, parameterized.TestCase): class TFDSFactoryTest(tf.test.TestCase, parameterized.TestCase):
def _create_test_example(self):
serialized_example = {
'image': tf.ones(shape=(100, 100, 3), dtype=tf.uint8),
'label': 1,
'image/id': 0,
'objects': {
'label': 1,
'is_crowd': 0,
'area': 0.5,
'bbox': [0.1, 0.2, 0.3, 0.4]
},
'segmentation_label': tf.ones((100, 100, 1), dtype=tf.uint8),
'image_left': tf.ones(shape=(100, 100, 3), dtype=tf.uint8)
}
return serialized_example
@parameterized.parameters( @parameterized.parameters(
('imagenet2012'), ('imagenet2012'),
('cifar10'), ('cifar10'),
...@@ -31,6 +47,10 @@ class TFDSFactoryTest(tf.test.TestCase, parameterized.TestCase): ...@@ -31,6 +47,10 @@ class TFDSFactoryTest(tf.test.TestCase, parameterized.TestCase):
def test_classification_decoder(self, tfds_name): def test_classification_decoder(self, tfds_name):
decoder = tfds_factory.get_classification_decoder(tfds_name) decoder = tfds_factory.get_classification_decoder(tfds_name)
self.assertIsInstance(decoder, base_decoder.Decoder) self.assertIsInstance(decoder, base_decoder.Decoder)
decoded_tensor = decoder.decode(self._create_test_example())
self.assertLen(decoded_tensor, 2)
self.assertIn('image/encoded', decoded_tensor)
self.assertIn('image/class/label', decoded_tensor)
@parameterized.parameters( @parameterized.parameters(
('flowers'), ('flowers'),
...@@ -48,6 +68,16 @@ class TFDSFactoryTest(tf.test.TestCase, parameterized.TestCase): ...@@ -48,6 +68,16 @@ class TFDSFactoryTest(tf.test.TestCase, parameterized.TestCase):
def test_detection_decoder(self, tfds_name): def test_detection_decoder(self, tfds_name):
decoder = tfds_factory.get_detection_decoder(tfds_name) decoder = tfds_factory.get_detection_decoder(tfds_name)
self.assertIsInstance(decoder, base_decoder.Decoder) self.assertIsInstance(decoder, base_decoder.Decoder)
decoded_tensor = decoder.decode(self._create_test_example())
self.assertLen(decoded_tensor, 8)
self.assertIn('image', decoded_tensor)
self.assertIn('source_id', decoded_tensor)
self.assertIn('height', decoded_tensor)
self.assertIn('width', decoded_tensor)
self.assertIn('groundtruth_classes', decoded_tensor)
self.assertIn('groundtruth_is_crowd', decoded_tensor)
self.assertIn('groundtruth_area', decoded_tensor)
self.assertIn('groundtruth_boxes', decoded_tensor)
@parameterized.parameters( @parameterized.parameters(
('pascal'), ('pascal'),
...@@ -65,6 +95,12 @@ class TFDSFactoryTest(tf.test.TestCase, parameterized.TestCase): ...@@ -65,6 +95,12 @@ class TFDSFactoryTest(tf.test.TestCase, parameterized.TestCase):
def test_segmentation_decoder(self, tfds_name): def test_segmentation_decoder(self, tfds_name):
decoder = tfds_factory.get_segmentation_decoder(tfds_name) decoder = tfds_factory.get_segmentation_decoder(tfds_name)
self.assertIsInstance(decoder, base_decoder.Decoder) self.assertIsInstance(decoder, base_decoder.Decoder)
decoded_tensor = decoder.decode(self._create_test_example())
self.assertLen(decoded_tensor, 4)
self.assertIn('image/encoded', decoded_tensor)
self.assertIn('image/segmentation/class/encoded', decoded_tensor)
self.assertIn('image/height', decoded_tensor)
self.assertIn('image/width', decoded_tensor)
@parameterized.parameters( @parameterized.parameters(
('coco'), ('coco'),
......
official/vision/beta/dataloaders/tfexample_utils.py
View file @ 763bee61
...@@ -54,16 +54,20 @@ IMAGE_KEY = 'image/encoded' ...@@ -54,16 +54,20 @@ IMAGE_KEY = 'image/encoded'
CLASSIFICATION_LABEL_KEY = 'image/class/label' CLASSIFICATION_LABEL_KEY = 'image/class/label'
LABEL_KEY = 'clip/label/index' LABEL_KEY = 'clip/label/index'
AUDIO_KEY = 'features/audio' AUDIO_KEY = 'features/audio'
DUMP_SOURCE_ID = b'123'
def make_image_bytes(shape: Sequence[int]): def encode_image(image_array: np.array, fmt: str) -> bytes:
"""Generates image and return bytes in JPEG format.""" image = Image.fromarray(image_array)
with io.BytesIO() as output:
image.save(output, format=fmt)
return output.getvalue()
def make_image_bytes(shape: Sequence[int], fmt: str = 'JPEG') -> bytes:
"""Generates image and return bytes in specified format."""
random_image = np.random.randint(0, 256, size=shape, dtype=np.uint8) random_image = np.random.randint(0, 256, size=shape, dtype=np.uint8)
random_image = Image.fromarray(random_image) return encode_image(random_image, fmt=fmt)
with io.BytesIO() as buffer:
random_image.save(buffer, format='JPEG')
raw_image_bytes = buffer.getvalue()
return raw_image_bytes
def put_int64_to_context(seq_example: tf.train.SequenceExample, def put_int64_to_context(seq_example: tf.train.SequenceExample,
...@@ -164,3 +168,102 @@ def create_3d_image_test_example(image_height: int, image_width: int, ...@@ -164,3 +168,102 @@ def create_3d_image_test_example(image_height: int, image_width: int,
bytes_list=tf.train.BytesList(value=[labels.tobytes()]))) bytes_list=tf.train.BytesList(value=[labels.tobytes()])))
} }
return tf.train.Example(features=tf.train.Features(feature=feature)) return tf.train.Example(features=tf.train.Features(feature=feature))
def create_detection_test_example(image_height: int, image_width: int,
image_channel: int,
num_instances: int) -> tf.train.Example:
"""Creates and returns a test example containing box and mask annotations.
Args:
image_height: The height of test image.
image_width: The width of test image.
image_channel: The channel of test image.
num_instances: The number of object instances per image.
Returns:
A tf.train.Example for testing.
"""
image = make_image_bytes([image_height, image_width, image_channel])
if num_instances == 0:
xmins = []
xmaxs = []
ymins = []
ymaxs = []
labels = []
areas = []
is_crowds = []
masks = []
labels_text = []
else:
xmins = list(np.random.rand(num_instances))
xmaxs = list(np.random.rand(num_instances))
ymins = list(np.random.rand(num_instances))
ymaxs = list(np.random.rand(num_instances))
labels_text = [b'class_1'] * num_instances
labels = list(np.random.randint(100, size=num_instances))
areas = [(xmax - xmin) * (ymax - ymin) * image_height * image_width
for xmin, xmax, ymin, ymax in zip(xmins, xmaxs, ymins, ymaxs)]
is_crowds = [0] * num_instances
masks = []
for _ in range(num_instances):
mask = make_image_bytes([image_height, image_width], fmt='PNG')
masks.append(mask)
return tf.train.Example(
features=tf.train.Features(
feature={
'image/encoded': (tf.train.Feature(
bytes_list=tf.train.BytesList(value=[image]))),
'image/source_id': (tf.train.Feature(
bytes_list=tf.train.BytesList(value=[DUMP_SOURCE_ID]))),
'image/height': (tf.train.Feature(
int64_list=tf.train.Int64List(value=[image_height]))),
'image/width': (tf.train.Feature(
int64_list=tf.train.Int64List(value=[image_width]))),
'image/object/bbox/xmin': (tf.train.Feature(
float_list=tf.train.FloatList(value=xmins))),
'image/object/bbox/xmax': (tf.train.Feature(
float_list=tf.train.FloatList(value=xmaxs))),
'image/object/bbox/ymin': (tf.train.Feature(
float_list=tf.train.FloatList(value=ymins))),
'image/object/bbox/ymax': (tf.train.Feature(
float_list=tf.train.FloatList(value=ymaxs))),
'image/object/class/label': (tf.train.Feature(
int64_list=tf.train.Int64List(value=labels))),
'image/object/class/text': (tf.train.Feature(
bytes_list=tf.train.BytesList(value=labels_text))),
'image/object/is_crowd': (tf.train.Feature(
int64_list=tf.train.Int64List(value=is_crowds))),
'image/object/area': (tf.train.Feature(
float_list=tf.train.FloatList(value=areas))),
'image/object/mask': (tf.train.Feature(
bytes_list=tf.train.BytesList(value=masks))),
}))
def create_segmentation_test_example(image_height: int, image_width: int,
image_channel: int) -> tf.train.Example:
"""Creates and returns a test example containing mask annotations.
Args:
image_height: The height of test image.
image_width: The width of test image.
image_channel: The channel of test image.
Returns:
A tf.train.Example for testing.
"""
image = make_image_bytes([image_height, image_width, image_channel])
mask = make_image_bytes([image_height, image_width], fmt='PNG')
return tf.train.Example(
features=tf.train.Features(
feature={
'image/encoded': (tf.train.Feature(
bytes_list=tf.train.BytesList(value=[image]))),
'image/segmentation/class/encoded': (tf.train.Feature(
bytes_list=tf.train.BytesList(value=[mask]))),
'image/height': (tf.train.Feature(
int64_list=tf.train.Int64List(value=[image_height]))),
'image/width': (tf.train.Feature(
int64_list=tf.train.Int64List(value=[image_width])))
}))
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment