Skip to content

Commit

Permalink
Testing bounding boxes in WithMixedPrecisionTest (keras-team#1860)
Browse files Browse the repository at this point in the history 
* added bounding boxes and fixed test configs

* added a batch axis

* Fix a few of the layers

* fixed one more test. 12 to go

* added flags for tests... 10F at the moment

* fixed 3 more tests... 7F at the moment

* fix for cutMix

* all tests fixed

* styling fixes

* linting

* linting again

* add string dtypes for keras core

* add condition for no_bbox_tests

* trying to make CI happy

* fix styling issues

* remove duplicate tests

* remove check inside nogpu

* fix cutmix

---------

Co-authored-by: ianjjohnson <[email protected]>
  • Loading branch information
@jaygala223 @ianstenbit
jaygala223 and ianstenbit authored Jul 31, 2023
1 parent 6005ff8 commit c8a80d4
Show file tree
Hide file tree
Showing 3 changed files with 123 additions and 27 deletions.
4 changes: 3 additions & 1 deletion keras_cv/layers/preprocessing/base_image_augmentation_layer.py
View file
Original file line number Diff line number Diff line change
Expand Up @@ -484,7 +484,9 @@ def _augment(self, inputs):
image=raw_image,
)

bounding_boxes = bounding_box.to_ragged(bounding_boxes)
bounding_boxes = bounding_box.to_ragged(
bounding_boxes, dtype=self.compute_dtype
)
result[BOUNDING_BOXES] = bounding_boxes

if keypoints is not None:
Expand Down
39 changes: 25 additions & 14 deletions keras_cv/layers/preprocessing/random_crop.py
View file
Original file line number Diff line number Diff line change
Expand Up @@ -78,11 +78,17 @@ def compute_ragged_image_signature(self, images):
return ragged_spec

def get_random_transformation_batch(self, batch_size, **kwargs):
tops = self._random_generator.random_uniform(
shape=(batch_size, 1), minval=0, maxval=1, dtype=tf.float32
tops = tf.cast(
self._random_generator.random_uniform(
shape=(batch_size, 1), minval=0, maxval=1
),
self.compute_dtype,
)
lefts = self._random_generator.random_uniform(
shape=(batch_size, 1), minval=0, maxval=1, dtype=tf.float32
lefts = tf.cast(
self._random_generator.random_uniform(
shape=(batch_size, 1), minval=0, maxval=1
),
self.compute_dtype,
)
return {"tops": tops, "lefts": lefts}

Expand Down Expand Up @@ -212,13 +218,14 @@ def _get_image_shape(self, images):
def _crop_images(self, images, transformations):
batch_size = tf.shape(images)[0]
heights, widths = self._get_image_shape(images)
heights = tf.cast(heights, dtype=tf.float32)
widths = tf.cast(widths, dtype=tf.float32)
heights = tf.cast(heights, dtype=self.compute_dtype)
widths = tf.cast(widths, dtype=self.compute_dtype)

tops = transformations["tops"]
lefts = transformations["lefts"]
x1s = lefts * (widths - self.width)
y1s = tops * (heights - self.height)

x2s = x1s + self.width
y2s = y1s + self.height
# normalize
Expand All @@ -229,8 +236,8 @@ def _crop_images(self, images, transformations):
boxes = tf.concat([y1s, x1s, y2s, x2s], axis=-1)

images = tf.image.crop_and_resize(
images,
boxes,
tf.cast(images, tf.float32),
tf.cast(boxes, tf.float32),
tf.range(batch_size),
[self.height, self.width],
method="nearest",
Expand All @@ -246,8 +253,8 @@ def _crop_bounding_boxes(self, images, boxes, transformation):
tops = transformation["tops"]
lefts = transformation["lefts"]
heights, widths = self._get_image_shape(images)
heights = tf.cast(heights, dtype=tf.float32)
widths = tf.cast(widths, dtype=tf.float32)
heights = tf.cast(heights, dtype=self.compute_dtype)
widths = tf.cast(widths, dtype=self.compute_dtype)

# compute offsets for xyxy bounding_boxes
top_offsets = tf.cast(
Expand All @@ -259,7 +266,9 @@ def _crop_bounding_boxes(self, images, boxes, transformation):
dtype=self.compute_dtype,
)

x1s, y1s, x2s, y2s = tf.split(boxes, 4, axis=-1)
x1s, y1s, x2s, y2s = tf.split(
tf.cast(boxes, self.compute_dtype), 4, axis=-1
)
x1s -= tf.expand_dims(left_offsets, axis=1)
y1s -= tf.expand_dims(top_offsets, axis=1)
x2s -= tf.expand_dims(left_offsets, axis=1)
Expand All @@ -269,11 +278,13 @@ def _crop_bounding_boxes(self, images, boxes, transformation):

def _resize_bounding_boxes(self, images, boxes):
heights, widths = self._get_image_shape(images)
heights = tf.cast(heights, dtype=tf.float32)
widths = tf.cast(widths, dtype=tf.float32)
heights = tf.cast(heights, dtype=self.compute_dtype)
widths = tf.cast(widths, dtype=self.compute_dtype)
x_scale = tf.cast(self.width / widths, dtype=self.compute_dtype)
y_scale = tf.cast(self.height / heights, dtype=self.compute_dtype)
x1s, y1s, x2s, y2s = tf.split(boxes, 4, axis=-1)
x1s, y1s, x2s, y2s = tf.split(
tf.cast(boxes, self.compute_dtype), 4, axis=-1
)
outputs = tf.concat(
[
x1s * x_scale[:, tf.newaxis, :],
Expand Down
107 changes: 95 additions & 12 deletions keras_cv/layers/preprocessing/with_mixed_precision_test.py
View file
Original file line number Diff line number Diff line change
Expand Up @@ -30,6 +30,8 @@
"target_size": (224, 224),
"crop_area_factor": (0.8, 1.0),
"aspect_ratio_factor": (3 / 4, 4 / 3),
"bounding_box_format": "xywh",
"dtype": "float32",
},
),
("Grayscale", layers.Grayscale, {}),
Expand All @@ -50,7 +52,11 @@
layers.RandomCutout,
{"height_factor": 0.2, "width_factor": 0.2},
),
("RandomFlip", layers.RandomFlip, {"mode": "horizontal"}),
(
"RandomFlip",
layers.RandomFlip,
{"mode": "horizontal", "bounding_box_format": "xyxy"},
),
(
"RandomHue",
layers.RandomHue,
Expand All @@ -59,7 +65,12 @@
(
"RandomTranslation",
layers.RandomTranslation,
{"width_factor": 0.5, "height_factor": 0.5},
{
"width_factor": 0.5,
"height_factor": 0.5,
"bounding_box_format": "xyxy",
"dtype": "float32",
},
),
(
"RandomChannelShift",
Expand All @@ -86,28 +97,64 @@
(
"RandomGaussianBlur",
layers.RandomGaussianBlur,
{"kernel_size": 3, "factor": (0.0, 3.0)},
{"kernel_size": 3, "factor": (0.0, 3.0), "dtype": "float32"},
),
(
"RandomJpegQuality",
layers.RandomJpegQuality,
{"factor": (75, 100), "dtype": "float32"},
),
(
"RandomRotation",
layers.RandomRotation,
{
"factor": 0.5,
"bounding_box_format": "xyxy",
"dtype": "float32",
},
),
("RandomJpegQuality", layers.RandomJpegQuality, {"factor": (75, 100)}),
("RandomRotation", layers.RandomRotation, {"factor": 0.5}),
("RandomSaturation", layers.RandomSaturation, {"factor": 0.5}),
(
"RandomSharpness",
layers.RandomSharpness,
{"factor": 0.5, "value_range": (0, 255)},
),
("RandomAspectRatio", layers.RandomAspectRatio, {"factor": (0.9, 1.1)}),
("RandomShear", layers.RandomShear, {"x_factor": 0.3, "x_factor": 0.3}),
(
"RandomAspectRatio",
layers.RandomAspectRatio,
{
"factor": (0.9, 1.1),
"bounding_box_format": "xyxy",
"dtype": "float32",
},
),
(
"RandomShear",
layers.RandomShear,
{
"x_factor": 0.3,
"x_factor": 0.3,
"bounding_box_format": "xyxy",
"dtype": "float32",
},
),
("Solarization", layers.Solarization, {"value_range": (0, 255)}),
("Mosaic", layers.Mosaic, {}),
("CutMix", layers.CutMix, {}),
(
"Mosaic",
layers.Mosaic,
{"bounding_box_format": "xyxy"},
),
("CutMix", layers.CutMix, {"dtype": "float32"}),
("MixUp", layers.MixUp, {}),
(
"Resizing",
layers.Resizing,
{
"height": 224,
"width": 224,
"bounding_box_format": "xyxy",
"pad_to_aspect_ratio": True,
"dtype": "float32",
},
),
(
Expand All @@ -117,6 +164,7 @@
"target_size": (224, 224),
"scale_factor": (0.8, 1.25),
"bounding_box_format": "xywh",
"dtype": "float32",
},
),
(
Expand All @@ -127,7 +175,7 @@
(
"RandomCrop",
layers.RandomCrop,
{"height": 224, "width": 224},
{"height": 224, "width": 224, "bounding_box_format": "xyxy"},
),
(
"Rescaling",
Expand All @@ -145,6 +193,12 @@
layers.RandomHue,
]

NO_BOUNDING_BOXES_TESTS = [
layers.RandomCutout,
layers.RandomZoom,
layers.CutMix,
]


class WithMixedPrecisionTest(TestCase):
@parameterized.named_parameters(*TEST_CONFIGURATIONS)
Expand All @@ -162,8 +216,37 @@ def test_can_run_in_mixed_precision(self, layer_cls, init_args):
img = tf.random.uniform(
shape=(3, 512, 512, 3), minval=0, maxval=255, dtype=tf.float32
)
labels = tf.ones((3,), dtype=tf.float16)
inputs = {"images": img, "labels": labels}

bounding_boxes = {
"boxes": tf.convert_to_tensor(
[
[
[200, 200, 400, 400],
[250, 250, 450, 450],
[300, 300, 500, 500],
], # Bounding boxes for image 1
[
[100, 100, 300, 300],
[150, 150, 350, 350],
[200, 200, 400, 400],
], # Bounding boxes for image 2
[
[300, 300, 500, 500],
[350, 350, 550, 550],
[400, 400, 600, 600],
],
], # Bounding boxes for image 3
dtype=tf.float32,
),
"classes": tf.ones((3, 3), dtype=tf.float32),
}

inputs = {"images": img}

if layer_cls in NO_BOUNDING_BOXES_TESTS:
inputs["labels"] = bounding_boxes["classes"]
else:
inputs["bounding_boxes"] = bounding_boxes

layer = layer_cls(**init_args)
layer(inputs)
Expand Down

0 comments on commit c8a80d4

Please sign in to comment.