Update keras cv docs to the newest release

guides/keras_cv/coco_metrics.py

@@ -22,26 +22,26 @@
 """
 ## Input format
 
-KerasCV COCO metrics require a specific input format.
+All KerasCV components that process bounding boxes, including COCO metrics, require a
+`bounding_box_format` parameter.  This parameter is used to tell the components what
+format your bounding boxes are in.  While this guide uses the `xyxy` format, a full
+list of supported formats is available in
+[the bounding_box API documentation](/api/keras_cv/bounding_box/formats).
 
 The metrics expect `y_true` and be a `float` Tensor with the shape `[batch,
-num_images, num_boxes, 5]`. The final axis stores the locational and class
-information for each specific bounding box. The dimensions in order are: `[left,
-top, right, bottom, class]`.
-
-The metrics expect `y_pred` and be a `float` Tensor with the shape `[batch,
-num_images, num_boxes, 56]`. The final axis stores the locational and class
-information for each specific bounding box. The dimensions in order are: `[left,
-top, right, bottom, class, confidence]`.
+num_images, num_boxes, 5]`, with the ordering of last set of axes determined by the
+provided format.  The same is true of `y_pred`, except that an additional `confidence`
+axis must be provided.
 
 Due to the fact that each image may have a different number of bounding boxes,
 the `num_boxes` dimension may actually have a mismatching shape between images.
 KerasCV works around this by allowing you to either pass a `RaggedTensor` as an
 input to the KerasCV COCO metrics, or padding unused bounding boxes with `-1`.
 
 Utility functions to manipulate bounding boxes, transform between formats, and
-pad bounding box Tensors with `-1s` are available at
-[`keras_cv.bounding_box`](https://github.com/keras-team/keras-cv/blob/master/keras_cv/bounding_box).
+pad bounding box Tensors with `-1s` are available from the
+[`keras_cv.bounding_box`](https://github.com/keras-team/keras-cv/blob/master/keras_cv/bounding_box)
+package.
 
 """
 
@@ -67,7 +67,9 @@
 from tensorflow import keras
 
 # only consider boxes with areas less than a 32x32 square.
-metric = keras_cv.metrics.COCORecall(class_ids=[1, 2, 3], area_range=(0, 32**2))
+metric = keras_cv.metrics.COCORecall(
+    bounding_box_format="xyxy", class_ids=[1, 2, 3], area_range=(0, 32**2)
+)
 
 """
 2.) Create Some Bounding Boxes:
@@ -130,7 +132,11 @@
 """
 
 recall = keras_cv.metrics.COCORecall(
-    max_detections=100, class_ids=[1], area_range=(0, 64**2), name="coco_recall"
+    bounding_box_format="xyxy",
+    max_detections=100,
+    class_ids=[1],
+    area_range=(0, 64**2),
+    name="coco_recall",
 )
 model.compile(metrics=[recall])
 

guides/keras_cv/custom_image_augmentations.py

@@ -430,6 +430,12 @@ def __init__(self, **kwargs):
 
 
 """
+
+Additionally, be sure to accept `**kwargs` to your `augment_*` methods to ensure
+forwards compatibility.  KerasCV will add additional label types in the future, and
+if you do not include a `**kwargs` argument your augmentation layers will not be
+forward compatible.
+
 ## Conclusion and next steps
 
 KerasCV offers a standard set of APIs to streamline the process of implementing your

guides/keras_cv/cut_mix_mix_up_and_rand_augment.py

@@ -13,7 +13,8 @@
 pipelines for image classification and object detection tasks. KerasCV offers a wide
 suite of preprocessing layers implementing common data augmentation techniques.
 
-Perhaps three of the most useful layers are `CutMix`, `MixUp`, and `RandAugment`. These
+Perhaps three of the most useful layers are `keras_cv.layers.CutMix`,
+`keras_cv.layers.MixUp`, and `keras_cv.layers.RandAugment`. These
 layers are used in nearly all state-of-the-art image classification pipelines.
 
 This guide will show you how to compose these layers into your own data
@@ -70,7 +71,7 @@
 num_classes = dataset_info.features["label"].num_classes
 
 
-def prepare(image, label):
+def to_dict(image, label):
     image = tf.image.resize(image, IMAGE_SIZE)
     image = tf.cast(image, tf.float32)
     label = tf.one_hot(label, num_classes)
@@ -214,7 +215,8 @@ def cut_mix_and_mix_up(samples):
 ## Customizing your augmentation pipeline
 
 Perhaps you want to exclude an augmentation from `RandAugment`, or perhaps you want to
-include the `GridMask()` as an option alongside the default `RandAugment` augmentations.
+include the `keras_cv.layers.GridMask` as an option alongside the default `RandAugment`
+augmentations.
 
 KerasCV allows you to construct production grade custom data augmentation pipelines using
 the `keras_cv.layers.RandomAugmentationPipeline` layer. This class operates similarly to
@@ -246,7 +248,7 @@ def cut_mix_and_mix_up(samples):
 ]
 
 """
-Next, let's add `GridMask` to our layers:
+Next, let's add `keras_cv.layers.GridMask` to our layers:
 """
 
 layers = layers + [keras_cv.layers.GridMask()]
@@ -263,12 +265,6 @@ def cut_mix_and_mix_up(samples):
 Let's check out the results!
 """
 
-
-def apply_pipeline(inputs):
-    inputs["images"] = pipeline(inputs["images"])
-    return inputs
-
-
 train_dataset = load_dataset().map(apply_pipeline, num_parallel_calls=AUTOTUNE)
 visualize_dataset(train_dataset, title="After custom pipeline")
 

scripts/autogen.py

@@ -258,7 +258,6 @@ def add_example(self, path, working_dir=None):
         )
         open(md_path, "w").write(md_content)
 
-
     def add_guide(self, name, working_dir=None):
         """e.g. add_guide('functional_api')"""
 
@@ -948,7 +947,7 @@ def generate_md_toc(entries, url, depth=2):
             title=title, full_url=full_url
         )
         if children:
-            assert path.endswith("/")
+            assert path.endswith("/"), f"{path} should end with /"
             for child in children:
                 if child.get("skip_from_toc", False):
                     continue

scripts/cv_api_master.py

@@ -8,6 +8,11 @@
             "title": "AutoContrast layer",
             "generate": ["keras_cv.layers.AutoContrast"],
         },
+        {
+            "path": "aug_mix",
+            "title": "AugMix layer",
+            "generate": ["keras_cv.layers.AugMix"],
+        },
         {
             "path": "channel_shuffle",
             "title": "ChannelShuffle layer",
@@ -64,7 +69,7 @@
             "generate": ["keras_cv.layers.RandomChannelShift"],
         },
         {
-            "path": "rancom_color_degeneration",
+            "path": "random_color_degeneration",
             "title": "RandomColorDegeneration layer",
             "generate": ["keras_cv.layers.RandomColorDegeneration"],
         },
@@ -101,6 +106,37 @@
     ],
 }
 
+BOUNDING_BOX_FORMATS = {
+    "path": "formats",
+    "title": "Bounding box formats",
+    "generate": [
+        "keras_cv.bounding_box.CENTER_XYWH",
+        "keras_cv.bounding_box.XYWH",
+        "keras_cv.bounding_box.XYXY",
+        "keras_cv.bounding_box.REL_XYXY",
+    ],
+}
+
+BOUNDING_BOX_UTILS = {
+    "path": "utils/",
+    "title": "Bounding box utilities",
+    "toc": True,
+    "children": [
+        {
+            "path": "convert_format",
+            "title": "Convert bounding box formats",
+            "generate": ["keras_cv.bounding_box.convert_format"],
+        },
+    ],
+}
+
+BOUNDING_BOX_MASTER = {
+    "path": "bounding_box/",
+    "title": "Bounding box formats and utilities",
+    "toc": True,
+    "children": [BOUNDING_BOX_FORMATS, BOUNDING_BOX_UTILS],
+}
+
 REGULARIZATION_MASTER = {
     "path": "regularization/",
     "title": "Regularization layers",
@@ -150,5 +186,5 @@
     "path": "keras_cv/",
     "title": "KerasCV",
     "toc": True,
-    "children": [LAYERS_MASTER, METRICS_MASTER],
+    "children": [LAYERS_MASTER, METRICS_MASTER, BOUNDING_BOX_MASTER],
 }

scripts/docstrings.py

@@ -115,6 +115,7 @@ def import_object(string: str):
         try:
             last_object_got = importlib.import_module(".".join(seen_names))
         except ModuleNotFoundError:
+            assert last_object_got is not None, f"Failed to import path {string}"
             last_object_got = getattr(last_object_got, name)
     return last_object_got
 
@@ -127,7 +128,7 @@ def make_source_link(cls, project_url):
 
     base_module = cls.__module__.split(".")[0]
     project_url = project_url[base_module]
-    assert project_url.endswith("/")
+    assert project_url.endswith("/"), f"{base_module} not found"
     project_url_version = project_url.split("/")[-2].replace("v", "")
     module_version = importlib.import_module(base_module).__version__
     if module_version != project_url_version:

templates/keras_cv/bounding_box/index.md

@@ -0,0 +1,10 @@
+# KerasCV Bounding Boxes
+
+All KerasCV components that process bounding boxes require a `bounding_box_format`
+argument.  This argument allows you to seamlessly integrate KerasCV components into
+your own workflows while preserving proper behavior of the components themselves.
+
+The bounding box formats supported in KerasCV 
+[are listed in the API docs](/api/keras_cv/bounding_box/formats)
+If a format you would like to use is missing,
+[feel free to open a GitHub issue on KerasCV](https://github.com/keras-team/keras-cv/issues)!

templates/keras_cv/index.md

@@ -25,6 +25,46 @@ pip install keras-cv --upgrade
 You can also check out other versions in our
 [GitHub repository](https://github.com/keras-team/keras-cv/releases).
 
+## Quick Introduction
+
+Create a preprocessing pipeline:
+
+```python
+import keras_cv
+from tensorflow import keras
+
+preprocessing_model = keras.Sequential([
+    keras_cv.layers.RandAugment(value_range=(0, 255))
+    keras_cv.layers.CutMix(),
+    keras_cv.layers.MixUp()
+], name="preprocessing_model")
+```
+
+Augment a `tf.data.Dataset`:
+
+```python
+dataset = dataset.map(lambda images, labels: {"images": images, "labels": labels})
+dataset = dataset.map(preprocessing_model)
+dataset = dataset.map(lambda inputs: (inputs["images"], inputs["labels"]))
+```
+
+Create a model:
+
+```python
+densenet = keras_cv.models.DenseNet(
+  include_rescaling=True,
+  include_top=True,
+  num_classes=102
+)
+densenet.compile(optimizer='adam', metrics=['accuracy'])
+```
+
+Train your model:
+
+```python
+densenet.fit(dataset)
+```
+
 ---
 ## Citing KerasCV