-Use a pre-trained and optimized model to identify hundreds of classes of objects, including people, activities, animals, plants, and places.
+Use a pre-trained and optimized model to identify hundreds of classes of
+objects, including people, activities, animals, plants, and places.
## Get started
-If you are unfamiliar with the concept of image classification, you should start by reading What is image classification?
+If you are unfamiliar with the concept of image classification, you should start
+by reading What is image
+classification?
-If you understand image classification, you’re new to TensorFlow Lite, and you’re working with Android or iOS, we recommend following the corresponding tutorial that will walk you through our sample code.
+If you understand image classification, you’re new to TensorFlow Lite, and
+you’re working with Android or iOS, we recommend following the corresponding
+tutorial that will walk you through our sample code.
Android
iOS
-If you are using a platform other than Android or iOS, or you are already familiar with the TensorFlow Lite APIs, you can download our starter image classification model and the accompanying labels.
+We also provide example applications you can
+use to get started.
-Once you have the starter model running on your target device, you can experiment with different models to find the optimal balance between performance, accuracy, and model size. For guidance, see Choose a different model.
+If you are using a platform other than Android or iOS, or you are already
+familiar with the TensorFlow Lite APIs, you can
+download our starter image classification model and the accompanying labels.
+Download
+starter model and labels
-If you are using a platform other than Android or iOS, or you are already familiar with the TensorFlow Lite APIs, you can download our starter image classification model and the accompanying labels.
+Once you have the starter model running on your target device, you can
+experiment with different models to find the optimal balance between
+performance, accuracy, and model size. For guidance, see
+Choose a different model.
-Download starter model and labels
+If you are using a platform other than Android or iOS, or you are already
+familiar with the TensorFlow Lite APIs, you can
+download our starter image classification model and the accompanying labels.
+
+Download
+starter model and labels
+
+### Example applications
+
+We have example applications for image classification for both Android and iOS.
+
+Android
+example
+iOS
+example
+
+The following screenshot shows the Android image classification example:
+
+
## What is image classification?
-A common use of machine learning is to identify what an image represents. For example, we might want to know what type of animal appears in the following photograph.
+
+A common use of machine learning is to identify what an image represents. For
+example, we might want to know what type of animal appears in the following
+photograph.
-The task of predicting what an image represents is called image classification. An image classification model is trained to recognize various classes of images. For example, a model might be trained to recognize photos representing three different types of animals: rabbits, hamsters, and dogs.
+The task of predicting what an image represents is called _image
+classification_. An image classification model is trained to recognize various
+classes of images. For example, a model might be trained to recognize photos
+representing three different types of animals: rabbits, hamsters, and dogs.
-When we subsequently provide a new image as input to the model, it will output the probabilities of the image representing each of the types of animal it was trained on. An example output might be as follows:
+When we subsequently provide a new image as input to the model, it will output
+the probabilities of the image representing each of the types of animal it was
+trained on. An example output might be as follows:
| Label | -Training data | -
|---|---|
| rabbit | -[three different images of rabbits] | -
| hamster | -[three different images of hamsters] | -
| dog | -[three different images of dogs] | -
|
- → | -[0.07, 0.02, 0.91] | +→ | +[0.07, 0.02, 0.91] |
-Detect multiple objects with bounding boxes. Yes, dogs and cats too.
+Detect multiple objects within an image, with bounding boxes. Recognize 80
+different classes of objects.
-Download starter model and labels
+## Get started
-## Tutorials (coming soon)
-iOS
-Android
+If you are new to TensorFlow Lite and are working with Android or iOS, we
+recommend exploring the following example applications that can help you get
+started.
+
+Android
+example
+iOS
+example
+
+If you are using a platform other than Android or iOS, or you are already
+familiar with the TensorFlow Lite APIs, you can
+download our starter object detection model and the accompanying labels.
+
+Download
+starter model and labels
+
+For more information about the starter model, see
+Starter model.
## What is object detection?
-Given an image or a video stream, an object detection model can identify which of a known set of objects might be present and provide information about their positions within the image.
-
-For example, this screenshot of our object detection sample app shows how several objects have been recognized and their positions annotated:
+Given an image or a video stream, an object detection model can identify which
+of a known set of objects might be present and provide information about their
+positions within the image.
+For example, this screenshot of our example
+application shows how two objects have been recognized and their positions
+annotated:
-
-TODO: Insert image
+
-An object detection model is trained to detect the presence and location of multiple classes of objects. For example, a model might be trained with images that contain various pieces of computer hardware, along with a label that specifies the class of hardware they represent (e.g. a laptop, a keyboard, or a monitor), and data specifying where each object appears in the image.
+An object detection model is trained to detect the presence and location of
+multiple classes of objects. For example, a model might be trained with images
+that contain various pieces of fruit, along with a _label_ that specifies the
+class of fruit they represent (e.g. an apple, a banana, or a strawberry), and
+data specifying where each object appears in the image.
-When we subsequently provide an image to the model, it will output a list of the objects it detects, the location of a bounding box that contains each object, and a score that indicates the confidence that detection was correct.
+When we subsequently provide an image to the model, it will output a list of the
+objects it detects, the location of a bounding box that contains each object,
+and a score that indicates the confidence that detection was correct.
### Model output
+Imagine a model has been trained to detect apples, bananas, and strawberries.
+When we pass it an image, it will output a set number of detection results - in
+this example, 5.
+
| Laptop | +Apple | 0.92 | [18, 21, 57, 63] |
| Keyboard | +Banana | 0.88 | [100, 30, 180, 150] |
| Monitor | +Strawberry | 0.87 | [7, 82, 89, 163] |
| Keyboard | +Banana | 0.23 | [42, 66, 57, 83] |
| Monitor | +Apple | 0.11 | [6, 42, 31, 58] |
| Laptop | +Apple | 0.92 | [18, 21, 57, 63] |
| Keyboard | +Banana | 0.88 | [100, 30, 180, 150] |
| Monitor | +Strawberry | 0.87 | [7, 82, 89, 163] |
| Keyboard | +Banana | 0.23 | [42, 66, 57, 83] |
| Monitor | +Apple | 0.11 | [6, 42, 31, 58] |
### Location
-For each detected object, the model will return an array of four numbers representing a bounding rectangle that surrounds its position. The numbers are ordered as follows:
+For each detected object, the model will return an array of four numbers
+representing a bounding rectangle that surrounds its position. For the starter
+model we provide, the numbers are ordered as follows:
-
-## Get started
-Android and iOS end-to-end tutorials are coming soon. In the meantime, if you want to experiment this on a web browser, check out the TensorFlow.js GitHub repository.
+
## How it performs
-Performance varies based on your device and output stride (heatmaps and offset vectors). The PoseNet model is image size invariant, which means it can predict pose positions in the same scale as the original image regardless of whether the image is downscaled. This means PoseNet can be configured to have a higher accuracy at the expense of performance.
-The output stride determines how much we’re scaling down the output relative to the input image size. It affects the size of the layers and the model outputs. The higher the output stride, the smaller the resolution of layers in the network and the outputs, and correspondingly their accuracy. In this implementation, the output stride can have values of 8, 16, or 32. In other words, an output stride of 32 will result in the fastest performance but lowest accuracy, while 8 will result in the highest accuracy but slowest performance. We recommend starting with 16.
+Performance varies based on your device and output stride (heatmaps and offset
+vectors). The PoseNet model is image size invariant, which means it can predict
+pose positions in the same scale as the original image regardless of whether the
+image is downscaled. This means PoseNet can be configured to have a higher
+accuracy at the expense of performance.
-
-The output stride determines how much we’re scaling down the output relative to the input image size. A higher output stride is faster but results in lower accuracy.
+The output stride determines how much we’re scaling down the output relative to
+the input image size. It affects the size of the layers and the model outputs.
+The higher the output stride, the smaller the resolution of layers in the
+network and the outputs, and correspondingly their accuracy. In this
+implementation, the output stride can have values of 8, 16, or 32. In other
+words, an output stride of 32 will result in the fastest performance but lowest
+accuracy, while 8 will result in the highest accuracy but slowest performance.
+We recommend starting with 16.
+
+The following image shows how the output stride determines how much we’re
+scaling down the output relative to the input image size. A higher output stride
+is faster but results in lower accuracy.
+
+
+
+## Read more about pose estimation
-## Read more about this
-DeepLab is a state-of-art deep learning model for semantic image segmentation, where the goal is to assign semantic labels (e.g., person, dog, cat and so on) to every pixel in the input image.
+## Get started
-Download starter model
+_DeepLab_ is a state-of-art deep learning model for semantic image segmentation,
+where the goal is to assign semantic labels (e.g. person, dog, cat) to every
+pixel in the input image.
-## Tutorials (coming soon)
-iOS
-Android
+Download
+starter model
## How it works
-It all started with classification where the model predicts an entire input. With advances in data, hardware, and software, object detection can infer objects with spatial location. Semantic segmentation offers the highest level of granularity with labels at a pixel level.
-Current implementation includes the following features:
+Semantic image segmentation predicts whether each pixel of an image is
+associated with a certain class. This is in contrast to
+object detection, which detects
+objects in rectangular regions, and
+image classification, which
+classifies the overall image.
+
+The current implementation includes the following features:
-## Read more about this
+The model will create a mask over the target objects with high accuracy.
+
+
+
+## Read more about segmentation
+
-Smart replies are contextually relevant, one-touch responses that help the user to reply to an incoming text message (or email) efficiently and effortlessly.
+## Get started
-Download starter model and labels
+Our smart reply model generates reply suggestions based on chat messages. The
+suggestions are intended to be contextually relevant, one-touch responses that
+help the user to easily reply to an incoming message.
-## Tutorials (coming soon)
-iOS
-Android
+Download
+starter model and labels
+
+### Sample application
+
+We have provided a pre-built APK that demonstrates the smart reply model on
+Android.
+
+Go to the
+GitHub
+page for instructions and list of supported ops and functionalities.
## How it works
-The model generates reply suggestions to input conversational chat messages with an efficient inference that can be easily be plugged in to your chat application to power on-device conversational intelligence.
+
+The model generates reply suggestions to conversational chat messages.
The on-device model comes with several benefits. It is:
-## How to use this model?
-We have provided a pre-built demo APK that you can download, install, and test on your phone. Go to the GitHub page for instructions and list of support ops and functionalities.
+
## Read more about this
+
## Users
+
-
-Recognize audio keywords!
-
-Download starter model
-
-## Tutorials (coming soon)
-iOS
-Android
-
-## What is speech recognition?
-Coming soon.
diff --git a/tensorflow/lite/kernels/internal/optimized/optimized_ops.h b/tensorflow/lite/kernels/internal/optimized/optimized_ops.h
index 3e2fce56056..6ddd790b6f6 100644
--- a/tensorflow/lite/kernels/internal/optimized/optimized_ops.h
+++ b/tensorflow/lite/kernels/internal/optimized/optimized_ops.h
@@ -20,6 +20,7 @@ limitations under the License.
#include 
-PoseNet is a vision model that can be used to estimate the pose of a person in an image/video by estimating where key body joints are.
+## Get started
-