Пример #1
0
// NewScope creates a Scope initialized with an empty Graph.
func NewScope() *Scope {
	return &Scope{graph: tf.NewGraph(), namemap: make(map[string]int), err: new(scopeErr)}
}
func Example() {
	// An example for using the TensorFlow Go API for image recognition
	// using a pre-trained inception model (http://arxiv.org/abs/1512.00567).
	//
	// The pre-trained model takes input in the form of a 4-dimensional
	// tensor with shape [ BATCH_SIZE, IMAGE_HEIGHT, IMAGE_WIDTH, 3 ],
	// where:
	// - BATCH_SIZE allows for inference of multiple images in one pass through the graph
	// - IMAGE_HEIGHT is the height of the images on which the model was trained
	// - IMAGE_WIDTH is the width of the images on which the model was trained
	// - 3 is the (R, G, B) values of the pixel colors represented as a float.
	//
	// And produces as output a vector with shape [ NUM_LABELS ].
	// output[i] is the probability that the input image was recognized as
	// having the i-th label.
	//
	// A separate file contains a list of string labels corresponding to the
	// integer indices of the output.
	//
	// This example:
	// - Loads the serialized representation of the pre-trained model into a Graph
	// - Creates a Session to execute operations on the Graph
	// - Converts an image file to a Tensor to provide as input for Graph execution
	// - Exectues the graph and prints out the label with the highest probability
	const (
		// Path to a pre-trained inception model.
		// The two files are extracted from a zip archive as so:
		/*
		   curl -L https://storage.googleapis.com/download.tensorflow.org/models/inception5h.zip -o /tmp/inception5h.zip
		   unzip /tmp/inception5h.zip -d /tmp
		*/
		modelFile  = "/tmp/tensorflow_inception_graph.pb"
		labelsFile = "/tmp/imagenet_comp_graph_label_strings.txt"

		// Image file to "recognize".
		testImageFilename = "/tmp/test.jpg"
	)

	// Load the serialized GraphDef from a file.
	model, err := ioutil.ReadFile(modelFile)
	if err != nil {
		log.Fatal(err)
	}

	// Construct an in-memory graph from the serialized form.
	graph := tf.NewGraph()
	if err := graph.Import(model, ""); err != nil {
		log.Fatal(err)
	}

	// Create a session for inference over graph.
	session, err := tf.NewSession(graph, nil)
	if err != nil {
		log.Fatal(err)
	}
	defer session.Close()

	// Run inference on testImageFilename.
	// For multiple images, session.Run() can be called in a loop (and
	// concurrently). Furthermore, images can be batched together since the
	// model accepts batches of image data as input.
	tensor, err := makeTensorFromImageForInception(testImageFilename)
	if err != nil {
		log.Fatal(err)
	}
	output, err := session.Run(
		map[tf.Output]*tf.Tensor{
			graph.Operation("input").Output(0): tensor,
		},
		[]tf.Output{
			graph.Operation("output").Output(0),
		},
		nil)
	if err != nil {
		log.Fatal(err)
	}
	// output[0].Value() is a vector containing probabilities of
	// labels for each image in the "batch". The batch size was 1.
	// Find the most probably label index.
	probabilities := output[0].Value().([][]float32)[0]
	printBestLabel(probabilities, labelsFile)
}
func Example() {
	// An example for using the TensorFlow Go API for image recognition
	// using a pre-trained inception model (http://arxiv.org/abs/1512.00567).
	//
	// Sample usage: <program> -dir=/tmp/modeldir -image=/path/to/some/jpeg
	//
	// The pre-trained model takes input in the form of a 4-dimensional
	// tensor with shape [ BATCH_SIZE, IMAGE_HEIGHT, IMAGE_WIDTH, 3 ],
	// where:
	// - BATCH_SIZE allows for inference of multiple images in one pass through the graph
	// - IMAGE_HEIGHT is the height of the images on which the model was trained
	// - IMAGE_WIDTH is the width of the images on which the model was trained
	// - 3 is the (R, G, B) values of the pixel colors represented as a float.
	//
	// And produces as output a vector with shape [ NUM_LABELS ].
	// output[i] is the probability that the input image was recognized as
	// having the i-th label.
	//
	// A separate file contains a list of string labels corresponding to the
	// integer indices of the output.
	//
	// This example:
	// - Loads the serialized representation of the pre-trained model into a Graph
	// - Creates a Session to execute operations on the Graph
	// - Converts an image file to a Tensor to provide as input to a Session run
	// - Executes the Session and prints out the label with the highest probability
	//
	// To convert an image file to a Tensor suitable for input to the Inception model,
	// this example:
	// - Constructs another TensorFlow graph to normalize the image into a
	//   form suitable for the model (for example, resizing the image)
	// - Creates an executes a Session to obtain a Tensor in this normalized form.
	modeldir := flag.String("dir", "", "Directory containing the trained model files. The directory will be created and the model downloaded into it if necessary")
	imagefile := flag.String("image", "", "Path of a JPEG-image to extract labels for")
	flag.Parse()
	if *modeldir == "" || *imagefile == "" {
		flag.Usage()
		return
	}
	// Load the serialized GraphDef from a file.
	modelfile, labelsfile, err := modelFiles(*modeldir)
	if err != nil {
		log.Fatal(err)
	}
	model, err := ioutil.ReadFile(modelfile)
	if err != nil {
		log.Fatal(err)
	}

	// Construct an in-memory graph from the serialized form.
	graph := tf.NewGraph()
	if err := graph.Import(model, ""); err != nil {
		log.Fatal(err)
	}

	// Create a session for inference over graph.
	session, err := tf.NewSession(graph, nil)
	if err != nil {
		log.Fatal(err)
	}
	defer session.Close()

	// Run inference on *imageFile.
	// For multiple images, session.Run() can be called in a loop (and
	// concurrently). Alternatively, images can be batched since the model
	// accepts batches of image data as input.
	tensor, err := makeTensorFromImage(*imagefile)
	if err != nil {
		log.Fatal(err)
	}
	output, err := session.Run(
		map[tf.Output]*tf.Tensor{
			graph.Operation("input").Output(0): tensor,
		},
		[]tf.Output{
			graph.Operation("output").Output(0),
		},
		nil)
	if err != nil {
		log.Fatal(err)
	}
	// output[0].Value() is a vector containing probabilities of
	// labels for each image in the "batch". The batch size was 1.
	// Find the most probably label index.
	probabilities := output[0].Value().([][]float32)[0]
	printBestLabel(probabilities, labelsfile)
}
Пример #4
0
// NewScope creates a Scope initialized with an empty Graph.
func NewScope() *Scope {
	return &Scope{graph: tf.NewGraph(), namemap: make(map[string]int)}
}