nbortolotti

model = tf.keras.Sequential([
  tf.keras.layers.Dense(16, input_dim=4),
  tf.keras.layers.Dense(3, activation=tf.nn.softmax),
])

model.summary()

# eager off
model.compile(loss='categorical_crossentropy',
              optimizer='sgd',

nbortolotti

# Build the dataset
# train
dataset = tf.data.Dataset.from_tensor_slices((train_plantfeatures, y_categorical))
dataset = dataset.batch(32)
dataset = dataset.shuffle(1000)
dataset = dataset.repeat()

#test
dataset_test = tf.data.Dataset.from_tensor_slices((test_plantfeatures, y_categorical_test))
dataset_test = dataset_test.batch(32)

nbortolotti

#Data download and dataset creation witout tf.data
train_ds_url = "http://download.tensorflow.org/data/iris_training.csv"
test_ds_url = "http://download.tensorflow.org/data/iris_test.csv"
ds_columns = ['SepalLength', 'SepalWidth','PetalLength', 'PetalWidth', 'Plants']
species = np.array(['Setosa', 'Versicolor', 'Virginica'], dtype=np.object)

#Load data
categories='Plants'
train_path = tf.keras.utils.get_file(train_ds_url.split('/')[-1], train_ds_url)
test_path = tf.keras.utils.get_file(test_ds_url.split('/')[-1], test_ds_url)

nbortolotti

# imports
import tensorflow as tf
import pandas as pd
import numpy as np

# Data download and dataset creation witout tf.data
train_ds_url = "http://download.tensorflow.org/data/iris_training.csv"
test_ds_url = "http://download.tensorflow.org/data/iris_test.csv"
ds_columns = ['SepalLength', 'SepalWidth','PetalLength', 'PetalWidth', 'Plants']
species = np.array(['Setosa', 'Versicolor', 'Virginica'], dtype=np.object)

nbortolotti

def dominant_color(np_object):
    pixs = np_object.reshape((-1, 3))

    n_colors = 5
    flags = cv2.KMEANS_RANDOM_CENTERS
    criteria = (cv2.TERM_CRITERIA_EPS + cv2.TERM_CRITERIA_MAX_ITER, 200, .1)
    _, labels, centroids = cv2.kmeans(np.float32(pixs), n_colors, None, criteria, 10, flags)

    palette = np.uint8(centroids)
    dominant_object_color = palette[np.argmax(itemfreq(labels)[:, -1])]

nbortolotti

 with detection_graph.as_default():
        with tf.Session(graph=detection_graph) as sess:
            image_tensor = detection_graph.get_tensor_by_name('image_tensor:0')
            detection_boxes = detection_graph.get_tensor_by_name('detection_boxes:0')
            detection_scores = detection_graph.get_tensor_by_name('detection_scores:0')
            detection_classes = detection_graph.get_tensor_by_name('detection_classes:0')
            num_detections = detection_graph.get_tensor_by_name('num_detections:0')
            for image_path in TEST_IMAGE_PATHS:
                image = Image.open(image_path)
                image_np = load_image_into_numpy_array(image)

nbortolotti

def slice_box_objects(n_image, img_with, img_height, cla, b, sco, category="tie", confident=0.7):
    objects = []
    for i, box in enumerate(np.squeeze(b)):
        if category_index[np.squeeze(cla)[i]]['name'] == category:
            if np.squeeze(sco)[i] > confident:
                crop = n_image[int(box[0] * img_height):int(box[2] * img_height),
                       int(box[1] * img_with):int(box[3] * img_with)]
                plt.imshow(crop)
                plt.show()
                objects.append(crop)

nbortolotti

[
  {
    "id": "b819610d-4da6-4a36-80c7-c55a44866526",
    "data": [
      {
        "text": "Is",
        "meta": "@sys.ignore",
        "userDefined": true
      },
      {

nbortolotti

{
  "id": "1effd397-0282-48b1-8f68-7b68d8068061",
  "name": "Arlo Image",
  "auto": true,
  "contexts": [],
  "responses": [
    {
      "resetContexts": false,
      "action": "image.analysis",
      "affectedContexts": [

nbortolotti

@app.route('/arlo', methods=['POST'])
def tensor_photo():
    try:
        # connect to Arlo using PyArlo library.
        arlo = PyArlo('user', read_file("pass.txt"))

        req = request.get_json(silent=True, force=True)
        action = req.get('result').get('action')

        # detect action from DialogFlow agent description.