Wie mit. Meta- und Checkpoint-Dateien in Tensorflow vorhersagen?

Question

Ich lerne gerade über MobileNet und ich bin neu in Tensorflow. Nach dem Training mit SSD-Mobilet-Modell, habe ich Checkpoint-Datei, Meta-Datei, Graph.pbtxt-Datei und so weiter. Wenn ich versuche, mit diesen Dateien zu prognostizieren, kann ich nicht die Ausgabe wie box_pred, class_scores ...

Dann habe ich festgestellt, Demo-Code verwendet .pb-Datei, um Grafik zu laden, und verwendet "get_tensor_by_name" zu erhalten Ausgabe , aber ich habe keine .pb-Datei. Also, wie kann ich ein Bild mit .meta- und ckpt-Dateien vorhersagen?

BTW, hier ist Dämon Hauptcode vorhersagen:

import numpy as np 
import os 
import six.moves.urllib as urllib 
import sys 
import tarfile 
import tensorflow as tf 
import zipfile 
import time 

from collections import defaultdict 
from io import StringIO 
from matplotlib import pyplot as plt 
from PIL import Image 

#%matplotlib inline 

# This is needed since the notebook is stored in the object_detection folder. 
sys.path.append("..") 

from utils import label_map_util 
from utils import visualization_utils as vis_util 

# What model to download. 
MODEL_NAME = 'ssd_mobilenet_v1_coco_11_06_2017' 
MODEL_FILE = MODEL_NAME + '.tar.gz' 
DOWNLOAD_BASE = 'http://download.tensorflow.org/models/object_detection/' 

# Path to frozen detection graph. This is the actual model that is used for the object detection. 
PATH_TO_CKPT = MODEL_NAME + '/frozen_inference_graph.pb' 

# List of the strings that is used to add correct label for each box. 
PATH_TO_LABELS = os.path.join('data', 'mscoco_label_map.pbtxt') 

NUM_CLASSES = 90 

#Load a (frozen) Tensorflow model into memory. 
detection_graph = tf.Graph() 
with detection_graph.as_default(): 
    od_graph_def = tf.GraphDef() 
    with tf.gfile.GFile(PATH_TO_CKPT, 'rb') as fid: 
     serialized_graph = fid.read() 
     od_graph_def.ParseFromString(serialized_graph) 
     tf.import_graph_def(od_graph_def, name='') 

#load label map 
label_map = label_map_util.load_labelmap(PATH_TO_LABELS) 
categories = label_map_util.convert_label_map_to_categories(label_map, max_num_classes=NUM_CLASSES, use_display_name=True) 
category_index = label_map_util.create_category_index(categories) 

def load_image_into_numpy_array(image): 
    (im_width, im_height) = image.size 
    return np.array(image.getdata()).reshape(
     (im_height, im_width, 3)).astype(np.uint8) 


#detection 
# For the sake of simplicity we will use only 2 images: 
# image1.jpg 
# image2.jpg 
# If you want to test the code with your images, just add path to the images to the TEST_IMAGE_PATHS. 
PATH_TO_TEST_IMAGES_DIR = 'test_images' 
TEST_IMAGE_PATHS = [ os.path.join(PATH_TO_TEST_IMAGES_DIR, 'image{}.jpg'.format(i)) for i in range(1, 3) ] 

# Size, in inches, of the output images. 
IMAGE_SIZE = (12, 8) 

with detection_graph.as_default(): 
    with tf.Session(graph=detection_graph) as sess: 
    for image_path in TEST_IMAGE_PATHS: 
     image = Image.open(image_path) 
     # the array based representation of the image will be used later in order to prepare the 
     # result image with boxes and labels on it. 
     image_np = load_image_into_numpy_array(image) 
     # Expand dimensions since the model expects images to have shape: [1, None, None, 3] 
     image_np_expanded = np.expand_dims(image_np, axis=0) 
     image_tensor = detection_graph.get_tensor_by_name('image_tensor:0') 
     # Each box represents a part of the image where a particular object was detected. 
     boxes = detection_graph.get_tensor_by_name('detection_boxes:0') 
     # Each score represent how level of confidence for each of the objects. 
     # Score is shown on the result image, together with the class label. 
     scores = detection_graph.get_tensor_by_name('detection_scores:0') 
     classes = detection_graph.get_tensor_by_name('detection_classes:0') 
     num_detections = detection_graph.get_tensor_by_name('num_detections:0') 
     # Actual detection. 
     (boxes, scores, classes, num_detections) = sess.run(
      [boxes, scores, classes, num_detections], 
      feed_dict={image_tensor: image_np_expanded}) 

Answer 1

Sie die Grafik tf.train.import_meta_graph() mit laden soll und dann die Tensoren get_tensor_by_name() mit bekommen. Sie können versuchen:

model_path = "model.ckpt" 
detection_graph = tf.Graph() 
with tf.Session(graph=detection_graph) as sess: 
    # Load the graph with the trained states 
    loader = tf.train.import_meta_graph(model_path+'.meta') 
    loader.restore(sess, model_path) 

    # Get the tensors by their variable name 
    image_tensor = detection_graph.get_tensor_by_name('image_tensor:0') 
    boxes = detection_graph.get_tensor_by_name('detection_boxes:0') 
    scores = detection_graph.get_tensor_by_name('detection_scores:0') 
    ... 
    # Make predictions 
    _boxes, _scores = sess.run([boxes, scores], feed_dict={image_tensor: image_np_expanded}) 

Answer 2

Nun, ich habe es gelungen die Grafik laden den Code mit Gebrüll:

with tf.Session(config=tf.ConfigProto(allow_soft_placement=True)) as sess: 
    #with tf.device("/cpu:0"): 
    new_saver = tf.train.import_meta_graph('./model.ckpt-1281.meta') 
    new_saver.restore(sess, './model.ckpt-1281') 
    detection_graph = tf.get_default_graph() 

    for image_path in TEST_IMAGE_PATHS: 
     image = Image.open(image_path) 
     image_np = load_image_into_numpy_array(image) 
     image_np_expanded = np.expand_dims(image_np, axis=0) 
     image_tensor = detection_graph.get_tensor_by_name('image_tensor:0') 
     boxes = detection_graph.get_tensor_by_name('detection_boxes:0') 
     scores = detection_graph.get_tensor_by_name('detection_scores:0') 
     classes = detection_graph.get_tensor_by_name('detection_classes:0') 
     num_detections = detection_graph.get_tensor_by_name('num_detections:0') 
     # Actual detection. 
     (boxes, scores, classes, num_detections) = sess.run(
      [boxes, scores, classes, num_detections], 
      feed_dict={image_tensor: image_np_expanded}) 
     print scores, boxes 

Aber ich habe diese erro:

KeyError:"The name 'image_tensor:0' refers to a Tensor which does not exist. The operation, 'image_tensor', does not exist in the graph." 

Dann prüfe ich den Tensor name in graph und graph.pbtxt datei gibt es keinen solchen namen wie "image_tensor", "detection_boxes", "detection_scores" oder gar "softmax". Wie kann ich also die Ausgabe des Graphen vorhersagen?