如何預測.meta和檢查點文件的張量流？

Question

我正在學習有關MobileNet的這些日子，我對tensorflow很陌生。經過ssd-mobilenet模型培訓後，我得到了checkpoint文件，.meta文件，graph.pbtxt文件等。當我嘗試預測這些文件，我無法得到輸出，如box_pred，classs_scores ...

然後，我發現預測演示代碼使用.pb文件來加載圖形，並使用「get_tensor_by_name」來獲得輸出，但我沒有.pb文件。那麼，如何用.meta和ckpt文件預測圖像呢？

BTW，這裏是妖預測主要代碼：

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

你應該使用tf.train.import_meta_graph()加載圖形，然後使用get_tensor_by_name()得到張量。你可以試試：

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

好了，我已經成功使用的代碼波紋管加載圖：

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 

但我得到這個埃羅：

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

然後，我檢查了張量名稱在graph和graph.pbtxt文件中，沒有像「image_tensor」，「detection_boxes」，「detection_scores」或甚至「softmax」這樣的名稱。那麼我怎樣才能預測圖的輸出呢？