快捷導(dǎo)航

30秒輕松實(shí)現(xiàn)TensorFlow物體檢測

更新時(shí)間：2018年03月14日 15:09:25 作者：wangli0519

這篇文章主要為大家詳細(xì)介紹了30秒輕松實(shí)現(xiàn)TensorFlow物體檢測，具有一定的參考價(jià)值，感興趣的小伙伴們可以參考一下

Google發(fā)布了新的TensorFlow物體檢測API，包含了預(yù)訓(xùn)練模型，一個(gè)發(fā)布模型的jupyter notebook，一些可用于使用自己數(shù)據(jù)集對模型進(jìn)行重新訓(xùn)練的有用腳本。

使用該API可以快速的構(gòu)建一些圖片中物體檢測的應(yīng)用。這里我們一步一步來看如何使用預(yù)訓(xùn)練模型來檢測圖像中的物體。

首先我們載入一些會(huì)使用的庫

import numpy as np 
import os 
import six.moves.urllib as urllib 
import sys 
import tarfile 
import tensorflow as tf 
import zipfile 
 
from collections import defaultdict 
from io import StringIO 
from matplotlib import pyplot as plt 
from PIL import Image

接下來進(jìn)行環(huán)境設(shè)置

%matplotlib inline 
sys.path.append("..")

物體檢測載入

from utils import label_map_util 
 
from utils import visualization_utils as vis_util

準(zhǔn)備模型

變量任何使用export_inference_graph.py工具輸出的模型可以在這里載入，只需簡單改變PATH_TO_CKPT指向一個(gè)新的.pb文件。這里我們使用“移動(dòng)網(wǎng)SSD”模型。

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_CKPT = MODEL_NAME + '/frozen_inference_graph.pb' 
 
PATH_TO_LABELS = os.path.join('data', 'mscoco_label_map.pbtxt') 
 
NUM_CLASSES = 90

下載模型

opener = urllib.request.URLopener() 
opener.retrieve(DOWNLOAD_BASE + MODEL_FILE, MODEL_FILE) 
tar_file = tarfile.open(MODEL_FILE) 
for file in tar_file.getmembers(): 
  file_name = os.path.basename(file.name) 
  if 'frozen_inference_graph.pb' in file_name: 
    tar_file.extract(file, os.getcwd())

將（frozen）TensorFlow模型載入內(nèi)存

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='')

載入標(biāo)簽圖

標(biāo)簽圖將索引映射到類名稱，當(dāng)我們的卷積預(yù)測5時(shí)，我們知道它對應(yīng)飛機(jī)。這里我們使用內(nèi)置函數(shù)，但是任何返回將整數(shù)映射到恰當(dāng)字符標(biāo)簽的字典都適用。

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)

輔助代碼

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)

檢測

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) ] 
IMAGE_SIZE = (12, 8) 
[python] view plain copy
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) 
   # 這個(gè)array在之后會(huì)被用來準(zhǔn)備為圖片加上框和標(biāo)簽 
   image_np = load_image_into_numpy_array(image) 
   # 擴(kuò)展維度，應(yīng)為模型期待: [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') 
   # 每個(gè)框代表一個(gè)物體被偵測到. 
   boxes = detection_graph.get_tensor_by_name('detection_boxes:0') 
   # 每個(gè)分值代表偵測到物體的可信度. 
   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') 
   # 執(zhí)行偵測任務(wù). 
   (boxes, scores, classes, num_detections) = sess.run( 
     [boxes, scores, classes, num_detections], 
     feed_dict={image_tensor: image_np_expanded}) 
   # 圖形化. 
   vis_util.visualize_boxes_and_labels_on_image_array( 
     image_np, 
     np.squeeze(boxes), 
     np.squeeze(classes).astype(np.int32), 
     np.squeeze(scores), 
     category_index, 
     use_normalized_coordinates=True, 
     line_thickness=8) 
   plt.figure(figsize=IMAGE_SIZE) 
   plt.imshow(image_np)

在載入模型部分可以嘗試不同的偵測模型以比較速度和準(zhǔn)確度，將你想偵測的圖片放入TEST_IMAGE_PATHS中運(yùn)行即可。

以上就是本文的全部內(nèi)容，希望對大家的學(xué)習(xí)有所幫助，也希望大家多多支持腳本之家。

您可能感興趣的文章: