微信公衆號：[inspurer]
關注可瞭解更多。問題或建議，請公衆號留言;
[若是你以爲本文對你有幫助，歡迎讚揚]python
原料
windows10+python3.5+pycharmgit
安裝tensorflow
利用Tensorflow訓練搭建本身的物體訓練模型，萬里長征第一步，先安裝tensorflow。github
tensorflow分爲cpu版和gpu版，gpu版的運行速度是cpu的50倍，可是gpu版的坑太多，要安裝許多開發套件,對windows的支持不夠友好；更爲致命的是,它須要Nvida的中高端顯卡，個人電腦系統是windows10,顯卡是入門級顯卡，開始我還想掙扎一下，安裝個gpu版，大概試了一個晚上，究竟是沒有成功，識時務者爲俊傑，那就安裝cpu版的吧。windows
pip insatll tensorflowbash
假如沒有報錯，作個測試，運行如下代碼微信
import tensorflow as tf
#指定一個常數張量
first_blood = tf.constant('double kill')
#建立一個會話，方便查看結果
sess = tf.Session()
print(str(sess.run(first_blood)))
運行結果以下網絡
E:\python\python.exe "E:/pycharm src/TF/__init__.py"
2018-12-01 23:33:25.181550: I tensorflow/core/platform/cpu_feature_guard.cc:141] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2
double kill
Process finished with exit code 0
若是出現警告:app
Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2測試
翻譯過來的大體意思是:你的CPU支持AVX擴展，可是你安裝的TensorFlow版本沒法編譯使用 網站
此時須要在第一行代碼前加上兩行代碼:
import os
os.environ['TF_CPP_MIN_LOG_LEVEL'] = '2'
import tensorflow as tf
# 指定一個常數張量
first_blood = tf.constant('double kill')
# 建立一個會話，方便查看結果
sess = tf.Session()
print(str(sess.run(first_blood)))
下載Tensorflow object detection API
若是有git的話，右鍵git bash,使用命令下載：
git clone https://github.com/tensorflow/models.git
或者直接打開網站:
https://github.com/tensorflow/models
點擊綠色按鈕->downlaod zip
下載好以後，把文件解壓，注意解壓路徑不要包含中文，好比個人解壓後的路徑是:
C:\Users\lenovo\Desktop\note\gitclone\models
若是下載速度很慢，能夠參考:https://blog.csdn.net/ygdxt/article/details/82825013
下載並配置protoc
在https://github.com/google/protobuf/releases中選擇windows版本：
只有win32,也就是windows32位的，64位是兼容32位的。
下載好以後，解壓，把bin目錄下的protoc.exe複製到..\models\research文件夾下。
接着就是配置protoc了，在打開cmd下切換到..\models\research目錄，
執行命令protoc object_detection\protos\*.proto --python_out=.
若是報如下的錯(其實很大可能性會報錯，不管是否是在管理員模式下）：
object_detection\protos*.proto: No such file or directory
則須要對指令作修改，指令protoc object_detection\protos\*.proto --python_out=.中的*.proto表示是對research目錄下的全部後綴名爲proto的文件作操做，那乾脆咱們把指令中的*.proto這部分改爲全部後綴名爲proto的文件，每執行一次，就會生成一個.py文件，因爲文件太多，我已經把指令寫成腳本:
import os
path_url = os.path.join(os.getcwd(),r"object_detection\protos")
print("proto path:",path_url)
for file in os.listdir(path_url):
cmd = "protoc object_detection\protos\{} --python_out=."
if file.endswith(".proto"):
command = cmd.format(file)
print("excuting command:",command)
os.popen(command)
在..\research目錄下新建一個文件excuter.py,把以上代碼複製進去，保存運行，稍等一下子就能夠看到..\research\object_detection\protos目錄下生成了許多.py文件，說明protoc配置成功。
models環境變量配置
配置環境變量
依次打開：個人電腦--->高級系統設置--->環境變量，新建一個系統變量:
系統變量名只要不和已有的重複，符合命令規範，沒有其餘要求，我這裏是
tensorflow
系統變量名下有兩個值,..\research和..\research\slim的絕對路徑。
測試
在..\research下打開cmd，運行如下命令，
python object_detection/builders/model_builder_test.py
若是出現錯誤:
報錯緣由是你的models路徑太長，python沒法找指定模塊，
解決辦法是在你的python安裝路徑下新建一個tensorflow_model.pth文件
(好比個人是E:\python\Lib\site-packages)
把寫到環境變量裏的那兩個路徑複製到該文件中。
再運行命令python object_detection/builders/model_builder_test.py
說明配置成功
利用tensorflow自帶模型測試
測試的圖片是在
C:\Users\lenovo\Desktop\note\gitclone\models\research\object_detection\test_images
咱們看到這裏有現成的兩張圖片，固然也能夠換成本身的。
測試的腳本是
C:\Users\lenovo\Desktop\note\gitclone\models\research\object_detection\object_detection_tutorial.ipynb
這是一個須要用jupyter notebook打開的文件，不過好像在jupyter notebook運行會有許多毛病
我已經把這個ipynb文件改寫成py文件，並修復了一些未知問題，文件內容以下:
import numpy as np
import os
import six.moves.urllib as urllib
import sys
import tarfile
import tensorflow as tf
import zipfile
from distutils.version import StrictVersion
from collections import defaultdict
from io import StringIO
from matplotlib import pyplot as plt
from PIL import Image
# This is needed since the notebook is stored in the object_detection folder.
sys.path.append("..")
from object_detection.utils import ops as utils_ops
if StrictVersion(tf.__version__) < StrictVersion('1.9.0'):
raise ImportError('Please upgrade your TensorFlow installation to v1.9.* or later!')
import numpy as np
import os
import six.moves.urllib as urllib
import sys
import tarfile
import tensorflow as tf
import zipfile
from distutils.version import StrictVersion
from collections import defaultdict
from io import StringIO
from matplotlib import pyplot as plt
from PIL import Image
# This is needed since the notebook is stored in the object_detection folder.
sys.path.append("..")
from object_detection.utils import ops as utils_ops
if StrictVersion(tf.__version__) < StrictVersion('1.9.0'):
raise ImportError('Please upgrade your TensorFlow installation to v1.9.* or later!')
from utils import label_map_util
from utils import visualization_utils as vis_util
# What model to download.
MODEL_NAME = 'ssd_mobilenet_v1_coco_2017_11_17'
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_FROZEN_GRAPH = 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')
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())
detection_graph = tf.Graph()
with detection_graph.as_default():
od_graph_def = tf.GraphDef()
with tf.gfile.GFile(PATH_TO_FROZEN_GRAPH, 'rb') as fid:
serialized_graph = fid.read()
od_graph_def.ParseFromString(serialized_graph)
tf.import_graph_def(od_graph_def, name='')
category_index = label_map_util.create_category_index_from_labelmap(PATH_TO_LABELS, use_display_name=True)
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)
# 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)
output_num = 1
output_img_dic = r'\output_images'
def run_inference_for_single_image(image, graph):
with graph.as_default():
with tf.Session() as sess:
# Get handles to input and output tensors
ops = tf.get_default_graph().get_operations()
all_tensor_names = {output.name for op in ops for output in op.outputs}
tensor_dict = {}
for key in [
'num_detections', 'detection_boxes', 'detection_scores',
'detection_classes', 'detection_masks'
]:
tensor_name = key + ':0'
if tensor_name in all_tensor_names:
tensor_dict[key] = tf.get_default_graph().get_tensor_by_name(
tensor_name)
if 'detection_masks' in tensor_dict:
# The following processing is only for single image
detection_boxes = tf.squeeze(tensor_dict['detection_boxes'], [0])
detection_masks = tf.squeeze(tensor_dict['detection_masks'], [0])
# Reframe is required to translate mask from box coordinates to image coordinates and fit the image size.
real_num_detection = tf.cast(tensor_dict['num_detections'][0], tf.int32)
detection_boxes = tf.slice(detection_boxes, [0, 0], [real_num_detection, -1])
detection_masks = tf.slice(detection_masks, [0, 0, 0], [real_num_detection, -1, -1])
detection_masks_reframed = utils_ops.reframe_box_masks_to_image_masks(
detection_masks, detection_boxes, image.shape[0], image.shape[1])
detection_masks_reframed = tf.cast(
tf.greater(detection_masks_reframed, 0.5), tf.uint8)
# Follow the convention by adding back the batch dimension
tensor_dict['detection_masks'] = tf.expand_dims(
detection_masks_reframed, 0)
image_tensor = tf.get_default_graph().get_tensor_by_name('image_tensor:0')
# Run inference
output_dict = sess.run(tensor_dict,
feed_dict={image_tensor: np.expand_dims(image, 0)})
# all outputs are float32 numpy arrays, so convert types as appropriate
output_dict['num_detections'] = int(output_dict['num_detections'][0])
output_dict['detection_classes'] = output_dict[
'detection_classes'][0].astype(np.uint8)
output_dict['detection_boxes'] = output_dict['detection_boxes'][0]
output_dict['detection_scores'] = output_dict['detection_scores'][0]
if 'detection_masks' in output_dict:
output_dict['detection_masks'] = output_dict['detection_masks'][0]
return output_dict
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)
# Actual detection.
output_dict = run_inference_for_single_image(image_np, detection_graph)
# Visualization of the results of a detection.
vis_util.visualize_boxes_and_labels_on_image_array(
image_np,
output_dict['detection_boxes'],
output_dict['detection_classes'],
output_dict['detection_scores'],
category_index,
instance_masks=output_dict.get('detection_masks'),
use_normalized_coordinates=True,
line_thickness=8)
plt.figure(figsize=IMAGE_SIZE)
print(1,image_np)
plt.imshow(image_np)
plt.show()
global output_num
global output_img_dic
if not os.path.exists(output_img_dic):
os.mkdir(output_img_dic)
output_img_path = os.path.join(output_img_dic,str(output_num)+".png")
plt.savefig(output_img_path)
運行上述代碼須要安裝
matplotlib庫，直接pip install matplotlib安裝失敗的能夠去官網安裝與python版本對應的whl文件。安裝matplotlib.whl時須要先出pycharm。
同時因爲須要下載模型文件，須要在網絡好的狀況下進行測試。不然就會報HTTP ERROR
運行效果圖
聲明
以上就是本次教程的全部內容，後續還會有系列教程，原創做品，轉載請聯繫2391527690@qq.com
歡迎你們多多上機操做，指出本教程的不足之處，若有問題，可加羣交流，羣號碼: 861016679
歡迎關注公衆號，瞭解更多
本文分享自微信公衆號 - 月小水長（inspurer）。
若有侵權，請聯繫 support@oschina.cn 刪除。
本文參與「OSC源創計劃」，歡迎正在閱讀的你也加入，一塊兒分享。