问题描述
import numpy as np
import os
import six.moves.urllib as urllib
import sys
import tarfile
import tensorflow.compat.v1 as tf
tf.disable_v2_behavior()
import zipfile
from collections import defaultdict
from io import StringIO
from matplotlib import pyplot as plt
from PIL import Image
from object_detection.utils import label_map_util
from object_detection.utils import visualization_utils as vis_util
from tensorflow.compat.v1 import ConfigProto
from tensorflow.compat.v1 import InteractiveSession
config = ConfigProto()
config.gpu_options.allow_growth = True
session = InteractiveSession(config=config)
# This is needed since the notebook is stored in the object_detection folder.
sys.path.append("..")
# script repurposed from sentdex's edits and TensorFlow's example script. Pretty messy as not all unnecessary
# parts of the original have been removed
# # Model preparation
# ## Variables
#
# Any model exported using the `export_inference_graph.py` tool can be loaded here simply by changing `PATH_TO_CKPT` to point to a new .pb file.
#
# By default we use an "SSD with Mobilenet" model here. See the [detection model zoo](https://github.com/tensorflow/models/blob/master/object_detection/g3doc/detection_model_zoo.md) for a list of other models that can be run out-of-the-Box with varying speeds and accuracies.
# What model to download.
MODEL_NAME = 'new_graph' # change to whatever folder has the new graph
# MODEL_FILE = MODEL_NAME + '.tar.gz' # these lines not needed as we are using our own model
# 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('training','object_detection.pbtxt') # our labels are in training/object-detection.pbkt
NUM_CLASSES = 4 # we only are using one class at the moment (mask at the time of edit)
# ## Download Model
# opener = urllib.request.URLopener() # we don't need to download model since we have our own
# 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())
# ## 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='')
# ## Loading label map
# Label maps map indices to category names,so that when our convolution network predicts `5`,we kNow that this corresponds to `airplane`. Here we use internal utility functions,but anything that returns a dictionary mapping integers to appropriate string labels would be fine
# In[7]:
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)
# 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(1,2)] # adjust range for # of images in folder
# Size,in inches,of the output images.
IMAGE_SIZE = (12,8)
with detection_graph.as_default():
with tf.Session(graph=detection_graph) as sess:
i = 0
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,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,num_detections],Feed_dict={image_tensor: image_np_expanded})
# Visualization of the results of a detection.
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) # matplotlib is configured for command line only so we save the outputs instead
plt.savefig("outputs/detection_output{}.png".format(i)) # create an outputs folder for the images to be saved
i = i+1 # this was a quick fix for iteration,create a pull request if you'd like
我正在使用此脚本来测试我训练有素的模型。我正在尝试使用mobilenet张量流模型构建自定义对象检测模型。我在test_images文件夹中只有一个测试图像，但是它仍然给我一个内存不足错误和大约批处理大小的信息。我不认为该脚本中提到了批量大小。 我得到的错误是
2020-09-03 20:19:33.808425: I tensorflow/stream_executor/cuda/cuda_driver.cc:831] Failed to allocate 2.39G (2571278592 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory
2020-09-03 20:19:34.234979: W tensorflow/core/common_runtime/bfc_allocator.cc:305] Garbage collection: deallocate free memory regions (i.e.,allocations) so that we can re-allocate a larger region to avoid OOM due to memory fragmentation. If you see this message frequently,you are running near the threshold of the available device memory and re-allocation may incur great performance overhead. You may try smaller batch sizes to observe the performance impact. Set TF_ENABLE_GPU_GARBAGE_COLLECTION=false if you'd like to disable this feature
任何想法都可以解决。我现在尝试做一天半。谢谢。
解决方法
暂无找到可以解决该程序问题的有效方法，小编努力寻找整理中！
如果你已经找到好的解决方法，欢迎将解决方案带上本链接一起发送给小编。
小编邮箱:dio#foxmail.com (将#修改为@）