I am using tensorflow to detect custom images and i also trained a custom model for it but when i am running the detection scripts it is giving the following error
and this is my code-
import numpy as np
import argparse
import os
import tensorflow as tf
from PIL import Image
from io import BytesIO
import glob
import matplotlib.pyplot as plt
from object_detection.utils import ops as utils_ops
from object_detection.utils import label_map_util
from object_detection.utils import visualization_utils as vis_util
# patch tf1 into `utils.ops`
utils_ops.tf = tf.compat.v1
# Patch the location of gfile
tf.gfile = tf.io.gfile
def load_model(model_path):
model = tf.saved_model.load(model_path)
return model
def load_image_into_numpy_array(path):
"""Load an image from file into a numpy array.
Puts image into numpy array to feed into tensorflow graph.
Note that by convention we put it into a numpy array with shape
(height, width, channels), where channels=3 for RGB.
Args:
path: a file path (this can be local or on colossus)
Returns:
uint8 numpy array with shape (img_height, img_width, 3)
"""
img_data = tf.io.gfile.GFile(path, 'rb').read()
image = Image.open(BytesIO(img_data))
(im_width, im_height) = image.size
return np.array(image.getdata()).reshape(
(im_height, im_width, 3)).astype(np.uint8)
def run_inference_for_single_image(model, image):
# The input needs to be a tensor, convert it using `tf.convert_to_tensor`.
input_tensor = tf.convert_to_tensor(image)
# The model expects a batch of images, so add an axis with `tf.newaxis`.
input_tensor = input_tensor[tf.newaxis, ...]
# Run inference
output_dict = model(input_tensor)
# All outputs are batches tensors.
# Convert to numpy arrays, and take index [0] to remove the batch dimension.
# We're only interested in the first num_detections.
num_detections = int(output_dict.pop('num_detections'))
output_dict = {key: value[0, :num_detections].numpy()
for key, value in output_dict.items()}
output_dict['num_detections'] = num_detections
# detection_classes should be ints.
output_dict['detection_classes'] = output_dict['detection_classes'].astype(np.int64)
# Handle models with masks:
if 'detection_masks' in output_dict:
# Reframe the the bbox mask to the image size.
detection_masks_reframed = utils_ops.reframe_box_masks_to_image_masks(
output_dict['detection_masks'], output_dict['detection_boxes'],
image.shape[0], image.shape[1])
detection_masks_reframed = tf.cast(detection_masks_reframed > 0.5, tf.uint8)
output_dict['detection_masks_reframed'] = detection_masks_reframed.numpy()
return output_dict
def run_inference(model, category_index, image_path):
if os.path.isdir(image_path):
image_paths = []
for file_extension in ('*.png', '*jpg'):
image_paths.extend(glob.glob(os.path.join(image_path, file_extension)))
for i_path in image_paths:
image_np = load_image_into_numpy_array(i_path)
# Actual detection.
output_dict = run_inference_for_single_image(model, image_np)
# 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_reframed', None),
use_normalized_coordinates=True,
line_thickness=8)
plt.imshow(image_np)
plt.show()
else:
image_np = load_image_into_numpy_array(image_path)
# Actual detection.
output_dict = run_inference_for_single_image(model, image_np)
# 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_reframed', None),
use_normalized_coordinates=True,
line_thickness=8)
plt.imshow(image_np)
plt.show()
if _name_ == '_main_':
parser = argparse.ArgumentParser(description='Detect objects inside webcam videostream')
parser.add_argument('-m', '--model', type=str, required=True, help='Model Path')
parser.add_argument('-l', '--labelmap', type=str, required=True, help='Path to Labelmap')
parser.add_argument('-i', '--image_path', type=str, required=True, help='Path to image (or folder)')
args = parser.parse_args()
detection_model = load_model(args.model)
category_index = label_map_util.create_category_index_from_labelmap(args.labelmap, use_display_name=True)
run_inference(detection_model, category_index, args.image_path)
i got this code from tannergilberts github repo and have been watching a yt video to do this but i dont know why i am getting the valueerror and i am not able to fix it also someone pls help
Related
I am using TensorFlow to analyze some images, but when I run the program the images are overwritten and I don't know how to fix it, I should see several images as a result, but only one image appears that is being overwritten over and over again
import numpy as np
import os
import six.moves.urllib as urllib
import sys
import tarfile
import tensorflow as tf
import zipfile
import json
import time
import glob
from io import StringIO
from PIL import Image
import matplotlib.pyplot as plt
from utils import visualization_utils as vis_util
from utils import label_map_util
from multiprocessing.dummy import Pool as ThreadPool
import argparse, sys
parser = argparse.ArgumentParser()
parser.add_argument('--labels', help='Directorio a label_map.pbtxt', default ='D:/Downloads/deteccion_objetos-master/deteccion_objetos-master/configuracion/label_map.pbtxt')
parser.add_argument('--images', help='Directorio de las imagenes a procesar', default = 'D:/Downloads/deteccion_objetos-master/deteccion_objetos-master/img_pruebas')
parser.add_argument('--model', help='Directorio al modelo congelado', default = 'D:/Downloads/deteccion_objetos-master/deteccion_objetos-master/modelo_congelado')
args = parser.parse_args()
MAX_NUMBER_OF_BOXES = 30
MINIMUM_CONFIDENCE = 0.4
PATH_TO_LABELS = args.labels
PATH_TO_TEST_IMAGES_DIR = args.images
label_map = label_map_util.load_labelmap(PATH_TO_LABELS)
categories = label_map_util.convert_label_map_to_categories(label_map, max_num_classes=sys.maxsize, use_display_name=True)
CATEGORY_INDEX = label_map_util.create_category_index(categories)
# Path to frozen detection graph. This is the actual model that is used for the object detection.
MODEL_NAME = args.model
PATH_TO_CKPT = MODEL_NAME + '/frozen_inference_graph.pb'
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)
def detect_objects(image_path):
image = Image.open(image_path)
image_np = load_image_into_numpy_array(image)
image_np_expanded = np.expand_dims(image_np, axis=0)
(boxes, scores, classes, num) = sess.run([detection_boxes, detection_scores, detection_classes, num_detections], feed_dict={image_tensor: image_np_expanded})
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,
min_score_thresh=MINIMUM_CONFIDENCE,
use_normalized_coordinates=True,
line_thickness=8)
fig = plt.figure()
fig.set_size_inches(16, 9)
ax = plt.Axes(fig, [0., 0., 1., 1.])
ax.set_axis_off()
fig.add_axes(ax)
plt.imshow(image_np, aspect = 'auto')
plt.savefig('D:/Downloads/deteccion_objetos-master/deteccion_objetos-master/output/img_pruebas/img_pruebas'.format(image_path), dpi = 62)
print(boxes)
plt.close(fig)
# TEST_IMAGE_PATHS = [ os.path.join(PATH_TO_TEST_IMAGES_DIR, 'image-{}.jpg'.format(i)) for i in range(1, 4) ]
TEST_IMAGE_PATHS = glob.glob(os.path.join(PATH_TO_TEST_IMAGES_DIR, '*.jpeg'))
print(TEST_IMAGE_PATHS)
# Load model into memory
print('Loading model...')
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='')
print('detecting...')
with detection_graph.as_default():
with tf.Session(graph=detection_graph) as sess:
image_tensor = detection_graph.get_tensor_by_name('image_tensor:0')
detection_boxes = detection_graph.get_tensor_by_name('detection_boxes:0')
detection_scores = detection_graph.get_tensor_by_name('detection_scores:0')
detection_classes = detection_graph.get_tensor_by_name('detection_classes:0')
num_detections = detection_graph.get_tensor_by_name('num_detections:0')
for image_path in TEST_IMAGE_PATHS:
detect_objects(image_path)
As a result, many different images should appear but instead the images that are being overwritten appear as a loop until I finish analyzing the images
You should adapt your line
plt.savefig('D:/Downloads/deteccion_objetos-master/deteccion_objetos-master/output/img_pruebas/img_pruebas'.format(image_path), dpi = 62)
Now, whatever the value of image_path is, the plot is always created at D:/Downloads/deteccion_objetos-master/deteccion_objetos-master/output/img_pruebas/img_pruebas.
You probably want something like:
import os
plt.savefig('D:/Downloads/deteccion_objetos-master/deteccion_objetos-master/output/img_pruebas/img_pruebas/{}'.format(os.path.basename(image_path)))
I have trained a tensorflow model based upon EfficientDet D2 on my custom dataset(related to football(soccer)).
I tested the model on Images and it works as expected, but the performance for video is very low. I haved downloaded a video from youtube on 360p(the file size is 9MB) and video performance is very low, about 5-9 fps.
The code is as follows
# Necessary Imports
import os
import tensorflow as tf
from object_detection.utils import label_map_util
from object_detection.utils import visualization_utils as viz_utils
from object_detection.builders import model_builder
from object_detection.utils import config_util
# Load pipeline config and build a detection model
configs = config_util.get_configs_from_pipeline_file('Tensorflow/workspace/models/my_effi_d2/pipeline.config')
detection_model = model_builder.build(model_config=configs['model'], is_training=False)
# Restore checkpoint
ckpt = tf.compat.v2.train.Checkpoint(model=detection_model)
ckpt.restore(os.path.join('Tensorflow/workspace/models/my_effi_d2/', 'ckpt-4')).expect_partial()
#tf.function
def detect_fn(image):
image, shapes = detection_model.preprocess(image)
prediction_dict = detection_model.predict(image, shapes)
detections = detection_model.postprocess(prediction_dict, shapes)
return detections
category_index = label_map_util.create_category_index_from_labelmap('Tensorflow/workspace/annotations/label_map.pbtxt')
video = cv2.VideoCapture('target.mp4')
size = (640,480)
while True:
ret, frame = video.read()
image_np_expanded = np.expand_dims(frame, axis=0)
# image_np = np.array(frame)
# input_tensor = tf.convert_to_tensor(np.expand_dims(image_np, 0), dtype=tf.float32)
detections = detect_fn(input_tensor)
num_detections = int(detections.pop('num_detections'))
detections = {key: value[0, :num_detections].numpy()
for key, value in detections.items()}
detections['num_detections'] = num_detections
# detection_classes should be ints.
detections['detection_classes'] = detections['detection_classes'].astype(np.int64)
label_id_offset = 1
image_np_with_detections = image_np.copy()
viz_utils.visualize_boxes_and_labels_on_image_array(
image_np_with_detections,
detections['detection_boxes'],
detections['detection_classes']+label_id_offset,
detections['detection_scores'],
category_index,
use_normalized_coordinates=True,
max_boxes_to_draw=2,
min_score_thresh=.30,
agnostic_mode=False)
cv2.imshow('object detection', cv2.resize(image_np_with_detections,size))
if cv2.waitKey(10) & 0xFF == ord('q'):
break
if ret == False:
print("vid not Present")
break
video.release()
All Paths are relative to root folder.
Is there anyway to get bit more performance for detecting objects on video.
Additional info:
No gpu. My laptop is from 2015. I have trained the model on Google colab
Tensorflow 2.4.1 and Python 3.6.13(virtualenv)
I'm running the video test locally on my laptop. All the versions of tensorflow match with the google colab ones
I try to run the custom face detection model locally on ubuntu 20
but when I run the script I got this
Traceback (most recent call last):
File "webcam_detection.py", line 104, in <module>
cv2.imshow('object detection', cv2.resize(image_np, (1200,900)))
cv2.error: OpenCV(4.4.0) /tmp/pip-req-build-h2062vqd/opencv/modules/highgui/src/window.cpp:651: error: (-2:Unspecified error) The function is not implemented. Rebuild the library with Windows, GTK+ 2.x or Cocoa support. If you are on Ubuntu or Debian, install libgtk2.0-dev and pkg-config, then re-run cmake or configure script in function 'cvShowImage'
Here is my script:
######## Object Detection for Image #########
#
# Author: Khai Do
# Date: 9/3/2019
## Some parts of the code is copied from Tensorflow object detection
## https://github.com/tensorflow/models/blob/master/research/object_detection/object_detection_tutorial.ipynb
# Import libraries
import numpy as np
import os
import six.moves.urllib as urllib
import sys
import tarfile
import zipfile
import cv2
import tensorflow.compat.v1 as tf
from collections import defaultdict
from io import StringIO
from matplotlib import pyplot as plt
from PIL import Image
from utils import label_map_util
from utils import visualization_utils as vis_util
# Define the video stream
cap = cv2.VideoCapture(0) # Change only if you have more than one webcams
# What model
directPath = os.getcwd()
print(directPath)
MODEL_NAME = 'fine_tune_graph'
# 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', 'object-detection.pbtxt')
# Number of classes to detect
NUM_CLASSES = 1
# 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_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)
# Helper code
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
with detection_graph.as_default():
with tf.Session(graph=detection_graph) as sess:
while True:
# Read frame from camera
ret, image_np = cap.read()
# Expand dimensions since the model expects images to have shape: [1, None, None, 3]
image_np_expanded = np.expand_dims(image_np, axis=0)
# Extract image tensor
image_tensor = detection_graph.get_tensor_by_name('image_tensor:0')
# Extract detection boxes
boxes = detection_graph.get_tensor_by_name('detection_boxes:0')
# Extract detection scores
scores = detection_graph.get_tensor_by_name('detection_scores:0')
# Extract detection classes
classes = detection_graph.get_tensor_by_name('detection_classes:0')
# Extract number of detectionsd
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})
# 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)
# Display output
cv2.imshow('object detection', cv2.resize(image_np, (1200,900)))
if cv2.waitKey(25) & 0xFF == ord('q'):
cv2.destroyAllWindows()
break
Extract the detected object along with the bounding box and save it as an image on my disk.
I have taken the code of Edge Electronics and successfully trained and tested the model. I got the bounding box on my images.
import os
import cv2
import numpy as np
import tensorflow as tf
import sys
from glob import glob
import glob
import csv
from PIL import Image
import json
sys.path.append("..")
# Import utilites
from utils import label_map_util
from utils import visualization_utils as vis_util
MODEL_NAME = 'inference_graph'
CWD_PATH = os.getcwd()
PATH_TO_CKPT = os.path.join(CWD_PATH,MODEL_NAME,'frozen_inference_graph.pb')
PATH_TO_LABELS = os.path.join(CWD_PATH,'training','labelmap.pbtxt')
PATH_TO_IMAGE = list(glob.glob("C:\\new_multi_cat\\models\\research\\object_detection\\img_test\\*jpeg"))
NUM_CLASSES = 3
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)
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='')
sess = tf.Session(graph=detection_graph)
image_tensor = detection_graph.get_tensor_by_name('image_tensor:0')
detection_boxes = detection_graph.get_tensor_by_name('detection_boxes:0')
detection_scores = detection_graph.get_tensor_by_name('detection_scores:0')
detection_classes = detection_graph.get_tensor_by_name('detection_classes:0')
num_detections = detection_graph.get_tensor_by_name('num_detections:0')
for paths in range(len(PATH_TO_IMAGE)):
image = cv2.imread(PATH_TO_IMAGE[paths])
image_expanded = np.expand_dims(image, axis=0)
(boxes, scores, classes, num) = sess.run([detection_boxes, detection_scores, detection_classes, num_detections],feed_dict={image_tensor: image_expanded})
vis_util.visualize_boxes_and_labels_on_image_array(
image,
np.squeeze(boxes),
np.squeeze(classes).astype(np.int32),
np.squeeze(scores),
category_index,
use_normalized_coordinates=True,
line_thickness=4,
min_score_thresh=0.80)
white_bg_img = 255*np.ones(PATH_TO_IMAGE[paths].shape, np.uint8)
vis_util.draw_bounding_boxes_on_image(
white_bg_img ,
np.squeeze(boxes),
color='red',
thickness=4)
cv2.imwrite("bounding_boxes.jpg", white_bg_img)
boxes = np.squeeze(boxes)
for i in range(len(boxes)):
box[0]=box[0]*height
box[1]=box[1]*width
box[2]=box[2]*height
box[3]=box[3]*width
roi = image[box[0]:box[2],box[1]:box[3]].copy()
cv2.imwrite("box_{}.jpg".format(str(i)), roi)
This is the error I am getting:
Traceback (most recent call last): File "objd_1.py", line
75, in <module>
white_bg_img = 255*np.ones(PATH_TO_IMAGE[paths].shape, np.uint8) AttributeError: 'str' object has no attribute 'shape'
I have searched a lot but not able to identify what is wrong in my code. Why am I not able to extract the detected region as an image?
You try to take shape from a file name instead of the image. Replace
white_bg_img = 255*np.ones(PATH_TO_IMAGE[paths].shape, np.uint8)
to
white_bg_img = 255*np.ones(image.shape, np.uint8)
Edit: corrected code
import os
import cv2
import numpy as np
import tensorflow as tf
import sys
from glob import glob
import glob
import csv
from PIL import Image
import json
sys.path.append("..")
# Import utilites
from utils import label_map_util
from utils import visualization_utils as vis_util
MODEL_NAME = 'inference_graph'
CWD_PATH = os.getcwd()
PATH_TO_CKPT = os.path.join(CWD_PATH,MODEL_NAME,'frozen_inference_graph.pb')
PATH_TO_LABELS = os.path.join(CWD_PATH,'training','labelmap.pbtxt')
PATH_TO_IMAGE = list(glob.glob("C:\\new_multi_cat\\models\\research\\object_detection\\img_test\\*jpeg"))
NUM_CLASSES = 3
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)
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='')
sess = tf.Session(graph=detection_graph)
image_tensor = detection_graph.get_tensor_by_name('image_tensor:0')
detection_boxes = detection_graph.get_tensor_by_name('detection_boxes:0')
detection_scores = detection_graph.get_tensor_by_name('detection_scores:0')
detection_classes = detection_graph.get_tensor_by_name('detection_classes:0')
num_detections = detection_graph.get_tensor_by_name('num_detections:0')
for paths in range(len(PATH_TO_IMAGE)):
image = cv2.imread(PATH_TO_IMAGE[paths])
image_expanded = np.expand_dims(image, axis=0)
(boxes, scores, classes, num) = sess.run([detection_boxes, detection_scores, detection_classes, num_detections],feed_dict={image_tensor: image_expanded})
vis_util.visualize_boxes_and_labels_on_image_array(
image,
np.squeeze(boxes),
np.squeeze(classes).astype(np.int32),
np.squeeze(scores),
category_index,
use_normalized_coordinates=True,
line_thickness=4,
min_score_thresh=0.80)
white_bg_img = 255*np.ones(image.shape, np.uint8)
vis_util.draw_bounding_boxes_on_image_array(
white_bg_img ,
np.squeeze(boxes),
color='red',
thickness=4)
cv2.imwrite("bounding_boxes.jpg", white_bg_img)
boxes = np.squeeze(boxes)
for i in range(len(boxes)):
box[0]=box[0]*height
box[1]=box[1]*width
box[2]=box[2]*height
box[3]=box[3]*width
roi = image[box[0]:box[2],box[1]:box[3]].copy()
cv2.imwrite("box_{}.jpg".format(str(i)), roi)
i am working on image detection model and following the steps from below link
https://pythonprogramming.net/training-custom-objects-tensorflow-object-detection-api-tutorial/?completed=/creating-tfrecord-files-tensorflow-object-detection-api-tutorial/
Though, I have trained my model and also downloaded the frozen_inference_graph.pb but while compiling it in jupyter notebook I am facing the error "
"graph." % (repr(name), repr(op_name)))
KeyError: "The name 'image_tensor:0' refers to a Tensor which does not exist. The operation, 'image_tensor', does not exist in the graph."
"
please advise as i am not able to find the solution.
below is the code i am using :
import numpy as np
import os
import six.moves.urllib as urllib
import sys
import tarfile
import tensorflow as tf
import zipfile
import io
import pandas as pd
sys.path.append("C:\\...\\tensorflow\\models\\research\\")
sys.path.append("C:\\...\\tensorflow\\models\\research\\object_detection\\utils")
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
from object_detection.utils import dataset_util
if StrictVersion(tf.__version__) < StrictVersion('1.9.0'):
raise ImportError('Please upgrade your TensorFlow installation to v1.9.* or later!')
# This is needed to display the images.
%matplotlib inline
from utils import label_map_util
from utils import visualization_utils as vis_util
MODEL_NAME = 'Trained_inference_graph'
# Path to frozen detection graph. This is the actual model that is used for the object detection.
PATH_TO_FROZEN_GRAPH = 'C:\\...\\Tensorflow\\models\\research\\object_detection\\inference_graph\\frozen_inference_graph.pb'
# List of the strings that is used to add correct label for each box.
PATH_TO_LABELS = 'C:\\...\\Tensorflow\\models\\research\\object_detection\\Training\\label_map.pbtxt'
Num_classes = 5
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)
PATH_TO_TEST_IMAGES_DIR = 'C:\\...\\Tensorflow\\models\\research\\object_detection\\test_images'
TEST_IMAGE_PATHS = [ os.path.join(PATH_TO_TEST_IMAGES_DIR, 'image{}.jpg'.format(i)) for i in range(3, 7) ]
# Size, in inches, of the output images.
IMAGE_SIZE = (12, 8)
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)
plt.imshow(image_np)
ERROR
KeyError
Traceback (most recent call last) <ipython-input-66-b19082c2666b> in <module>
7 image_np_expanded = np.expand_dims(image_np, axis=0)
8 # Actual detection.
----> 9 output_dict = run_inference_for_single_image(image_np, detection_graph)
10 # Visualization of the results of a detection.
11 vis_util.visualize_boxes_and_labels_on_image_array(
<ipython-input-65-f22e65a052c1> in run_inference_for_single_image(image, graph)
29 tensor_dict['detection_masks'] = tf.expand_dims(
30 detection_masks_reframed, 0)
---> 31 image_tensor = tf.get_default_graph().get_tensor_by_name('image_tensor:0')
32
33 # Run inference
D:\anaconda\envs\tensorflow_cpu\lib\site-packages\tensorflow\python\framework\ops.py in get_tensor_by_name(self, name) 3664 raise TypeError("Tensor names are strings (or similar), not %s." % 3665 type(name).__name__)
-> 3666 return self.as_graph_element(name, allow_tensor=True, allow_operation=False) 3667 3668 def
_get_tensor_by_tf_output(self, tf_output):
D:\anaconda\envs\tensorflow_cpu\lib\site-packages\tensorflow\python\framework\ops.py in as_graph_element(self, obj, allow_tensor, allow_operation) 3488 3489 with self._lock:
-> 3490 return self._as_graph_element_locked(obj, allow_tensor, allow_operation) 3491 3492 def _as_graph_element_locked(self, obj, allow_tensor, allow_operation):
D:\anaconda\envs\tensorflow_cpu\lib\site-packages\tensorflow\python\framework\ops.py in _as_graph_element_locked(self, obj, allow_tensor, allow_operation) 3530 raise KeyError("The name %s refers to a Tensor which does not " 3531 "exist. The operation, %s, does not exist in the "
-> 3532 "graph." % (repr(name), repr(op_name))) 3533 try: 3534 return op.outputs[out_n]
KeyError: "The name 'image_tensor:0' refers to a Tensor which does not exist. The operation, 'image_tensor', does not exist in the graph."