We Keep Coding

Tensorflow Objection Detection slow on Video

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

Custome object detection on webcame

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

google.protobuf.message.DecodeError: Wrong wire type in tag

I am building project on detection of floating garbage in water using raspberrypi4b. My model was trained on faster_rcnn. I am using tensorflow version 1.14. I followed https://github.com/EdjeElectronics/TensorFlow-Object-Detection-on-the-Raspberry-Pi this tutorial.This is my code.
import os
import cv2
import numpy as np
from picamera.array import PiRGBArray
from picamera import PiCamera
import tensorflow as tf
import argparse
import sys
# Set up camera constants
IM_WIDTH = 1280
IM_HEIGHT = 720
#IM_WIDTH = 640 Use smaller resolution for
#IM_HEIGHT = 480 slightly faster framerate
# Select camera type (if user enters --usbcam when calling this script,
# a USB webcam will be used)
camera_type = 'picamera'
parser = argparse.ArgumentParser()
parser.add_argument('--usbcam', help='Use a USB webcam instead of picamera',
action='store_true')
args = parser.parse_args()
if args.usbcam:
camera_type = 'usb'
# This is needed since the working directory is the object_detection folder.
sys.path.append('..')
# Import utilites
from utils import label_map_util
from utils import visualization_utils as vis_util
# Name of the directory containing the object detection module we're using
MODEL_NAME = 'litter'
# Grab path to current working directory
CWD_PATH = os.getcwd()
# Path to frozen detection graph .pb file, which contains the model that is used
# for object detection.
PATH_TO_CKPT = os.path.join(CWD_PATH,MODEL_NAME,'frozen_inference_graph.pb')
# Path to label map file
PATH_TO_LABELS = os.path.join(CWD_PATH,MODEL_NAME,'label_map.pbtxt')
# Number of classes the object detector can identify
NUM_CLASSES = 1
## Load the label map.
# Label maps map indices to category names, so that when the 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
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)
# Load the 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='')
sess = tf.Session(graph=detection_graph)
# Define input and output tensors (i.e. data) for the object detection classifier
# Input tensor is the image
image_tensor = detection_graph.get_tensor_by_name('image_tensor:0')
# Output tensors are the detection boxes, scores, and classes
# Each box represents a part of the image where a particular object was detected
detection_boxes = detection_graph.get_tensor_by_name('detection_boxes:0')
# Each score represents level of confidence for each of the objects.
# The score is shown on the result image, together with the class label.
detection_scores = detection_graph.get_tensor_by_name('detection_scores:0')
detection_classes = detection_graph.get_tensor_by_name('detection_classes:0')
# Number of objects detected
num_detections = detection_graph.get_tensor_by_name('num_detections:0')
# Initialize frame rate calculation
frame_rate_calc = 1
freq = cv2.getTickFrequency()
font = cv2.FONT_HERSHEY_SIMPLEX
# Initialize camera and perform object detection.
# The camera has to be set up and used differently depending on if it's a
# Picamera or USB webcam.
# I know this is ugly, but I basically copy+pasted the code for the object
# detection loop twice, and made one work for Picamera and the other work
# for USB.
### Picamera ###
if camera_type == 'picamera':
# Initialize Picamera and grab reference to the raw capture
camera = PiCamera()
camera.resolution = (IM_WIDTH,IM_HEIGHT)
camera.framerate = 10
rawCapture = PiRGBArray(camera, size=(IM_WIDTH,IM_HEIGHT))
rawCapture.truncate(0)
for frame1 in camera.capture_continuous(rawCapture, format="bgr",use_video_port=True):
t1 = cv2.getTickCount()
# Acquire frame and expand frame dimensions to have shape: [1, None, None, 3]
# i.e. a single-column array, where each item in the column has the pixel RGB value
frame = np.copy(frame1.array)
frame.setflags(write=1)
frame_rgb = cv2.cvtColor(frame, cv2.COLOR_BGR2RGB)
frame_expanded = np.expand_dims(frame_rgb, axis=0)
# Perform the actual detection by running the model with the image as input
(boxes, scores, classes, num) = sess.run(
[detection_boxes, detection_scores, detection_classes, num_detections],
feed_dict={image_tensor: frame_expanded})
# Draw the results of the detection (aka 'visulaize the results')
vis_util.visualize_boxes_and_labels_on_image_array(
frame,
np.squeeze(boxes),
np.squeeze(classes).astype(np.int32),
np.squeeze(scores),
category_index,
use_normalized_coordinates=True,
line_thickness=8,
min_score_thresh=0.40)
cv2.putText(frame,"FPS: {0:.2f}".format(frame_rate_calc),(30,50),font,1,(255,255,0),2,cv2.LINE_AA)
# All the results have been drawn on the frame, so it's time to display it.
cv2.imshow('Object detector', frame)
t2 = cv2.getTickCount()
time1 = (t2-t1)/freq
frame_rate_calc = 1/time1
# Press 'q' to quit
if cv2.waitKey(1) == ord('q'):
break
rawCapture.truncate(0)
camera.close()
### USB webcam ###
elif camera_type == 'usb':
# Initialize USB webcam feed
camera = cv2.VideoCapture(0)
ret = camera.set(3,IM_WIDTH)
ret = camera.set(4,IM_HEIGHT)
while(True):
t1 = cv2.getTickCount()
# Acquire frame and expand frame dimensions to have shape: [1, None, None, 3]
# i.e. a single-column array, where each item in the column has the pixel RGB value
ret, frame = camera.read()
frame_rgb = cv2.cvtColor(frame, cv2.COLOR_BGR2RGB)
frame_expanded = np.expand_dims(frame_rgb, axis=0)
# Perform the actual detection by running the model with the image as input
(boxes, scores, classes, num) = sess.run(
[detection_boxes, detection_scores, detection_classes, num_detections],
feed_dict={image_tensor: frame_expanded})
# Draw the results of the detection (aka 'visulaize the results')
vis_util.visualize_boxes_and_labels_on_image_array(
frame,
np.squeeze(boxes),
np.squeeze(classes).astype(np.int32),
np.squeeze(scores),
category_index,
use_normalized_coordinates=True,
line_thickness=8,
min_score_thresh=0.85)
cv2.putText(frame,"FPS: {0:.2f}".format(frame_rate_calc),(30,50),font,1,(255,255,0),2,cv2.LINE_AA)
# All the results have been drawn on the frame, so it's time to display it.
cv2.imshow('Object detector', frame)
t2 = cv2.getTickCount()
time1 = (t2-t1)/freq
frame_rate_calc = 1/time1
# Press 'q' to quit
if cv2.waitKey(1) == ord('q'):
break
camera.release()
cv2.destroyAllWindows()
This is the error I am getting:
Traceback (most recent call last):
File "litter.py", line 85, in <module>
od_graph_def.ParseFromString(serialized_graph)
File "/home/pi/.local/lib/python3.7/site-packages/google/protobuf/message.py", line 187, in
ParseFromString
return self.MergeFromString(serialized)
File "/home/pi/.local/lib/python3.7/site-packages/google/protobuf/internal/python_message.py", line
1127, in MergeFromString
if self._InternalParse(serialized, 0, length) != length:
File "/home/pi/.local/lib/python3.7/site-packages/google/protobuf/internal/python_message.py", line
1181, in InternalParse
buffer, new_pos, wire_type) # pylint: disable=protected-access
File "/home/pi/.local/lib/python3.7/site-packages/google/protobuf/internal/decoder.py", line 973, in
_DecodeUnknownField
raise _DecodeError('Wrong wire type in tag.')
google.protobuf.message.DecodeError: Wrong wire type in tag.

Extracting bounding box as .jpg

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)

KeyError: "The name 'image_tensor:0'

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."