We Keep Coding

Value error in tensorflow custom image detection

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

Tensorflow object detection slow inference time

I need to measure the inference time for a TF1 object detection model. I have developed the following code by looking at various tutorials and at the official Tensorflow Github repository.
import numpy as np
import os
import sys
import tensorflow as tf
import time
from collections import defaultdict
from matplotlib import pyplot as plt
from PIL import Image
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
%matplotlib inline
os.environ['TF_CPP_MIN_LOG_LEVEL'] = '2' # Suppress TensorFlow logging (1)
import pathlib
tf.get_logger().setLevel('ERROR') # Suppress TensorFlow logging (2)
# Enable GPU dynamic memory allocation
gpus = tf.config.experimental.list_physical_devices('GPU')
for gpu in gpus:
tf.config.experimental.set_memory_growth(gpu, True)
# Initialize tf.Graph()
detection_graph = tf.Graph()
with detection_graph.as_default():
od_graph_def = tf.GraphDef()
with tf.gfile.GFile('/home/luigi/Downloads/SSD_MobileNet_300000/frozen_inference_graph.pb', 'rb') as fid:
serialized_graph = fid.read()
od_graph_def.ParseFromString(serialized_graph)
tf.import_graph_def(od_graph_def, name='')
# Loads labels
label_map = label_map_util.load_labelmap('/home/luigi/Downloads/DOTA-3/train/Objects_label_map.pbtxt')
categories = label_map_util.convert_label_map_to_categories(label_map, max_num_classes=15, use_display_name=True)
category_index = label_map_util.create_category_index(categories)
# Run Inference and populates results in a dict.
def run_inference(graph, image):
with graph.as_default():
with tf.Session() as sess:
ops = tf.get_default_graph().get_operations()
all_tensor_names = [output.name for op in ops for output in op.outputs]
tensor_dict = {}
tensor_keys = ['num_detections', 'detection_boxes', 'detection_scores', 'detection_classes']
for key in tensor_keys:
tensor_name = key + ':0'
if tensor_name in all_tensor_names:
tensor_dict[key] = tf.get_default_graph().get_tensor_by_name(tensor_name)
# Actual inference.
image_tensor = tf.get_default_graph().get_tensor_by_name('image_tensor:0')
output_dict = sess.run(tensor_dict, feed_dict={image_tensor: np.expand_dims(image, 0)})
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]
return output_dict
path = '/home/luigi/Downloads/test/'
#[os.path.join('/home/luigi/Downloads/test/', image_path)]
for image_path in os.listdir(path):
input_path = os.path.join(path, image_path)
print('Evaluating:', input_path)
image = Image.open(input_path)
img_width, img_height = image.size
image_np = np.array(image.getdata()).reshape((img_height, img_width, 3)).astype(np.uint8)
# Run inference.
start = time.time()
output_dict = run_inference(detection_graph, image_np)
end = time.time()
# 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,
use_normalized_coordinates=True,
line_thickness=8)
plt.figure(figsize=(12, 8))
plt.imshow(image_np)
print("Prediction time for: " + image_path + " " + str(end-start))
I think that for some reason related to the code above, the inference times that I get are slow and could be improved. I have been looking online but haven't had any luck finding anything useful. Any tips?

How to fix my results are overwritten with tensorflow and matplotlib?

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)))

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)