I can't find why this plt.show() is not working. I'm using the code given in Tensorflow:
https://tensorflow-object-detection-api-tutorial.readthedocs.io/en/latest/auto_examples/plot_object_detection_saved_model.html
I found solutions saying that I should use plt.show(block=false) and add plt.pause(5) but it didn't work. Please help.
After running the code I get:
Running inference for image... Done, but it doesn't show any image.
# 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(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)
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'],
detections['detection_scores'],
category_index,
use_normalized_coordinates=True,
max_boxes_to_draw=200,
min_score_thresh=.30,
agnostic_mode=False)
plt.figure()
plt.imshow(image_np_with_detections)
print('Done')
plt.show()
Related
I'm trying to write code using Tensorflow from tutorial for detecting objects with a camera, I want the detected object to print once as soon as it is detected.
cap = cv2.VideoCapture(0)
width = int(cap.get(cv2.CAP_PROP_FRAME_WIDTH))
height = int(cap.get(cv2.CAP_PROP_FRAME_HEIGHT))
while cap.isOpened():
ret, frame = cap.read()
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=5,
min_score_thresh=.8,
agnostic_mode=False)
cv2.imshow('object detection', cv2.resize(image_np_with_detections, (800, 600)))
if cv2.waitKey(10) & 0xFF == ord('q'):
cap.release()
cv2.destroyAllWindows()
break
Here are the names of my labels that have been learned
labels = [{'name':'phone', 'id':1}, {'name':'headphones', 'id':2}, {'name':'glasses', 'id':3}, {'name':'mug', 'id':4}]
with open(files['LABELMAP'], 'w') as f:
for label in labels:
f.write('item { \n')
f.write('\tname:\'{}\'\n'.format(label['name']))
f.write('\tid:{}\n'.format(label['id']))
f.write('}\n')
I'm trying to print "test" while detecting an object with leable id 1. The word test is printed non-stop :(
if 1 in detections['detection_classes']:
print("test")
cap = cv2.VideoCapture(0)
width = int(cap.get(cv2.CAP_PROP_FRAME_WIDTH))
height = int(cap.get(cv2.CAP_PROP_FRAME_HEIGHT))
while cap.isOpened():
ret, frame = cap.read()
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=5,
min_score_thresh=.8,
agnostic_mode=False)
cv2.imshow('object detection', cv2.resize(image_np_with_detections, (800, 600)))
if cv2.waitKey(10) & 0xFF == ord('q'):
cap.release()
cv2.destroyAllWindows()
break
I am interested in printing the name id actually gets detected on the screen.
this is my code for train model for object detection. i used google colab. using ssd_mobilenet_v2_fpnlite_320x320_coco17_tpu-8.config. i have an error when try to detect image. its not detect my picture but always show the bounding box. bounding box is not moving but the accuracy changed
%cd /content/models/research/object_detection
#Loading the saved_model
import tensorflow as tf
import time
import numpy as np
import warnings
warnings.filterwarnings('ignore')
from PIL import Image
from google.colab.patches import cv2_imshow
from object_detection.utils import label_map_util
from object_detection.utils import visualization_utils as viz_utils
IMAGE_SIZE = (12, 8) # Output display size as you want
import matplotlib.pyplot as plt
PATH_TO_SAVED_MODEL="/mydrive/customTF2/data/inference_graph/saved_model"
print('Loading model...', end='')
# Load saved model and build the detection function
detect_fn=tf.saved_model.load(PATH_TO_SAVED_MODEL)
print('Done!')
#Loading the label_map
category_index=label_map_util.create_category_index_from_labelmap("/mydrive/customTF2/data/label_map.pbtxt",use_display_name=True)
#category_index=label_map_util.create_category_index_from_labelmap([path_to_label_map],use_display_name=True)
def load_image_into_numpy_array(path):
return np.array(Image.open(path))
image_path = "/mydrive/papaya_test_images/pp.jpg"
#print('Running inference for {}... '.format(image_path), end='')
image_np = load_image_into_numpy_array(image_path)
# The input needs to be a tensor, convert it using `tf.convert_to_tensor`.
input_tensor = tf.convert_to_tensor(image_np)
# The model expects a batch of images, so add an axis with `tf.newaxis`.
input_tensor = input_tensor[tf.newaxis, ...]
detections = detect_fn(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(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)
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'],
detections['detection_scores'],
category_index,
use_normalized_coordinates=True,
max_boxes_to_draw=200,
min_score_thresh=.07, # Adjust this value to set the minimum probability boxes to be classified as True
agnostic_mode=False)
%matplotlib inline
plt.figure(figsize=IMAGE_SIZE, dpi=200)
plt.axis("off")
plt.imshow(image_np_with_detections)
plt.show()
i use tutorial from edje electronics with Faster R-CNN and it's works
but i want to improve it. i want to count the object
the question is....... how can i remove the percentage of accuracy and replace it with number of counted bounding box.
i don't know which one i must add and remove it to counting the bounding box
here is the code
import os
import cv2
import numpy as np
import tensorflow as tf
import sys
sys.path.append("..")
from utils import label_map_util
from utils import visualization_utils as vis_util
MODEL_NAME = 'inference_graph'
VIDEO_NAME = 'animal.mov'
# 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,'training','labelmap.pbtxt')
PATH_TO_VIDEO = os.path.join(CWD_PATH,VIDEO_NAME)
NUM_CLASSES = 6
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)
# Define input and output tensors (i.e. data) for the object detection classifier
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')
video = cv2.VideoCapture(PATH_TO_VIDEO)
while(video.isOpened()):
ret, frame = video.read()
frame_rgb = cv2.cvtColor(frame, cv2.COLOR_BGR2RGB)
frame_expanded = np.expand_dims(frame_rgb, axis=0)
(boxes, scores, classes, num) = sess.run(
[detection_boxes, detection_scores, detection_classes, num_detections],
feed_dict={image_tensor: frame_expanded})
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=0.60)
cv2.imshow('Object detector', frame)
if cv2.waitKey(1) == ord('q'):
break
video.release()
cv2.destroyAllWindows()
You have to modify the visualize_boxes_and_labels_on_image_array() function in utils/visualization_utils.py to remove the conf score display and show length of boxes array
I have trained a faster rcnn model using the Tensorflow object detection API and am using this inference script with my frozen graph:
https://github.com/tensorflow/models/blob/master/research/object_detection/object_detection_tutorial.ipynb
I intend to use it for object tracking in videos, but inference using this script is very slow since it only processes one image at a time instead of a batch of images. Is there any way to do inference on a batch of images at once ? The relevant inference function is here, I am wondering how to modify it to work with a stack of 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
Instead of passing just one numpy array of the size (1, image_width, image_heigt, 3) you can pass a numpy array with your image batch of the size (batch_size, image_width, image_heigt, 3) to the sess.run command:
output_dict = sess.run(tensor_dict, feed_dict={image_tensor: image_batch})
The output_dict will be slightly different then before, still haven't figured out how exactly. Maybe someone can help furthermore?
Edit
It seems that the output_dict gets another index which corresponds to the image number in your batch. So you'll find the boxes for a certain image in:
output_dict['detection_boxes'][image_counter]
Edit2
For some reason this won't work with Mask RCNN...
If you run export_inference_graph.py, you should be able to input batches of images by default as it sets the image_tensor shape to [None, None, None, 3].
python object_detection/export_inference_graph.py \
--input_type image_tensor \
--pipeline_config_path ${PIPELINE_CONFIG_PATH} \
--trained_checkpoint_prefix ${TRAIN_PATH} \
--output_directory output_inference_graph.pb