I'm learning about MobileNet thesedays and i'm new to tensorflow. After training with ssd-mobilenet model,i got checkpoint file , .meta file , graph.pbtxt file and so on. When I try to predict with these files, i can't get the output such as box_pred, classs_scores...
Then I found predict demo code used .pb file to load graph ,and used "get_tensor_by_name" to get output, but Ｉ don't have .pb file. So, how can I predict an image with .meta and ckpt files ?
BTW, here is predict demon main code:
import numpy as np
import os
import six.moves.urllib as urllib
import sys
import tarfile
import tensorflow as tf
import zipfile
import time
from collections import defaultdict
from io import StringIO
from matplotlib import pyplot as plt
from PIL import Image
#%matplotlib inline
# This is needed since the notebook is stored in the object_detection folder.
sys.path.append("..")
from utils import label_map_util
from utils import visualization_utils as vis_util
# What model to download.
MODEL_NAME = 'ssd_mobilenet_v1_coco_11_06_2017'
MODEL_FILE = MODEL_NAME + '.tar.gz'
DOWNLOAD_BASE = 'http://download.tensorflow.org/models/object_detection/'
# Path to frozen detection graph. This is the actual model that is used for the object detection.
PATH_TO_CKPT = MODEL_NAME + '/frozen_inference_graph.pb'
# List of the strings that is used to add correct label for each box.
PATH_TO_LABELS = os.path.join('data', 'mscoco_label_map.pbtxt')
NUM_CLASSES = 90
#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='')
#load 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)
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
# For the sake of simplicity we will use only 2 images:
# image1.jpg
# image2.jpg
# If you want to test the code with your images, just add path to the images to the TEST_IMAGE_PATHS.
PATH_TO_TEST_IMAGES_DIR = 'test_images'
TEST_IMAGE_PATHS = [ os.path.join(PATH_TO_TEST_IMAGES_DIR, 'image{}.jpg'.format(i)) for i in range(1, 3) ]
# Size, in inches, of the output images.
IMAGE_SIZE = (12, 8)
with detection_graph.as_default():
with tf.Session(graph=detection_graph) as sess:
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)
image_tensor = detection_graph.get_tensor_by_name('image_tensor:0')
# Each box represents a part of the image where a particular object was detected.
boxes = detection_graph.get_tensor_by_name('detection_boxes:0')
# Each score represent how level of confidence for each of the objects.
# Score is shown on the result image, together with the class label.
scores = detection_graph.get_tensor_by_name('detection_scores:0')
classes = detection_graph.get_tensor_by_name('detection_classes:0')
num_detections = detection_graph.get_tensor_by_name('num_detections:0')
# Actual detection.
(boxes, scores, classes, num_detections) = sess.run(
[boxes, scores, classes, num_detections],
feed_dict={image_tensor: image_np_expanded})
You should load the graph using tf.train.import_meta_graph() and then get the tensors using get_tensor_by_name(). You can try:
model_path = "model.ckpt"
detection_graph = tf.Graph()
with tf.Session(graph=detection_graph) as sess:
# Load the graph with the trained states
loader = tf.train.import_meta_graph(model_path+'.meta')
loader.restore(sess, model_path)
# Get the tensors by their variable name
image_tensor = detection_graph.get_tensor_by_name('image_tensor:0')
boxes = detection_graph.get_tensor_by_name('detection_boxes:0')
scores = detection_graph.get_tensor_by_name('detection_scores:0')
...
# Make predictions
_boxes, _scores = sess.run([boxes, scores], feed_dict={image_tensor: image_np_expanded})
Just for those who have the problem like wu ruize and CoupDeMistral:
But I got this error: "The name 'image_tensor:0' refers to a Tensor which does not exist. The operation, 'image_tensor', does not exist in the graph."
You need to name your tensor first before using detection_graph.get_tensor_by_name.
For example, something like this:
accuracy = tf.reduce_mean(tf.cast(correct_pred, tf.float32),name='accuracy')
Notice that the tensor above has been named as 'accuracy'.
After that you can enjoy the restore operation by:
detection_graph.get_tensor_by_name('accuracy:0')
Have fun now :P!
Related
I am new to TensorFlow, I am getting this valuing error for some images while on other images works fine. Is there anything wrong with the code?
import numpy as np
import os
import six.moves.urllib as urllib
import sys
import tarfile
import tensorflow.compat.v1 as tf
tf.disable_v2_behavior()
import zipfile
from collections import defaultdict
from io import StringIO
from matplotlib import pyplot as plt
from PIL import Image
from object_detection.utils import label_map_util
from object_detection.utils import visualization_utils as vis_util
# This is needed since the notebook is stored in the object_detection folder.
sys.path.append("..")
MODEL_NAME = 'new_graph' # change to whatever folder has the new graph
# MODEL_FILE = MODEL_NAME + '.tar.gz' # these lines not needed as we are using our own model
# DOWNLOAD_BASE = 'http://download.tensorflow.org/models/object_detection/'
PATH_TO_CKPT = MODEL_NAME + '/frozen_inference_graph.pb'
# List of the strings that is used to add correct label for each box.
PATH_TO_LABELS = os.path.join('training', 'object-detection.pbtxt') # our labels are in training/object-detection.pbkt
NUM_CLASSES = 3
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='')
label_map = label_map_util.load_labelmap(PATH_TO_LABELS)
categories = label_map_util.convert_label_map_to_categories(label_map, max_num_classes=NUM_CLASSES, use_display_name=True)
category_index = label_map_util.create_category_index(categories)
def load_image_into_numpy_array(image):
(im_width, im_height) = image.size
return np.array(image.getdata()).reshape(
(im_height, im_width, 4)).astype(np.uint8)
PATH_TO_TEST_IMAGES_DIR = 'test_images'
TEST_IMAGE_PATHS = [os.path.join(PATH_TO_TEST_IMAGES_DIR, 'image{}.png'.format(i)) for i in range(1, 8)]
# adjust range for # of images in folder
# Size, in inches, of the output images.
IMAGE_SIZE = (12, 8)
with detection_graph.as_default():
with tf.Session(graph=detection_graph) as sess:
i = 0
for image_path in TEST_IMAGE_PATHS:
image = Image.open(image_path)
# the array based representation of the image will be used later in order to prepare the
# result image with boxes and labels on it.
# # image = np.reshape(image, ())
# print(image)
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)
image_tensor = detection_graph.get_tensor_by_name('image_tensor:0')
# Each box represents a part of the image where a particular object was detected.
boxes = detection_graph.get_tensor_by_name('detection_boxes:0')
# Each score represent how level of confidence for each of the objects.
# Score is shown on the result image, together with the class label.
scores = detection_graph.get_tensor_by_name('detection_scores:0')
classes = detection_graph.get_tensor_by_name('detection_classes:0')
num_detections = detection_graph.get_tensor_by_name('num_detections:0')
# Actual detection.
(boxes, scores, classes, num_detections) = sess.run(
[boxes, 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)
plt.figure(figsize=IMAGE_SIZE)
plt.imshow(image_np) # matplotlib is configured for command line only so we save the outputs instead
plt.savefig("outputs/detection_output{}.png".format(i)) # create an outputs folder for the images to be saved
i = i+1 # this was a quick fix for iteration, create a pull request if you'd like
Error :
Traceback (most recent call last):
File "custom_model_images.py", line 82, in
feed_dict={image_tensor: image_np_expanded})
File "C:\Python36\lib\site-packages\tensorflow_core\python\client\session.py", line 956, in run
run_metadata_ptr)
File "C:\Python36\lib\site-packages\tensorflow_core\python\client\session.py", line 1156, in _run
(np_val.shape, subfeed_t.name, str(subfeed_t.get_shape())))
ValueError: Cannot feed value of shape (1, 233, 472, 4) for Tensor 'image_tensor:0', which has shape '(?, ?, ?, 3)'
Looks like some of your images have three channels, others - four channels (probably with alpha). Your model expecting three channels
I want to convert this object detection model into Human detection model. For this I only need to use the person class and filter out the boxes for other classes without retraining the entire model. Its ok if the other classes get detected in the background provided the detection boxes don't appear. Can someone please help me figure out what changes should be made to this code to achieve this?
import numpy as np
import os
import six.moves.urllib as urllib
import sys
import tarfile
import tensorflow as tf
import zipfile
from collections import defaultdict
from io import StringIO
from matplotlib import pyplot as plt
from PIL import Image
import cv2
cap = cv2.VideoCapture(0)
# cap = cv2.VideoCapture("video.mp4")
sys.path.append("..")
from utils import label_map_util
from utils import visualization_utils as vis_util
MODEL_NAME = 'ssd_mobilenet_v1_coco_11_06_2017'
MODEL_FILE = MODEL_NAME + '.tar.gz'
DOWNLOAD_BASE = 'http://download.tensorflow.org/models/object_detection/'
# Path to frozen detection graph. This is the actual model that is used for the object detection.
PATH_TO_CKPT = MODEL_NAME + '/frozen_inference_graph.pb'
# List of the strings that is used to add correct label for each box.
PATH_TO_LABELS = os.path.join('data', 'mscoco_label_map.pbtxt')
NUM_CLASSES = 90
opener = urllib.request.URLopener()
opener.retrieve(DOWNLOAD_BASE + MODEL_FILE, MODEL_FILE)
tar_file = tarfile.open(MODEL_FILE)
for file in tar_file.getmembers():
file_name = os.path.basename(file.name)
if 'frozen_inference_graph.pb' in file_name:
tar_file.extract(file, os.getcwd())
detection_graph = tf.Graph()
with detection_graph.as_default():
od_graph_def = tf.compat.v1.GraphDef()
with tf.compat.v2.io.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='')
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)
with detection_graph.as_default():
with tf.compat.v1.Session(graph=detection_graph) as sess:
while True:
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)
image_tensor = detection_graph.get_tensor_by_name('image_tensor:0')
# Each box represents a part of the image where a particular object was detected.
boxes = detection_graph.get_tensor_by_name('detection_boxes:0')
# Each score represent how level of confidence for each of the objects.
# Score is shown on the result image, together with the class label.
scores = detection_graph.get_tensor_by_name('detection_scores:0')
classes = detection_graph.get_tensor_by_name('detection_classes:0')
num_detections = detection_graph.get_tensor_by_name('num_detections:0')
# Actual detection.
(boxes, scores, classes, num_detections) = sess.run(
[boxes, 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)
cv2.imshow('object detection', cv2.resize(image_np, (800,600)))
if cv2.waitKey(25) & 0xFF == ord('q'):
cv2.destroyAllWindows()
break
Iḿ trying to run an objects detection code using tensorflow
import numpy as np
import os
import six.moves.urllib as urllib
import sys
import tarfile
import tensorflow as tf
import zipfile
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
# # Model preparation
# Any model exported using the `export_inference_graph.py` tool can be loaded here simply by changing `PATH_TO_CKPT` to point to a new .pb file.
# By default we use an "SSD with Mobilenet" model here. See the [detection model zoo](https://github.com/tensorflow/models/blob/master/object_detection/g3doc/detection_model_zoo.md) for a list of other models that can be run out-of-the-box with varying speeds and accuracies.
# What model to download.
MODEL_NAME = 'ssd_mobilenet_v1_coco_11_06_2017'
MODEL_FILE = MODEL_NAME + '.tar.gz'
DOWNLOAD_BASE = 'http://download.tensorflow.org/models/object_detection/'
# Path to frozen detection graph. This is the actual model that is used for the object detection.
PATH_TO_CKPT = MODEL_NAME + '/frozen_inference_graph.pb'
# List of the strings that is used to add correct label for each box.
PATH_TO_LABELS = os.path.join('data', 'mscoco_label_map.pbtxt')
NUM_CLASSES = 90
# ## Download Model
if not os.path.exists(MODEL_NAME + '/frozen_inference_graph.pb'):
print ('Downloading the model')
opener = urllib.request.URLopener()
opener.retrieve(DOWNLOAD_BASE + MODEL_FILE, MODEL_FILE)
tar_file = tarfile.open(MODEL_FILE)
for file in tar_file.getmembers():
file_name = os.path.basename(file.name)
if 'frozen_inference_graph.pb' in file_name:
tar_file.extract(file, os.getcwd())
print ('Download complete')
else:
print ('Model already exists')
# ## Load a (frozen) Tensorflow model into memory.
detection_graph = tf.Graph()
with detection_graph.as_default():
od_graph_def = tf.GraphDef()
with tf.gfile.GFile(PATH_TO_CKPT, 'rb') as fid:
serialized_graph = fid.read()
od_graph_def.ParseFromString(serialized_graph)
tf.import_graph_def(od_graph_def, name='')
# ## Loading label map
# Label maps map indices to category names, so that when our convolution network predicts `5`, we know that this corresponds to `airplane`. Here we use internal utility functions, but anything that returns a dictionary mapping integers to appropriate string labels would be fine
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)
#intializing the web camera device
import cv2
cap = cv2.VideoCapture(0)
# Running the tensorflow session
with detection_graph.as_default():
with tf.Session(graph=detection_graph) as sess:
ret = True
while (ret):
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)
image_tensor = detection_graph.get_tensor_by_name('image_tensor:0')
# Each box represents a part of the image where a particular object was detected.
boxes = detection_graph.get_tensor_by_name('detection_boxes:0')
# Each score represent how level of confidence for each of the objects.
# Score is shown on the result image, together with the class label.
scores = detection_graph.get_tensor_by_name('detection_scores:0')
classes = detection_graph.get_tensor_by_name('detection_classes:0')
num_detections = detection_graph.get_tensor_by_name('num_detections:0')
# Actual detection.
(boxes, scores, classes, num_detections) = sess.run(
[boxes, 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)
# plt.figure(figsize=IMAGE_SIZE)
# plt.imshow(image_np)
cv2.imshow('image',cv2.resize(image_np,(1280,960)))
if cv2.waitKey(25) & 0xFF == ord('q'):
cv2.destroyAllWindows()
cap.release()
break
But it shows me this problem
Traceback (most recent call last):
File "object_detection_webcam.py", line 97, in <module>
feed_dict={image_tensor: image_np_expanded})
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/client/session.py", line 778, in run
run_metadata_ptr)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/client/session.py", line 954, in _run
np_val = np.asarray(subfeed_val, dtype=subfeed_dtype)
File "/usr/lib/python2.7/dist-packages/numpy/core/numeric.py", line 531, in asarray
return array(a, dtype, copy=False, order=order)
TypeError: long() argument must be a string or a number, not 'NoneType'
Weŕe using tenserflow on Raspberry PI 3 and weŕe using the Raspberry camera.
We tried to import every library and it works(All imported libraries are installed)
We added the tensorflow/models/research/slim folder to the $PYTHONPATH
What could this problem cause be, and how can We solve it?
The problem is with this part:
ret = True
while (ret):
ret,image_np = cap.read()
After the last frame it will read None into image_np, but the inside of your loop still runs and tries to feed that None to the network, and would only stop when it gets to the while again.
You need to restructure similar to this:
while ( True ):
ret, image_np = cap.read()
if not ret:
break
I changed some sources to be real time object detection in the object_detection_tutorial provided by the tensorflow object detection API. However, the following error occurred. What is the solution?
The code that caused the problem is shown below.
import numpy as np
import os
import six.moves.urllib as urllib
import sys
import tarfile
import tensorflow as tf
import zipfile
from collections import defaultdict
from io import StringIO
from matplotlib import pyplot as plt
from PIL import Image
import cv2
cap = cv2.VideoCapture(1)
if tf.__version__ < '1.4.0':
raise ImportError('Please upgrade your tensorflow installation to v1.4.* or later!')
# This is needed since the notebook is stored in the object_detection folder.
sys.path.append("..")
# ## Object detection imports
# Here are the imports from the object detection module.
from utils import label_map_util
from utils import visualization_utils as vis_util
# # Model preparation
# ## Variables
#
# Any model exported using the `export_inference_graph.py` tool can be loaded here simply by changing `PATH_TO_CKPT` to point to a new .pb file.
#
# By default we use an "SSD with Mobilenet" model here. See the [detection model zoo](https://github.com/tensorflow/models/blob/master/research/object_detection/g3doc/detection_model_zoo.md) for a list of other models that can be run out-of-the-box with varying speeds and accuracies.
# What model to download.
MODEL_NAME = 'ssd_mobilenet_v1_coco_2017_11_17'
MODEL_FILE = MODEL_NAME + '.tar.gz'
DOWNLOAD_BASE = 'http://download.tensorflow.org/models/object_detection/'
# Path to frozen detection graph. This is the actual model that is used for the object detection.
PATH_TO_CKPT = MODEL_NAME + '/frozen_inference_graph.pb'
# List of the strings that is used to add correct label for each box.
PATH_TO_LABELS = os.path.join('data', 'mscoco_label_map.pbtxt')
NUM_CLASSES = 90
# ## Download Model
opener = urllib.request.URLopener()
opener.retrieve(DOWNLOAD_BASE + MODEL_FILE, MODEL_FILE)
tar_file = tarfile.open(MODEL_FILE)
for file in tar_file.getmembers():
file_name = os.path.basename(file.name)
if 'frozen_inference_graph.pb' in file_name:
tar_file.extract(file, os.getcwd())
# ## Load a (frozen) Tensorflow model into memory.
detection_graph = tf.Graph()
with detection_graph.as_default():
od_graph_def = tf.GraphDef()
with tf.gfile.GFile(PATH_TO_CKPT, 'rb') as fid:
serialized_graph = fid.read()
od_graph_def.ParseFromString(serialized_graph)
tf.import_graph_def(od_graph_def, name='')
# ## Loading label map
# Label maps map indices to category names, so that when our convolution network predicts `5`, we know that this corresponds to `airplane`. Here we use internal utility functions, but anything that returns a dictionary mapping integers to appropriate string labels would be fine
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
# For the sake of simplicity we will use only 2 images:
# image1.jpg
# image2.jpg
# If you want to test the code with your images, just add path to the images to the TEST_IMAGE_PATHS.
PATH_TO_TEST_IMAGES_DIR = 'test_images'
TEST_IMAGE_PATHS = [ os.path.join(PATH_TO_TEST_IMAGES_DIR, 'image{}.jpg'.format(i)) for i in range(1, 3) ]
# Size, in inches, of the output images.
IMAGE_SIZE = (12, 8)
with detection_graph.as_default():
with tf.Session(graph=detection_graph) as sess:
# Definite input and output Tensors for detection_graph
image_tensor = detection_graph.get_tensor_by_name('image_tensor:0')
# Each box represents a part of the image where a particular object was detected.
detection_boxes = detection_graph.get_tensor_by_name('detection_boxes:0')
# Each score represent how level of confidence for each of the objects.
# Score is shown on the result image, together with the class label.
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')
while True:
ret, image_np = cv2.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)
# Actual detection.
(boxes, scores, classes, num) = sess.run(
[detection_boxes, detection_scores, detection_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)
cv2.imshow('object detection',cv2.resize(image_np,(800,600)))
if cv2.waitkey(25) & 0xFF == ord('q'):
cv2.destroyAllWindows()
break;
This is the result of running the corresponding source as Anaconda Prompt
(tensorflow3_6) c:\Users\MrSong\Downloads\models\research>python object_detection/object_detection_tutorial.py
Traceback (most recent call last):
File "object_detection/object_detection_tutorial.py", line 104, in <module>
label_map = label_map_util.load_labelmap(PATH_TO_LABELS)
File "c:\Users\MrSong\Downloads\models\research\object_detection\utils\label_map_util.py", line 117, in load_labelmap
label_map_string = fid.read()
File "C:\Users\MrSong\Anaconda3\envs\tensorflow3_6\lib\site-packages\tensorflow\python\lib\io\file_io.py", line 119, in read
self._preread_check()
File "C:\Users\MrSong\Anaconda3\envs\tensorflow3_6\lib\site-packages\tensorflow\python\lib\io\file_io.py", line 79, in _preread_check
compat.as_bytes(self.__name), 1024 * 512, status)
File "C:\Users\MrSong\Anaconda3\envs\tensorflow3_6\lib\site-packages\tensorflow\python\framework\errors_impl.py", line 473, in __exit__
c_api.TF_GetCode(self.status.status))
tensorflow.python.framework.errors_impl.NotFoundError: NewRandomAccessFile failed to Create/Open: data\mscoco_label_map.pbtxt : \udcc1\udcf6\udcc1\udca4\udcb5\udcc8 \udcb0\udce6\udcb7θ\udca6 ã\udcc0\udcbb \udcbc\udcf6 \udcbe\udcf8\udcbd\udcc0\udcb4ϴ\udcd9.
; No such process
Make sure you have the 'mscoco_label_map.pbtxt' in the data folder in 'object_detection' directory. The CONFIG file and the labelmap should be in the same directory.
System information
What is the top-level directory of the model you are using: tensorflow/models
Have I written custom code (as opposed to using a stock example script provided in TensorFlow): No
OS Platform and Distribution (e.g., Linux Ubuntu 16.04): Windows 10 x64
TensorFlow installed from (source or binary): binary
TensorFlow version (use command below): 1.3.0
Bazel version (if compiling from source):
CUDA/cuDNN version:
GPU model and memory:
Exact command to reproduce: python object_detection\eval.py --logtostderr --checkpoint_dir=train --eval_dir=eval --pipeline_config_path=ssd_mobilenet_v1.config
&
python detect.py
Describe the problem
When training the Oxford-IIIT Pet Dataset from with finetune checkpoint from COCO set, I get the following error message while running the eval.py script:
Corrupt JPEG data: 245 extraneous bytes before marker 0xd9
While running the detect.py script after the failed evaluation I get the attached images without any detection boxes.
Source code / logs
code for detect.py:
import numpy as np
import os
import six.moves.urllib as urllib
import sys
import tensorflow as tf
import zipfile
from object_detection.utils import label_map_util
from object_detection.utils import visualization_utils as vis_util
from collections import defaultdict
from io import StringIO
from matplotlib import pyplot as plt
from PIL import Image
PATH_TO_CKPT = os.path.join('inference_graphs', 'frozen_inference_graph.pb')
PATH_TO_LABELS = 'pet_label_map.pbtxt'
PATH_TO_TEST_IMAGES_DIR = os.path.join('test')
NUM_CLASSES = 37
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='')
label_map = label_map_util.load_labelmap(PATH_TO_LABELS)
categories = label_map_util.convert_label_map_to_categories(label_map, max_num_classes=NUM_CLASSES, use_display_name=True)
category_index = label_map_util.create_category_index(categories)
def load_image_into_numpy_array(image):
(im_width, im_height) = image.size
return np.array(image.getdata()).reshape(
(im_height, im_width, 3)).astype(np.uint8)
TEST_IMAGE_PATHS = [ os.path.join(PATH_TO_TEST_IMAGES_DIR,'{}'.format(file)) for file in os.listdir(PATH_TO_TEST_IMAGES_DIR)]
print(TEST_IMAGE_PATHS)
#TEST_IMAGE_PATHS = [ os.path.join(PATH_TO_TEST_IMAGES_DIR, 'image#{}.jpg'.format(i)) for i in range(1, 3) ]
# Size, in inches, of the output images.
IMAGE_SIZE = (12, 8)
def write_jpeg(data, filepath):
g = tf.Graph()
with g.as_default():
data_t = tf.placeholder(tf.uint8)
op = tf.image.encode_jpeg(data_t, format='rgb', quality=100)
init = tf.initialize_all_variables()
with tf.Session(graph=g) as sess:
sess.run(init)
data_np = sess.run(op, feed_dict={ data_t: data })
with open(filepath, 'wb') as fd:
fd.write(data_np)
with detection_graph.as_default():
with tf.Session(graph=detection_graph) as sess:
# Definite input and output Tensors for detection_graph
image_tensor = detection_graph.get_tensor_by_name('image_tensor:0')
# Each box represents a part of the image where a particular object was detected.
detection_boxes = detection_graph.get_tensor_by_name('detection_boxes:0')
# Each score represent how level of confidence for each of the objects.
# Score is shown on the result image, together with the class label.
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:
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.
(boxes, scores, classes, num) = sess.run(
[detection_boxes, detection_scores, detection_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)
write_jpeg(image_np, os.path.join(os.path.dirname(image_path),'inferred', os.path.basename(image_path)))
plt.figure(figsize=IMAGE_SIZE)
plt.imshow(image_np)
plt.show()
print(image_path)
print(boxes)
print(classes)
print(scores)
#write_jpeg(image_np, os.path.join(os.path.dirname(image_path),os.path.splitext(os.path.basename(image_path))[1]))
The detection failed because the training requires a lot of steps. I started getting results at 2000 steps. The jpeg corruption error has probably to do with the oxford data set, but I was still able to test with the error.