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