customvision.ai を使用してモデルをトレーニングし、モデルをエクスポートしてローカルで使用しました。
次の行に問題があります。
output_layer = 'loss:0'
"The name 'loss:0' refers to a Tensor which does not exist. The operation, 'loss', does not exist in the graph."
output_layer=に変更するoutput_layer = 'model_outputs:0'と、テスト用に 80x80x3 の画像があるため、このエラーが発生します。
Cannot feed value of shape (1, 80, 80, 3) for Tensor 'Placeholder:0', which has shape '(?, 416, 416, 3)'
ソースコードは次のとおりです。
import tensorflow as tf
import os
graph_def = tf.GraphDef()
labels = []
# These are set to the default names from exported models, update as needed.
filename = "model.pb"
labels_filename = "labels.txt"
# Import the TF graph
with tf.gfile.FastGFile(filename, 'rb') as f:
graph_def.ParseFromString(f.read())
tf.import_graph_def(graph_def, name='')
# Create a list of labels.
with open(labels_filename, 'rt') as lf:
for l in lf:
labels.append(l.strip())
from PIL import Image
import numpy as np
import cv2
def update_orientation(image):
exif_orientation_tag = 0x0112
if hasattr(image, '_getexif'):
exif = image._getexif()
if (exif != None and exif_orientation_tag in exif):
orientation = exif.get(exif_orientation_tag, 1)
# orientation is 1 based, shift to zero based and flip/transpose based on 0-based values
orientation -= 1
if orientation >= 4:
image = image.transpose(Image.TRANSPOSE)
if orientation == 2 or orientation == 3 or orientation == 6 or orientation == 7:
image = image.transpose(Image.FLIP_TOP_BOTTOM)
if orientation == 1 or orientation == 2 or orientation == 5 or orientation == 6:
image = image.transpose(Image.FLIP_LEFT_RIGHT)
return image
def convert_to_opencv(image):
# RGB -> BGR conversion is performed as well.
r,g,b,a = np.array(image).T
opencv_image = np.array([b,g,r]).transpose()
return opencv_image
def crop_center(img,cropx,cropy):
h, w = img.shape[:2]
startx = w//2-(cropx//2)
starty = h//2-(cropy//2)
return img[starty:starty+cropy, startx:startx+cropx]
def resize_down_to_1600_max_dim(image):
h, w = image.shape[:2]
if (h < 1600 and w < 1600):
return image
new_size = (1600 * w // h, 1600) if (h > w) else (1600, 1600 * h // w)
return cv2.resize(image, new_size, interpolation = cv2.INTER_LINEAR)
def resize_to_256_square(image):
h, w = image.shape[:2]
return cv2.resize(image, (256, 256), interpolation = cv2.INTER_LINEAR)
# Load from a file
imageFile = "test01.png"
image = Image.open(imageFile)
# Update orientation based on EXIF tags, if the file has orientation info.
image = update_orientation(image)
# Convert to OpenCV format
image = convert_to_opencv(image)
# If the image has either w or h greater than 1600 we resize it down respecting
# aspect ratio such that the largest dimension is 1600
image = resize_down_to_1600_max_dim(image)
# We next get the largest center square
h, w = image.shape[:2]
min_dim = min(w,h)
max_square_image = crop_center(image, min_dim, min_dim)
# Resize that square down to 256x256
augmented_image = resize_to_256_square(max_square_image)
# Get the input size of the model
with tf.Session() as sess:
input_tensor_shape = sess.graph.get_tensor_by_name('Placeholder:0').shape.as_list()
network_input_size = input_tensor_shape[1]
# Crop the center for the specified network_input_Size
augmented_image = crop_center(augmented_image, network_input_size, network_input_size)
# These names are part of the model and cannot be changed.
output_layer = 'loss:0'
input_node = 'Placeholder:0'
with tf.Session() as sess:
prob_tensor = sess.graph.get_tensor_by_name(output_layer)
sess.run(prob_tensor, {input_node: [augmented_image] })
predictions, = sess.run(prob_tensor, {input_node: [augmented_image] })
# Print the highest probability label
highest_probability_index = np.argmax(predictions)
print('Classified as: ' + labels[highest_probability_index])
print()
# Or you can print out all of the results mapping labels to probabilities.
label_index = 0
for p in predictions[0]:
truncated_probablity = np.float64(np.round(p,8))
print (labels[label_index], truncated_probablity)
label_index += 1