如何正确使用预训练的 CNN 对图像文件夹进行图像预测
How to properly use pre-trained CNN for image prediction on a folder of images
我正在尝试构建一个 CNN 模型并将其用于 2833 张图像，以查看它是否可以预测（我自己选择的）三个特征的选择以及来自表格数据集的流行度得分。到目前为止，我的代码如下所示：
import os
import cv2
import argparse
import numpy as np
from keras.applications.vgg16 import VGG16
from keras.preprocessing import image as image_utils
from keras.applications.imagenet_utils import preprocess_input, decode_predictions
# Construct argument parser and parse the arguments
argument_parser = argparse.ArgumentParser()
# First two arguments specifies our only argument "image" with both short-/longhand versions where either
# can be used
# This is a required argument, noted by required=True, the help gives additional info in the terminal
# if needed
argument_parser.add_argument("-i", "--image", required=True, help="path to the input image")
# Set path to files
img_path = "images/"
files = os.listdir(img_path)
print("[INFO] loading and processing images...")
# Loop through images
for filename in files:
# Load original via OpenCV, so we can draw on it and display it on our screen
original = cv2.imread(filename)
# Load image while resizing to 224x224 pixels, then convert to a NumPy array because load_img returns
# Pillow format
image = image_utils.load_img(filename, target_size=(224, 224))
image = image_utils.img_to_array(image)
"""
PRE-PROCESS
The image is now a NumPy array of shape (224, 224, 3). 224 pixels tall, 224 pixels wide, 3 channels =
Red, Green, Blue. We need to expand to (1, 3, 224, 224) because when classifying images using Deep
Learning and Convolutional Neural Networks, we often send several images (instead of one) through
the network in “batches” for efficiency. We also subtract the mean RGB pixel intensity from the
ImageNet dataset.
"""
image = np.expand_dims(image, axis=0)
image = preprocess_input(image)
# Load Keras and classify the image
print("[INFO] loading network...")
model = VGG16(weights="imagenet") # Load the VGG16 network pre-trained on the ImageNet dataset
print("[INFO] classifying image...")
predictions = model.predict(image) # Classify the image (NumPy array with 1000 entries)
P = decode_predictions(predictions) # Get the ImageNet Unique ID of the label, along with human-readable label
print(P)
# Loop over the predictions and display the rank-5 (5 epochs) predictions + probabilities to our terminal
for (i, (imagenetID, label, prob)) in enumerate(P[0]):
print("{}. {}: {:.2f}%".format(i + 1, label, prob * 100))
# Load the image via OpenCV, draw the top prediction on the image, and display the
image to our screen
original = cv2.imread(filename)
(imagenetID, label, prob) = P[0][0]
cv2.putText(original, "Label: {}, {:.2f}%".format(label, prob * 100), (10, 30),
cv2.FONT_HERSHEY_SIMPLEX, 0.8, (0, 255, 0), 2)
cv2.imshow("Classification", original)
cv2.waitKey(0)
我按照 this 文章中的操作方法进行了操作，它在一张图片上起作用。但是当我试图将代码放入循环中时，我得到了这个错误信息：
[ WARN:0@44.040] global D:\a\opencv-python\opencv-python\opencv\modules\imgcodecs\src\loadsave.cpp (239) cv::findDecoder imread_('100.png'): can't open/read file: check file path/integrity
Traceback (most recent call last):
File "C:\PATH\test_imagenet.py", line 28, in <module>
image = image_utils.load_img(filename, target_size=(224, 224))
File "C:\PATH\AppData\Local\Programs\Python\Python39\lib\site-packages\keras\preprocessing\image.py", line 313, in load_img
return image.load_img(path, grayscale=grayscale, color_mode=color_mode,
File "C:\PATH\AppData\Local\Programs\Python\Python39\lib\site-packages\keras_preprocessing\image\utils.py", line 113, in load_img
with open(path, 'rb') as f:
FileNotFoundError: [Errno 2] No such file or directory: '100.png'
如你所见，我在项目中有这个文件，不知道为什么找不到。我如何正确地为一个图像文件执行此操作，而不是仅对一个图像执行此操作？
请在下面找到工作代码；
import os
import cv2
import argparse
import numpy as np
from keras.applications.vgg16 import VGG16
from keras.preprocessing import image as image_utils
from keras.applications.imagenet_utils import preprocess_input, decode_predictions
# Construct argument parser and parse the arguments
argument_parser = argparse.ArgumentParser()
# First two arguments specifies our only argument "image" with both short-/longhand versions where either
# can be used
# This is a required argument, noted by required=True, the help gives additional info in the terminal
# if needed
argument_parser.add_argument("-i", "--image", required=True, help="path to the input image")
# Set path to files
img_path = "/content/train/"
files = os.listdir(img_path)
print("[INFO] loading and processing images...")
for filename in files:
# Passing the entire path of the image file
file= os.path.join(img_path, filename)
# Load original via OpenCV, so we can draw on it and display it on our screen
original = cv2.imread(file)
image = image_utils.load_img(file, target_size=(224, 224))
image = image_utils.img_to_array(image)
image = np.expand_dims(image, axis=0)
image = preprocess_input(image)
print("[INFO] loading network...")
model = VGG16(weights="imagenet") # Load the VGG16 network pre-trained on the ImageNet dataset
print("[INFO] classifying image...")
predictions = model.predict(image) # Classify the image (NumPy array with 1000 entries)
P = decode_predictions(predictions) # Get the ImageNet Unique ID of the label, along with human-readable label
print(P)
# Loop over the predictions and display the rank-5 (5 epochs) predictions + probabilities to our terminal
for (i, (imagenetID, label, prob)) in enumerate(P[0]):
print("{}. {}: {:.2f}%".format(i + 1, label, prob * 100))
original = cv2.imread(file)
(imagenetID, label, prob) = P[0][0]
cv2.putText(original, "Label: {}, {:.2f}%".format(label, prob * 100), (10, 30),
cv2.FONT_HERSHEY_SIMPLEX, 0.8, (0, 255, 0), 2)
cv2.imshow(original)
cv2.waitKey(0)
输出如下：
如果问题仍然存在，请告诉我们。谢谢！
我正在尝试构建一个 CNN 模型并将其用于 2833 张图像，以查看它是否可以预测（我自己选择的）三个特征的选择以及来自表格数据集的流行度得分。到目前为止，我的代码如下所示：
import os
import cv2
import argparse
import numpy as np
from keras.applications.vgg16 import VGG16
from keras.preprocessing import image as image_utils
from keras.applications.imagenet_utils import preprocess_input, decode_predictions
# Construct argument parser and parse the arguments
argument_parser = argparse.ArgumentParser()
# First two arguments specifies our only argument "image" with both short-/longhand versions where either
# can be used
# This is a required argument, noted by required=True, the help gives additional info in the terminal
# if needed
argument_parser.add_argument("-i", "--image", required=True, help="path to the input image")
# Set path to files
img_path = "images/"
files = os.listdir(img_path)
print("[INFO] loading and processing images...")
# Loop through images
for filename in files:
# Load original via OpenCV, so we can draw on it and display it on our screen
original = cv2.imread(filename)
# Load image while resizing to 224x224 pixels, then convert to a NumPy array because load_img returns
# Pillow format
image = image_utils.load_img(filename, target_size=(224, 224))
image = image_utils.img_to_array(image)
"""
PRE-PROCESS
The image is now a NumPy array of shape (224, 224, 3). 224 pixels tall, 224 pixels wide, 3 channels =
Red, Green, Blue. We need to expand to (1, 3, 224, 224) because when classifying images using Deep
Learning and Convolutional Neural Networks, we often send several images (instead of one) through
the network in “batches” for efficiency. We also subtract the mean RGB pixel intensity from the
ImageNet dataset.
"""
image = np.expand_dims(image, axis=0)
image = preprocess_input(image)
# Load Keras and classify the image
print("[INFO] loading network...")
model = VGG16(weights="imagenet") # Load the VGG16 network pre-trained on the ImageNet dataset
print("[INFO] classifying image...")
predictions = model.predict(image) # Classify the image (NumPy array with 1000 entries)
P = decode_predictions(predictions) # Get the ImageNet Unique ID of the label, along with human-readable label
print(P)
# Loop over the predictions and display the rank-5 (5 epochs) predictions + probabilities to our terminal
for (i, (imagenetID, label, prob)) in enumerate(P[0]):
print("{}. {}: {:.2f}%".format(i + 1, label, prob * 100))
# Load the image via OpenCV, draw the top prediction on the image, and display the
image to our screen
original = cv2.imread(filename)
(imagenetID, label, prob) = P[0][0]
cv2.putText(original, "Label: {}, {:.2f}%".format(label, prob * 100), (10, 30),
cv2.FONT_HERSHEY_SIMPLEX, 0.8, (0, 255, 0), 2)
cv2.imshow("Classification", original)
cv2.waitKey(0)
我按照 this 文章中的操作方法进行了操作，它在一张图片上起作用。但是当我试图将代码放入循环中时，我得到了这个错误信息：
[ WARN:0@44.040] global D:\a\opencv-python\opencv-python\opencv\modules\imgcodecs\src\loadsave.cpp (239) cv::findDecoder imread_('100.png'): can't open/read file: check file path/integrity
Traceback (most recent call last):
File "C:\PATH\test_imagenet.py", line 28, in <module>
image = image_utils.load_img(filename, target_size=(224, 224))
File "C:\PATH\AppData\Local\Programs\Python\Python39\lib\site-packages\keras\preprocessing\image.py", line 313, in load_img
return image.load_img(path, grayscale=grayscale, color_mode=color_mode,
File "C:\PATH\AppData\Local\Programs\Python\Python39\lib\site-packages\keras_preprocessing\image\utils.py", line 113, in load_img
with open(path, 'rb') as f:
FileNotFoundError: [Errno 2] No such file or directory: '100.png'
如你所见，我在项目中有这个文件，不知道为什么找不到。我如何正确地为一个图像文件执行此操作，而不是仅对一个图像执行此操作？
请在下面找到工作代码；
import os
import cv2
import argparse
import numpy as np
from keras.applications.vgg16 import VGG16
from keras.preprocessing import image as image_utils
from keras.applications.imagenet_utils import preprocess_input, decode_predictions
# Construct argument parser and parse the arguments
argument_parser = argparse.ArgumentParser()
# First two arguments specifies our only argument "image" with both short-/longhand versions where either
# can be used
# This is a required argument, noted by required=True, the help gives additional info in the terminal
# if needed
argument_parser.add_argument("-i", "--image", required=True, help="path to the input image")
# Set path to files
img_path = "/content/train/"
files = os.listdir(img_path)
print("[INFO] loading and processing images...")
for filename in files:
# Passing the entire path of the image file
file= os.path.join(img_path, filename)
# Load original via OpenCV, so we can draw on it and display it on our screen
original = cv2.imread(file)
image = image_utils.load_img(file, target_size=(224, 224))
image = image_utils.img_to_array(image)
image = np.expand_dims(image, axis=0)
image = preprocess_input(image)
print("[INFO] loading network...")
model = VGG16(weights="imagenet") # Load the VGG16 network pre-trained on the ImageNet dataset
print("[INFO] classifying image...")
predictions = model.predict(image) # Classify the image (NumPy array with 1000 entries)
P = decode_predictions(predictions) # Get the ImageNet Unique ID of the label, along with human-readable label
print(P)
# Loop over the predictions and display the rank-5 (5 epochs) predictions + probabilities to our terminal
for (i, (imagenetID, label, prob)) in enumerate(P[0]):
print("{}. {}: {:.2f}%".format(i + 1, label, prob * 100))
original = cv2.imread(file)
(imagenetID, label, prob) = P[0][0]
cv2.putText(original, "Label: {}, {:.2f}%".format(label, prob * 100), (10, 30),
cv2.FONT_HERSHEY_SIMPLEX, 0.8, (0, 255, 0), 2)
cv2.imshow(original)
cv2.waitKey(0)
输出如下：
如果问题仍然存在，请告诉我们。谢谢！