图像分类器未显示损失,准确性和培训过程

发布于 2025-02-07 09:00:47 字数 2956 浏览 0 评论 0原文

我的代码不起作用。我一直关注的教程是: https://www.youtube。 com/watch?v = t0ezvcvqjge& t = 1052s 。没有任何错误或其他任何内容,但它并没有显示末尾的损失,准确性和训练过程(我正在使用VSCODE),就像视频中(视频中的17:53)一样。这是我的代码:

import cv2 as cv2
import numpy as numpy
import matplotlib.pyplot as plt
from tensorflow.keras import datasets, layers, models

(training_images, training_labels), (testing_images, testing_labels) = datasets.cifar10.load_data()
training_images, testing_images = training_images / 255, testing_images / 255

class_names = ['Plane', 'Car', 'Bird', 'Cat', 'Deer', 'Dog', 'Frog', 'Horse', 'Ship', 'Truck']

for i in range(16):
    plt.subplot(4,4,i+1)
    plt.xticks([])
    plt.yticks([])
    plt.imshow(training_images[i], cmap=plt.cm.binary)
    plt.xlabel(class_names[training_labels[i][0]])

plt.show()

training_images = training_images[:5000]
training_labels = training_labels[:5000]
testing_images = testing_images[:1000]
testing_labels = testing_labels[:1000]

model = models.Sequential()
model.add(layers.Conv2D(32, (3,3), activation='relu', input_shape=(32,32,3)))
model.add(layer.MaxPooling2D((2,2)))
model.add(layers.Conv2D(32, (3,3), activation='relu'))
model.add(layer.MaxPooling2D((2,2)))
model.add(layers.Conv2D(32, (3,3), activation='relu'))
model.add(layers.flatten())
model.add(layers.Dense(64, activation='relu'))
model.add(layers.Dense(10, activation='softmax'))

model.complie(optimizer='adam', loss='sparse_categorical_crossentropy', metrics=['accuracy'])

model.fit(training_images, training_labels, epochs=10, validation_data=(testing_images, testing_labels))

loss, accuracy = model.evaluate(testing_images, testing_labels)
print(f"Loss: {loss}")
print(f"Accuracy: {accuracy}")

model.save('image_classifier.model')

此外,我的航站楼中还有一些显示的东西:

I tensorflow/core/platform/cpu_feature_guard.cc:142] This TensorFlow binary is optimized with oneAPI Deep Neural Network Library (oneDNN) to use the following CPU instructions in performance-critical operations:  AVX2
To enable them in other operations, rebuild TensorFlow with the appropriate compiler flags.
OMP: Error #15: Initializing libiomp5, but found libiomp5md.dll already initialized.
OMP: Hint This means that multiple copies of the OpenMP runtime have been linked into the program. That is dangerous, since it can degrade performance or cause incorrect results. The best thing to do is to ensure that only a single OpenMP runtime is linked into the process, e.g. by avoiding static linking of the OpenMP runtime in any library. As an unsafe, unsupported, undocumented workaround you can set the environment variable KMP_DUPLICATE_LIB_OK=TRUE to allow the program to continue to execute, but that may cause crashes or silently produce incorrect results. For more information, please see http://openmp.llvm.org/      

有人知道发生了什么吗?如果是这样,请回复。谢谢!

My code isn't working. The tutorial that I've been following is: https://www.youtube.com/watch?v=t0EzVCvQjGE&t=1052s. There's no errors or anything, but it doesn't show the loss, accuracy, and training process at the end (I'm using vscode), like it does in the video (17:53 in the video). Here's my code:

import cv2 as cv2
import numpy as numpy
import matplotlib.pyplot as plt
from tensorflow.keras import datasets, layers, models

(training_images, training_labels), (testing_images, testing_labels) = datasets.cifar10.load_data()
training_images, testing_images = training_images / 255, testing_images / 255

class_names = ['Plane', 'Car', 'Bird', 'Cat', 'Deer', 'Dog', 'Frog', 'Horse', 'Ship', 'Truck']

for i in range(16):
    plt.subplot(4,4,i+1)
    plt.xticks([])
    plt.yticks([])
    plt.imshow(training_images[i], cmap=plt.cm.binary)
    plt.xlabel(class_names[training_labels[i][0]])

plt.show()

training_images = training_images[:5000]
training_labels = training_labels[:5000]
testing_images = testing_images[:1000]
testing_labels = testing_labels[:1000]

model = models.Sequential()
model.add(layers.Conv2D(32, (3,3), activation='relu', input_shape=(32,32,3)))
model.add(layer.MaxPooling2D((2,2)))
model.add(layers.Conv2D(32, (3,3), activation='relu'))
model.add(layer.MaxPooling2D((2,2)))
model.add(layers.Conv2D(32, (3,3), activation='relu'))
model.add(layers.flatten())
model.add(layers.Dense(64, activation='relu'))
model.add(layers.Dense(10, activation='softmax'))

model.complie(optimizer='adam', loss='sparse_categorical_crossentropy', metrics=['accuracy'])

model.fit(training_images, training_labels, epochs=10, validation_data=(testing_images, testing_labels))

loss, accuracy = model.evaluate(testing_images, testing_labels)
print(f"Loss: {loss}")
print(f"Accuracy: {accuracy}")

model.save('image_classifier.model')

Furthermore, there's also something that shows in my terminal:

I tensorflow/core/platform/cpu_feature_guard.cc:142] This TensorFlow binary is optimized with oneAPI Deep Neural Network Library (oneDNN) to use the following CPU instructions in performance-critical operations:  AVX2
To enable them in other operations, rebuild TensorFlow with the appropriate compiler flags.
OMP: Error #15: Initializing libiomp5, but found libiomp5md.dll already initialized.
OMP: Hint This means that multiple copies of the OpenMP runtime have been linked into the program. That is dangerous, since it can degrade performance or cause incorrect results. The best thing to do is to ensure that only a single OpenMP runtime is linked into the process, e.g. by avoiding static linking of the OpenMP runtime in any library. As an unsafe, unsupported, undocumented workaround you can set the environment variable KMP_DUPLICATE_LIB_OK=TRUE to allow the program to continue to execute, but that may cause crashes or silently produce incorrect results. For more information, please see http://openmp.llvm.org/      

Does anyone know what's going on? If so, please reply. Thanks!

如果你对这篇内容有疑问,欢迎到本站社区发帖提问 参与讨论,获取更多帮助,或者扫码二维码加入 Web 技术交流群。

扫码二维码加入Web技术交流群

发布评论

需要 登录 才能够评论, 你可以免费 注册 一个本站的账号。

评论(1

青衫负雪 2025-02-14 09:00:47

从我的看来,在这里添加这两条线应在您的代码中起作用。我认为您的Keras安装有问题。

import os
os.environ['KMP_DUPLICATE_LIB_OK']='True'

为了始终避免添加这些行,我想您应该将其添加到系统中的ENV变量中。

另一个解决方案是删除库中的libiomp5md.dll文件。您可以检查目录中是否存在该文件。

From what I have looked up over here adding these two lines should work in your code. I assume something is wrong with your installation of keras.

import os
os.environ['KMP_DUPLICATE_LIB_OK']='True'

To always avoid adding these lines I suppose you should add that to env variables in the system.

Another solution is to delete libiomp5md.dll file in your libraries. You could check to see if that file exists in your directories.

~没有更多了~
我们使用 Cookies 和其他技术来定制您的体验包括您的登录状态等。通过阅读我们的 隐私政策 了解更多相关信息。 单击 接受 或继续使用网站,即表示您同意使用 Cookies 和您的相关数据。
原文