用keras识别狗狗

news2024/11/21 2:25:03

一、需求场景

从照片从识别出狗狗

from keras.applications.resnet50 import ResNet50
from keras.preprocessing import image
from keras.applications.resnet50 import preprocess_input, decode_predictions
import numpy as np

# 加载预训练的ResNet50模型
model = ResNet50(weights='imagenet')
def recognize_dog(img_path):
    # 加载图片并调整尺寸为224x224
    img = image.load_img(img_path, target_size=(224, 224))
    # 将图片转换为numpy数组
    x = image.img_to_array(img)
    # 扩展维度以适应模型的输入要求
    x = np.expand_dims(x, axis=0)
    # 预处理图片
    x = preprocess_input(x)
    # 使用模型进行预测
    preds = model.predict(x)
    # 解码预测结果，得到前3个最可能的类别及其概率
    results = decode_predictions(preds, top=3)[0]
    # 检查是否包含"dog"
    for result in results:
        print(result)

# 测试
print(recognize_dog('e:\\testImage\dog1.jpg'))
print(recognize_dog('e:\\testImage\dog2.jpg'))

"C:\Program Files (x86)\Microsoft Visual Studio\Shared\Python39_64\python.exe" E:\PycharmProjects\pythonProject\test20240503-001.py
2024-05-03 13:09:11.097463: I tensorflow/core/util/port.cc:113] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable `TF_ENABLE_ONEDNN_OPTS=0`.
2024-05-03 13:09:11.755791: I tensorflow/core/util/port.cc:113] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable `TF_ENABLE_ONEDNN_OPTS=0`.
2024-05-03 13:09:13.229779: I tensorflow/core/platform/cpu_feature_guard.cc:210] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations.
To enable the following instructions: AVX2 FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags.
1/1 ━━━━━━━━━━━━━━━━━━━━ 1s 1s/step
('n02099712', 'Labrador_retriever', 0.755565)
('n02109047', 'Great_Dane', 0.15936635)
('n02099267', 'flat-coated_retriever', 0.059484843)
None
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 78ms/step
('n02113186', 'Cardigan', 0.65025693)
('n02113023', 'Pembroke', 0.34579375)
('n02115641', 'dingo', 0.0023858186)
None

Process finished with exit code 0

二、知识点Keras

Keras是一个高级的神经网络框架，它用Python编写，旨在实现快速的实验和原型设计。

解释说明：

Keras是为了简化神经网络的构建和训练过程而设计的，它提供了一种简洁、直观的方式让用户能够轻松地定义和训练深度学习模型。
作为一个高级API，Keras可以运行在多个后端之上，包括TensorFlow、Microsoft CNTK和Theano。这意味着用户可以利用这些后端引擎的强大功能，同时享受Keras提供的简洁和易用性。
Keras支持卷积神经网络（CNNs）和循环神经网络（RNNs），这两种网络是深度学习中非常重要的结构，广泛应用于图像识别、语音识别等领域。

使用示例：

安装Keras可以通过pip命令进行：pip install keras。
一个简单的Keras模型定义和训练的例子可能如下：

from keras.models import Sequential
from keras.layers import Dense

model = Sequential()
model.add(Dense(units=64, activation='relu', input_dim=100))
model.add(Dense(units=10, activation='softmax'))
model.compile(loss='categorical_crossentropy', optimizer='sgd', metrics=['accuracy'])

model.fit(x_train, y_train, epochs=5, batch_size=32)

Keras是一个强大的工具，特别适合那些希望快速开发和实验深度学习模型的用户。它的设计理念是简化复杂性，使得初学者和非专家也能够轻松上手深度学习项目。