Keras - 使用 ResNet 模型进行实时预测

简述

ResNet是一个预训练模型。它是使用ImageNet训练的。在ImageNet上预训练的 ResNet 模型权重。它具有以下语法 -



keras.applications.resnet.ResNet50 (

   include_top = True, 

   weights = 'imagenet', 

   input_tensor = None, 

   input_shape = None, 

   pooling = None, 

   classes = 1000

)

说明

include_top指的是网络顶部的全连接层。
weights是指 ImageNet 上的预训练。
input_tensor是指可选的 Keras 张量，用作模型的图像输入。
input_shape是指可选的形状元组。此模型的默认输入大小为 224x224。
classes是指可选数量的类来对图像进行分类。

让我们通过写一个简单的例子来理解模型 -

第一步：导入模块

让我们加载必要的模块，如下所示 -



>>> import PIL 

>>> from keras.preprocessing.image import load_img 

>>> from keras.preprocessing.image import img_to_array 

>>> from keras.applications.imagenet_utils import decode_predictions 

>>> import matplotlib.pyplot as plt 

>>> import numpy as np 

>>> from keras.applications.resnet50 import ResNet50 

>>> from keras.applications import resnet50

第 2 步：选择输入

让我们选择一个输入图像，Lotus，如下所示 -



>>> filename = 'banana.jpg' 

>>> ## load an image in PIL format 

>>> original = load_img(filename, target_size = (224, 224)) 

>>> print('PIL image size',original.size)

PIL image size (224, 224) 

>>> plt.imshow(original) 

<matplotlib.image.AxesImage object at 0x1304756d8> 

>>> plt.show()

在这里，我们加载了一个图像（banana.jpg）并显示它。

第 3 步：将图像转换为 NumPy 数组

让我们将输入Banana转换为 NumPy 数组，以便可以将其传递到模型中进行预测。



>>> #convert the PIL image to a numpy array 

>>> numpy_image = img_to_array(original) 



>>> plt.imshow(np.uint8(numpy_image)) 

<matplotlib.image.AxesImage object at 0x130475ac8> 



>>> print('numpy array size',numpy_image.shape) 

numpy array size (224, 224, 3) 



>>> # Convert the image / images into batch format 

>>> image_batch = np.expand_dims(numpy_image, axis = 0) 



>>> print('image batch size', image_batch.shape) 

image batch size (1, 224, 224, 3)

>>>

第 4 步：模型预测

让我们将输入输入模型以获得预测



>>> prepare the image for the resnet50 model >>> 

>>> processed_image = resnet50.preprocess_input(image_batch.copy()) 



>>> # create resnet model 

>>>resnet_model = resnet50.ResNet50(weights = 'imagenet') 

>>> Downloavding data from https://github.com/fchollet/deep-learning-models/releas

es/download/v0.2/resnet50_weights_tf_dim_ordering_tf_kernels.h5 

102858752/102853048 [==============================] - 33s 0us/step 



>>> # get the predicted probabilities for each class 

>>> predictions = resnet_model.predict(processed_image) 



>>> # convert the probabilities to class labels 

>>> label = decode_predictions(predictions) 

Downloading data from https://storage.googleapis.com/download.tensorflow.org/

data/imagenet_class_index.json 

40960/35363 [==================================] - 0s 0us/step 



>>> print(label)

输出



[

   [

      ('n07753592', 'banana', 0.99229723), 

      ('n03532672', 'hook', 0.0014551596), 

      ('n03970156', 'plunger', 0.0010738898), 

      ('n07753113', 'fig', 0.0009359837) , 

      ('n03109150', 'corkscrew', 0.00028538404)

   ]

]

在这里，模型正确地将图像预测为香蕉。