ResNet 模型實現即時預測

ResNet 是一個預訓練的模型。它是使用 ImageNet 進行訓練的。ResNet 模型的權值預訓練於 ImageNet。它的語法如下 -

keras.applications.resnet.ResNet50 (
   include_top = True, 
   weights = 'imagenet', 
   input_tensor = None, 
   input_shape = None, 
   pooling = None, 
   classes = 1000
)

此處，

• include_top 表示網路頂部的全連線層。

• weights 表示在 ImageNet 上的預訓練。

• input_tensor 表示可選的 Keras 張量，用作模型的影像輸入。

• input_shape 表示可選的形狀元組。此模型的預設輸入大小為 224x224。

• classes 表示對影像進行分類的可選類別數。

讓我們透過編寫一個簡單示例來了解該模型 -

步驟 1：匯入模組

讓我們載入如下指定的必要模組 -

>>> 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

步驟 2：選擇輸入

讓我們選擇一個輸入影像，Lotus 如下指定 -

>>> 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()

此處，我們載入了一張圖片 (banana.jpg) 並顯示了它。

步驟 3：將圖片轉換為 NumPy 陣列

讓我們將我們的輸入，Banana 轉換為 NumPy 陣列，以便將其傳遞給模型進行預測。

>>> #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)
>>> 

步驟 4：模型預測

讓我們將我們的輸入輸入模型以獲得預測

>>> 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)

輸出

[
   [
      ('n07753592', 'banana', 0.99229723), 
      ('n03532672', 'hook', 0.0014551596), 
      ('n03970156', 'plunger', 0.0010738898), 
      ('n07753113', 'fig', 0.0009359837) , 
      ('n03109150', 'corkscrew', 0.00028538404)
   ]
]

在此，模型正確地將影像預測為香蕉。