将下面一段话翻译成英文;ImageClassifier类实现过程：1__init__selfmodel_config_pathmodel_weights_pathcat_to_label_path cat_to_name_path 初始化方法接收四个参数分别是模型配置文件路径、模型权重文件路径、类别到标签的映射文件路径和类别到名称的映射文件路径。在初始化过程中保存传入的路径到类的成员变量中并调用l

Implementation of ImageClassifier class:

1. init(self, model_config_path, model_weights_path, cat_to_label_path, cat_to_name_path): Initialization method that receives four parameters: model configuration file path, model weights file path, category-to-label mapping file path, and category-to-name mapping file path. During initialization, save the passed paths to class member variables and call load_model() method to load the model, load_class_index_dict() method to load the category label mapping, and load_classname() method to load the category name mapping.
2. load_model(self): Method to load the model. First, a pre-trained MobileNet model is created as the base model, and a custom model is built on top of it by adding a global average pooling layer and a fully connected layer. Then, the model configuration information is loaded using the model configuration file path, and the model weights are loaded using the model weights file path. Finally, the model is compiled using the Adam optimizer and the cross-entropy loss function, and the loaded and compiled model object is returned.
3. load_class_index_dict(self): Method to load the category label mapping. The category label mapping is loaded using the category-to-label mapping file path and stored in the class_index_dict. The category label mapping dictionary is then returned.
4. load_classname(self): Method to load the category name mapping. The category name mapping is loaded using the category-to-name mapping file path and stored in classname. The category name mapping dictionary is then returned.
5. predict_image(self, image_path): Image classification prediction method that receives an image path as a parameter. First, the image is opened using Image.open() from the PIL library and resized to 224x224 pixels. Then, the image is converted to a NumPy array and normalized. Next, the image array is expanded by one dimension to match the model input requirements. The model is then used to predict the image classification and returns the probability distribution of the prediction results. The class index with the highest probability is then obtained from the prediction results. Based on the class index, the corresponding category label is obtained from the category label mapping, and the corresponding category name is obtained from the category name mapping. Finally, the predicted category label and category name are returned. After 30 rounds of training, the accuracy of the trained model gradually improved, and the loss gradually decreased