def load_models(models_dir): models = {} for model_file in os.listdir(models_dir): with open(os.path.join(models_dir, model_file), 'rb') as f: try: models[model_file] = pickle.load(f)['model'] except pickle.UnpicklingError: continue return models

这是一个加载机器学习模型的函数。其中，models_dir 表示存储模型文件的文件夹。函数首先创建一个空字典 models，然后遍历 models_dir 文件夹中的所有文件。对于每个文件，使用 pickle.load() 函数加载其中存储的模型，并将其存储在 models 字典中。如果加载模型时出现了 UnpicklingError 异常，则跳过该文件。最后，返回加载的所有模型组成的字典。

相关问题

import pickle import numpy as np import os # from scipy.misc import imread def load_CIFAR_batch(filename): with open(filename, 'rb') as f: datadict = pickle.load(f, encoding='bytes') X = datadict[b'data'] Y = datadict[b'labels'] X = X.reshape(10000, 3, 32, 32).transpose(0, 2, 3, 1).astype("float") Y = np.array(Y) return X, Y def load_CIFAR10(ROOT): xs = [] ys = [] for b in range(1, 2): f = os.path.join(ROOT, 'data_batch_%d' % (b,)) X, Y = load_CIFAR_batch(f) xs.append(X) ys.append(Y) Xtr = np.concatenate(xs) Ytr = np.concatenate(ys) del X, Y Xte, Yte = load_CIFAR_batch(os.path.join(ROOT, 'test_batch')) return Xtr, Ytr, Xte, Yte def get_CIFAR10_data(num_training=5000, num_validation=500, num_test=500): cifar10_dir = r'D:\daima\cifar-10-python\cifar-10-batches-py' X_train, y_train, X_test, y_test = load_CIFAR10(cifar10_dir) print(X_train.shape) mask = range(num_training, num_training + num_validation) X_val = X_train[mask] y_val = y_train[mask] mask = range(num_training) X_train = X_train[mask] y_train = y_train[mask] mask = range(num_test) X_test = X_test[mask] y_test = y_test[mask] mean_image = np.mean(X_train, axis=0) X_train -= mean_image X_val -= mean_image X_test -= mean_image X_train = X_train.transpose(0, 3, 1, 2).copy() X_val = X_val.transpose(0, 3, 1, 2).copy() X_test = X_test.transpose(0, 3, 1, 2).copy() return { 'X_train': X_train, 'y_train': y_train, 'X_val': X_val, 'y_val': y_val, 'X_test': X_test, 'y_test': y_test, } def load_models(models_dir): models = {} for model_file in os.listdir(models_dir): with open(os.path.join(models_dir, model_file), 'rb') as f: try: models[model_file] = pickle.load(f)['model'] except pickle.UnpicklingError: continue return models这是一个加载cifar10数据集的函数，如何修改使其能加载mnist数据集，不使用TensorFlow

可以使用以下代码加载MNIST数据集：

import gzip
import os
import pickle
import numpy as np

def load_mnist(path, kind='train'):
    labels_path = os.path.join(path, '%s-labels-idx1-ubyte.gz' % kind)
    images_path = os.path.join(path, '%s-images-idx3-ubyte.gz' % kind)

    with gzip.open(labels_path, 'rb') as lbpath:
        labels = np.frombuffer(lbpath.read(), dtype=np.uint8, offset=8)

    with gzip.open(images_path, 'rb') as imgpath:
        images = np.frombuffer(imgpath.read(), dtype=np.uint8, offset=16).reshape(len(labels), 784)

    return images, labels

def get_mnist_data(num_training=5000, num_validation=500, num_test=500):
    mnist_dir = r'D:\daima\mnist' # 修改为mnist数据集所在的目录
    X_train, y_train = load_mnist(mnist_dir, kind='train')
    X_test, y_test = load_mnist(mnist_dir, kind='t10k')
    print(X_train.shape)

    mask = range(num_training, num_training + num_validation)
    X_val = X_train[mask]
    y_val = y_train[mask]
    mask = range(num_training)
    X_train = X_train[mask]
    y_train = y_train[mask]
    mask = range(num_test)
    X_test = X_test[mask]
    y_test = y_test[mask]

    X_train = X_train.astype('float32') / 255
    X_val = X_val.astype('float32') / 255
    X_test = X_test.astype('float32') / 255

    return {
        'X_train': X_train,
        'y_train': y_train,
        'X_val': X_val,
        'y_val': y_val,
        'X_test': X_test,
        'y_test': y_test,
    }

这个函数将会返回训练集、验证集和测试集的图像和标签。其中，图像是一个形如`(num_samples, 784)`的数组，标签是一个形如`(num_samples,)`的数组。

自定义数据生成器类：由于你没有提供具体的自定义数据生成器类，因此这里没有对其进行修改。如果需要，可以在相应的类中添加 super().__init__(**kwargs)。按照以上要求在代码中添加

为了满足您的需求，在代码中添加自定义数据生成器类，并确保在类初始化方法中调用 `super().__init__(**kwargs)`。以下是修改后的代码片段：

import os
import json
import numpy as np
import pandas as pd
from PIL import Image
import tensorflow as tf
from sklearn.model_selection import train_test_split
from tensorflow.keras.applications.resnet50 import ResNet50
from tensorflow.keras.models import Model
from tensorflow.keras.layers import Dense, GlobalAveragePooling2D, Dropout
from tensorflow.keras.preprocessing.image import ImageDataGenerator
from tensorflow.keras.optimizers import Adam
from sklearn.metrics import f1_score, accuracy_score

# 自定义数据生成器类
class CustomImageDataGenerator(ImageDataGenerator):
    def __init__(self, **kwargs):
        super().__init__(**kwargs)
        # 可以在这里添加其他自定义参数或方法

# 定义路径常量
TRAIN_DATA_DIR = "C:\\Users\\24067\\Desktop\\peach_split\\train"
VAL_DATA_DIR = "C:\\Users\\24067\\Desktop\\peach_split\\val"
TEST_DATA_DIR = "C:\\Users\\24067\\Desktop\\peach_split\\test"
TRAIN_LABEL_PATH = "C:\\Users\\24067\\Desktop\\train_label.json"
VAL_LABEL_PATH = "C:\\Users\\24067\\Desktop\\val_label.json"
OUTPUT_PATH = "C:\\Users\\24067\\Desktop\\data\\submission.csv"

# 加载数据集
def load_data(data_dir, label_path):
    with open(label_path, 'r') as f:
        labels_list = json.load(f)
    labels = {item['文件名']: item['标签'] for item in labels_list if '文件名' in item and '标签' in item}
    images = []
    targets = []
    for file_name, label in labels.items():
        img_path = os.path.join(data_dir, file_name)
        if not os.path.exists(img_path):
            continue
        img = Image.open(img_path).resize((128, 128))
        img_array = np.array(img) / 255.0
        images.append(img_array)
        targets.append(label)
    if len(images) == 0:
        raise ValueError("No valid images found.")
    return np.array(images), np.array(targets)

# 加载训练集和验证集
X_train, y_train = load_data(TRAIN_DATA_DIR, TRAIN_LABEL_PATH)
X_val, y_val = load_data(VAL_DATA_DIR, VAL_LABEL_PATH)

# 标签映射
label_map = {'特级': 3, '一级': 2, '二级': 1, '三级': 0}
y_train = np.array([label_map[label] for label in y_train])
y_val = np.array([label_map[label] for label in y_val])

# 创建模型
def create_resnet_model(input_shape=(128, 128, 3)):
    base_model = ResNet50(weights=None, include_top=False, input_shape=input_shape)
    x = base_model.output
    x = GlobalAveragePooling2D()(x)
    x = Dense(256, activation='relu')(x)
    x = Dropout(0.5)(x)
    predictions = Dense(4, activation='softmax')(x)
    model = Model(inputs=base_model.input, outputs=predictions)
    return model

# 实例化模型
model = create_resnet_model()

# 编译模型
model.compile(optimizer=Adam(learning_rate=0.0001), loss='sparse_categorical_crossentropy', metrics=['accuracy'])

# 图像增强
datagen = CustomImageDataGenerator(
    rotation_range=20,
    width_shift_range=0.2,
    height_shift_range=0.2,
    shear_range=0.15,
    zoom_range=0.15,
    horizontal_flip=True,
    vertical_flip=True,
    fill_mode='nearest'
)

# 训练模型
history = model.fit(datagen.flow(X_train, y_train, batch_size=32), epochs=50, validation_data=(X_val, y_val))

# 评估模型
def evaluate_model(model, X, y):
    predictions = model.predict(X)
    predicted_labels = np.argmax(predictions, axis=1)
    accuracy = accuracy_score(y, predicted_labels)
    f1 = f1_score(y, predicted_labels, average='weighted')
    print(f'Accuracy: {accuracy:.4f}')
    print(f'F1 Score: {f1:.4f}')
    return accuracy, f1

evaluate_model(model, X_val, y_val)

# 预测测试集并保存结果
def predict_and_save(test_data_dir, output_path):
    test_images = []
    test_file_names = []
    # 遍历测试集目录中的所有图像文件
    for file_name in os.listdir(test_data_dir):
        img_path = os.path.join(test_data_dir, file_name)
        if not os.path.exists(img_path) or not file_name.lower().endswith(('.png', '.jpg', '.jpeg')):
            continue
        img = Image.open(img_path).resize((128, 128))
        img_array = np.array(img) / 255.0
        test_images.append(img_array)
        test_file_names.append(file_name)
    test_images = np.array(test_images)
    predictions = model.predict(test_images)
    predicted_labels = np.argmax(predictions, axis=1)
    label_map_inv = {v: k for k, v in label_map.items()}
    predicted_labels = [label_map_inv[label] for label in predicted_labels]
    submission_df = pd.DataFrame({'文件名': test_file_names, '标签': predicted_labels})
    submission_df.to_csv(output_path, index=False)

# 进行预测并保存结果
predict_and_save(TEST_DATA_DIR, OUTPUT_PATH)

在这个版本中，我们创建了一个名为 `CustomImageDataGenerator` 的自定义数据生成器类，并在其中调用了 `super().__init__(**kwargs)`。这样可以确保继承了 `ImageDataGenerator` 类的所有功能，并且可以根据需要添加额外的自定义逻辑。