把其中的训练模型替换为ResNet-50,并将训练模型保存在路径"C:\Users\24067\Desktop\data"下,将完整代码列出
时间: 2024-10-26 18:16:08 浏览: 24
以下是修改后的代码,使用了ResNet-50作为模型,并且在训练完成后将模型保存到指定路径:
```python
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.layers import Dense, GlobalAveragePooling2D
from tensorflow.keras.models import Model
from tensorflow.keras.preprocessing.image import ImageDataGenerator
from tensorflow.keras.optimizers import Adam
from sklearn.metrics import f1_score, accuracy_score
# 定义数据路径
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"
MODEL_SAVE_PATH = "C:\\Users\\24067\\Desktop\\data\\resnet50_model.h5"
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((224, 224))
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)
# 加载训练数据
train_images, train_labels = load_data(TRAIN_DATA_DIR, TRAIN_LABEL_PATH)
# 加载验证数据
val_images, val_labels = 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}
train_labels = np.array([label_map[label] for label in train_labels])
val_labels = np.array([label_map[label] for label in val_labels])
# 创建模型
def create_model(input_shape=(224, 224, 3)):
base_model = ResNet50(weights='imagenet', include_top=False, input_shape=input_shape)
x = base_model.output
x = GlobalAveragePooling2D()(x)
x = Dense(128, 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_model()
# 冻结基础模型的层
for layer in model.layers[:-5]:
layer.trainable = False
# 编译模型
model.compile(optimizer=Adam(learning_rate=0.001), loss='sparse_categorical_crossentropy', metrics=['accuracy'])
# 图像增强
datagen = ImageDataGenerator(
rotation_range=20,
width_shift_range=0.2,
height_shift_range=0.2,
horizontal_flip=True,
vertical_flip=True
)
# 训练模型
history = model.fit(datagen.flow(train_images, train_labels, batch_size=32),
epochs=10,
validation_data=(val_images, val_labels))
# 保存模型
model.save(MODEL_SAVE_PATH)
# 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, val_images, val_labels)
# 预测测试集并保存结果
def predict_and_save(test_data_dir, test_label_path, output_path):
test_images = []
test_file_names = []
with open(test_label_path, 'r') as f:
test_labels_list = json.load(f)
test_labels = {item['文件名']: item['标签'] for item in test_labels_list if '文件名' in item and '标签' in item}
for file_name in test_labels.keys():
img_path = os.path.join(test_data_dir, file_name)
if not os.path.exists(img_path):
continue
img = Image.open(img_path).resize((224, 224))
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, TEST_LABEL_PATH, OUTPUT_PATH)
```
### 主要修改点:
1. **模型部分**:使用了ResNet-50作为基础模型,并添加了一个全局平均池化层和一个全连接层。
2. **图像尺寸**:调整图像尺寸为224x224,以适应ResNet-50的要求。
3. **模型保存**:在训练完成后,将模型保存到指定路径`MODEL_SAVE_PATH`。
4. **训练轮数**:增加训练轮数至10轮(可以根据实际情况调整)。
这样修改后,代码将使用ResNet-50进行训练,并在训练完成后保存模型。
阅读全文