测试集并不存在标签文件,但是最终要在训练后要用于最终的模型性能评估,生成正确的文件名和标签,请修改正确的代码
时间: 2024-10-26 07:02:40 浏览: 42
卡通人物猫和老鼠的图像数据集,共484张图片
5星 · 资源好评率100%
为了处理测试集没有标签文件的问题,并生成最终的预测结果文件(包含文件名和预测标签),我们需要对 `predict_and_save` 函数进行一些调整。具体来说,我们不再从 JSON 文件中读取测试集的标签,而是直接遍历测试集目录中的所有图像文件,并生成预测结果。
以下是修改后的代码:
```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.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
# 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 = ImageDataGenerator(
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)
```
### 主要修改点:
1. **移除了测试集标签文件的加载**:不再从 `test_label.json` 文件中读取标签。
2. **遍历测试集目录中的所有图像文件**:使用 `os.listdir` 遍历测试集目录中的所有图像文件,并将其加载到内存中。
3. **生成预测结果**:对测试集中的每张图像进行预测,并将预测结果保存到 DataFrame 中。
4. **保存预测结果**:将预测结果保存到指定的输出路径 `OUTPUT_PATH`。
这样,即使测试集没有标签文件,也可以生成包含文件名和预测标签的结果文件。
阅读全文