解决TensorFlow模型预测中的输入形状不匹配问题

ValueError: Input 0 of layer "sequential" is incompatible with the layer: expected shape=(None, 180, 180, 3), found shape=(None, 180, 3)

import tensorflow as tf
from tensorflow import keras
from tensorflow.keras import layers
from tensorflow.keras.models import Sequential

# ... (其他导入和变量定义，如 img_height, img_width, num_classes)

img_height = 180
img_width = 180
channels = 3 # 通常为3代表RGB图像

model = Sequential([
    # 显式定义输入层，指定期望的图片尺寸和通道数
    layers.InputLayer(input_shape=(img_height, img_width, channels)),
    layers.Rescaling(1./255), # 归一化层，通常放在InputLayer之后
    layers.Conv2D(16, 3, padding='same', activation='relu'),
    layers.MaxPooling2D(),
    layers.Conv2D(32, 3, padding='same', activation='relu'),
    layers.MaxPooling2D(),
    layers.Conv2D(64, 3, padding='same', activation='relu'),
    layers.MaxPooling2D(),
    layers.Flatten(),
    layers.Dense(128, activation='relu'),
    layers.Dense(num_classes)
])

model.compile(optimizer='adam',
              loss=tf.keras.losses.SparseCategoricalCrossentropy(from_logits=True),
              metrics=['accuracy'])

# 有了InputLayer，通常不需要手动调用 model.build()，Keras会在第一次调用时自动构建
# model.build((None,180,180,3))
model.summary()

import numpy as np
import cv2

# ... (其他导入和变量定义)

img_height = 180
img_width = 180

# 加载并预处理图片
image_path = "C:\anImage\c000b634560ef3c9211cbf9e08ebce74.jpg"
image = cv2.imread(image_path)
if image is None:
    print(f"Error: Could not load image from {image_path}")
    exit()

# 调整图片大小
image = cv2.resize(image, (img_width, img_height))

# 转换为float32类型
# 注意：如果模型中有layers.Rescaling(1./255)，则输入图片应保持0-255的像素值范围。
# 如果没有Rescaling层，则需要手动将像素值归一化到0-1或-1到1。
image = np.asarray(image).astype('float32')

# 关键步骤：添加批次维度
# 方法一：使用 np.expand_dims
image_batch = np.expand_dims(image, axis=0) # 形状变为 (1, 180, 180, 3)

# 方法二：使用 np.newaxis
# image_batch = image[np.newaxis, ...] # 形状同样变为 (1, 180, 180, 3)

print(f"单张图片原始形状: {image.shape}")
print(f"添加批次维度后形状: {image_batch.shape}")

# 现在可以安全地进行预测
# model.predict(image_batch)

import matplotlib.pyplot as plt
import numpy as np
import os
import PIL
import tensorflow as tf
import cv2
from tensorflow import keras
from tensorflow.keras import layers
from tensorflow.keras.models import Sequential
import pathlib

# 定义图像尺寸和通道数
img_height = 180
img_width = 180
channels = 3 # RGB图像

# 数据集路径（用于模型训练，这里仅为完整性展示）
data_dir = pathlib.Path("C:\diseases\train")
valid_dir = pathlib.Path("C:\diseases\valid")

# 检查路径是否存在，避免后续错误
if not data_dir.exists() or not valid_dir.exists():
    print("Error: Dataset directories not found. Please adjust paths.")
    # For demonstration, we'll proceed, but in real scenario, you'd handle this.
    # Creating dummy datasets for model building if paths don't exist
    # This part is just to make the code runnable for model definition
    # In a real scenario, ensure your data paths are correct.
    print("Creating dummy dataset for model definition only...")
    train_ds = tf.data.Dataset.from_tensor_slices(np.random.rand(10, img_height, img_width, channels).astype('float32'))
    val_ds = tf.data.Dataset.from_tensor_slices(np.random.rand(2, img_height, img_width, channels).astype('float32'))
    class_names = ['class_a', 'class_b'] # Dummy class names
else:
    train_ds = tf.keras.utils.image_dataset_from_directory(
        data_dir,
        validation_split=0.2,
        subset="training",
        seed=123,
        image_size=(img_height, img_width),
        batch_size=32)

    val_ds = tf.keras.utils.image_dataset_from_directory(
        valid_dir,
        validation_split=0.2, # Note: validation_split on val_ds might be unusual, usually it's on main_data_dir
        subset="validation",
        seed=123,
        image_size=(img_height, img_width),
        batch_size=32)

    class_names = train_ds.class_names

num_classes = len(class_names)

# 构建模型：显式定义InputLayer
model = Sequential([
    layers.InputLayer(input_shape=(img_height, img_width, channels)), # 明确指定输入形状
    layers.Rescaling(1./255), # 归一化层
    layers.Conv2D(16, 3, padding='same', activation='relu'),
    layers.MaxPooling2D(),
    layers.Conv2D(32, 3, padding='same', activation='relu'),
    layers.MaxPooling2D(),
    layers.Conv2D(64, 3, padding='same', activation='relu'),
    layers.MaxPooling2D(),
    layers.Flatten(),
    layers.Dense(128, activation='relu'),
    layers.Dense(num_classes)
])

model.compile(optimizer='adam',
              loss=tf.keras.losses.SparseCategoricalCrossentropy(from_logits=True),
              metrics=['accuracy'])

model.summary()

# 模型训练（示例）
epochs = 1
# Ensure train_ds and val_ds are not None or empty for fitting
if 'train_ds' in locals() and train_ds is not None and 'val_ds' in locals() and val_ds is not None:
    try:
        history = model.fit(
            train_ds,
            validation_data=val_ds,
            epochs=epochs
        )
    except Exception as e:
        print(f"Error during model fitting (might be due to dummy data): {e}")
else:
    print("Skipping model fitting due to missing dataset.")


# 单张图片预测
image_to_predict_path = "C:\anImage\c000b634560ef3c9211cbf9e08ebce74.jpg"

# 检查图片路径是否存在
if not os.path.exists(image_to_predict_path):
    print(f"Error: Image for prediction not found at {image_to_predict_path}. Using a dummy image.")
    # 创建一个随机的虚拟图片用于演示
    dummy_image = np.random.randint(0, 256, size=(img_height, img_width, channels), dtype=np.uint8)
    image = dummy_image
else:
    image = cv2.imread(image_to_predict_path)
    if image is None:
        print(f"Error: Could not load image from {image_to_predict_path}. Using a dummy image.")
        dummy_image = np.random.randint(0, 256, size=(img_height, img_width, channels), dtype=np.uint8)
        image = dummy_image

# 调整图片大小并转换为float32
image = cv2.resize(image, (img_width, img_height))
image = np.asarray(image).astype('float32')

# 关键步骤：添加批次维度
image_batch = np.expand_dims(image, axis=0) # 形状变为 (1, 180, 180, 3)

print(f"
准备预测的图片形状: {image_batch.shape}")

# 进行预测
try:
    predictions = model.predict(image_batch)
    print("预测结果 (logits):", predictions)
    # 将logits转换为概率（如果模型最后一层没有激活函数）
    probabilities = tf.nn.softmax(predictions[0])
    print("预测结果 (概率):", probabilities.numpy())
    predicted_class_index = np.argmax(probabilities)
    print(f"预测类别索引: {predicted_class_index}")
    if class_names:
        print(f"预测类别名称: {class_names[predicted_class_index]