我建立了一个CNN模型来检测图像上的两种缺陷。这些类都是“大”和“小”的,而且准确度真的很好。我的模型的架构如下:
inputs = tf.keras.Input(shape=(120, 120, 3))
x = tf.keras.layers.Conv2D(filters=16, kernel_size=(3, 3), activation='relu')(inputs)
x = tf.keras.layers.MaxPool2D(pool_size=(2, 2))(x)
x = tf.keras.layers.Conv2D(filters=32, kernel_size=(3, 3), activation='relu')(x)
x = tf.keras.layers.MaxPool2D(pool_size=(2, 2))(x)
x = tf.keras.layers.GlobalAveragePooling2D()(x)
outputs = tf.keras.layers.Dense(1, activation='sigmoid')(x)
model = tf.keras.Model(inputs=inputs, outputs=outputs)
model.compile(
optimizer='adam',
loss='binary_crossentropy',
metrics=['accuracy']
)
print(model.summary())
history = model.fit(
train_data,
validation_data=val_data,
epochs=100,
callbacks=[
tf.keras.callbacks.EarlyStopping(
monitor='val_loss',
patience=3,
restore_best_weights=True
)
]
)
现在,我想将CNN模型用于多个类,类将是“大”、“小”、“其他”。我有数据集,但我不知道如何更改三个类的模型。此外,在最后,我想测试一个图像到我的CNN模型,并获得标签,如果插入的图像是大,小或其他,但我不知道如何。
发布于 2021-09-08 14:01:47
试试这个:
model = tf.keras.Sequential()
model.add(tf.keras.layers.Conv2D(input_shape = (120, 120, 3), filters=16, kernel_size=(3, 3), activation='relu'))
model.add(tf.keras.layers.MaxPool2D(pool_size=(2, 2)))
model.add(tf.keras.layers.Conv2D(filters=32, kernel_size=(3, 3), activation='relu'))
model.add(tf.keras.layers.MaxPool2D(pool_size=(2, 2)))
model.add(tf.keras.layers.GlobalAveragePooling2D())
model.add(tf.keras.layers.Dense(3, activation='softmax'))
model.compile(optimizer='adam', loss='sparse_categorical_crossentropy', metrics=['accuracy'])
要进行预测,您可以使用以下代码:
from PIL import Image
import numpy as np
from skimage import transform
def load(filename):
np_image = Image.open(filename)
np_image = np.array(np_image).astype('float32')/255
np_image = transform.resize(np_image, (120, 120, 3))
np_image = np.expand_dims(np_image, axis=0)
return np_image
folder_path = 'Dataset/test/4.jpg'
image = load(folder_path)
pred = model.predict_classes(image)
pred.tolist()[0]
https://stackoverflow.com/questions/69103940
复制相似问题