keras 迁移学习模型学习不多，确认平台在45%，而培训上升到90%

nuypyhwy 于 2023-01-21 发布在其他

关注(0)|答案(1)|浏览(118)

所以我花了很多时间在这个图像分类模型上。我有70000张图像和375个类。我试着用Vgg 16，Xception，Resnet和Mobilenet训练它......我总是得到相同的45%的验证限制。
As you can see here
我试过添加丢失层和正则化，它得到了相同的验证结果，数据扩增也没有多大帮助，你知道为什么这不起作用吗？
下面是我使用的上一个模型的代码片段：

from keras.models import Sequential
from keras.layers import Dense
from tensorflow import keras
from tensorflow.keras.preprocessing.image import ImageDataGenerator
from keras import regularizers
from PIL import Image
from PIL import ImageFile
ImageFile.LOAD_TRUNCATED_IMAGES = True

validation_datagen = ImageDataGenerator(rescale=1./255)
target_size = (height, width)

datagen = ImageDataGenerator(rescale=1./255,
    validation_split=0.2)

train_generator = datagen.flow_from_directory(
    path,
    target_size=(height, width),
    batch_size=batchSize,
    shuffle=True,
    class_mode='categorical',
    subset='training')

validation_generator = datagen.flow_from_directory(
    path,
    target_size=(height, width),
    batch_size=batchSize,
    class_mode='categorical',
    subset='validation')

num_classes = len(train_generator.class_indices)


xception_model = Xception(weights='imagenet',input_shape=(width, height, 3), include_top=False,classes=num_classes)
x = xception_model.output
x = GlobalAveragePooling2D()(x)
x = Dense(512, activation='relu')(x)
out = Dense(num_classes, activation='softmax')(x)

opt = Adam()
model.compile(optimizer=opt, loss='categorical_crossentropy', metrics=['accuracy'])

n_时间点= 15
历史记录=model.fit（训练生成器，每个epoch的步骤数=训练生成器.样本//批次大小，验证数据=验证生成器，验证步骤数=验证生成器.样本//批次大小，详细信息=1，epoch = n_epoch）

keras

来源：https://stackoverflow.com/questions/74934614/transfer-learning-model-not-learning-much-validation-plateau-at-45-while-train

1条答案

按热度按时间

vmdwslir1#

是的，您可能需要数据集中每个类别之间的平衡数据集，以获得更好的模型训练性能。请通过更改class_mode='sparse'和loss='sparse_categorical_crossentropy'重试，因为您正在使用图像数据集。另外，冻结预训练模型层'xception_model.trainable = False'。
检查以下代码：（我使用了5个类的花卉数据集）

xception_model = tf.keras.applications.Xception(weights='imagenet',input_shape=(width, height, 3), include_top=False,classes=num_classes)
xception_model.trainable = False
x = xception_model.output
x = GlobalAveragePooling2D()(x)
x = Dense(32, activation='relu')(x)
out = Dense(num_classes, activation='softmax')(x)

opt = tf.keras.optimizers.Adam()
model = keras.Model(inputs=xception_model.input, outputs=out)
model.compile(optimizer=opt, loss='sparse_categorical_crossentropy', metrics=['accuracy'])
history = model.fit(train_generator,  epochs=10, validation_data=validation_generator)

输出：

Epoch 1/10
217/217 [==============================] - 23s 95ms/step - loss: 0.5945 - accuracy: 0.7793 - val_loss: 0.4610 - val_accuracy: 0.8337
Epoch 2/10
217/217 [==============================] - 20s 91ms/step - loss: 0.3439 - accuracy: 0.8797 - val_loss: 0.4550 - val_accuracy: 0.8419
Epoch 3/10
217/217 [==============================] - 20s 93ms/step - loss: 0.2570 - accuracy: 0.9150 - val_loss: 0.4437 - val_accuracy: 0.8384
Epoch 4/10
217/217 [==============================] - 20s 91ms/step - loss: 0.2040 - accuracy: 0.9340 - val_loss: 0.4592 - val_accuracy: 0.8477
Epoch 5/10
217/217 [==============================] - 20s 91ms/step - loss: 0.1649 - accuracy: 0.9494 - val_loss: 0.4686 - val_accuracy: 0.8512
Epoch 6/10
217/217 [==============================] - 20s 92ms/step - loss: 0.1301 - accuracy: 0.9589 - val_loss: 0.4805 - val_accuracy: 0.8488
Epoch 7/10
217/217 [==============================] - 20s 93ms/step - loss: 0.0966 - accuracy: 0.9754 - val_loss: 0.4993 - val_accuracy: 0.8442
Epoch 8/10
217/217 [==============================] - 20s 91ms/step - loss: 0.0806 - accuracy: 0.9806 - val_loss: 0.5488 - val_accuracy: 0.8372
Epoch 9/10
217/217 [==============================] - 20s 91ms/step - loss: 0.0623 - accuracy: 0.9864 - val_loss: 0.5802 - val_accuracy: 0.8360
Epoch 10/10
217/217 [==============================] - 22s 100ms/step - loss: 0.0456 - accuracy: 0.9896 - val_loss: 0.6005 - val_accuracy: 0.8360

赞(0）回复(0）举报 2023-01-21

我来回答

keras 迁移学习模型学习不多，确认平台在45%，而培训上升到90%

1条答案

相关问题

热门标签

最新问答