为什么我在 Keras 中的 resnet50 模型不收敛？
Why is my resnet50 model in Keras not converging?
我目前正在尝试对有缺陷和无缺陷图像中的集成电路进行分类。我已经尝试过 VGG16 和 InceptionV3，并且两者都获得了非常好的结果（95% 的验证准确率和低 val 损失）。现在我想尝试 resnet50，但我的模型没有收敛。它的准确率也是 95%，但验证损失不断增加，而 val acc 卡在 50%。
到目前为止，这是我的脚本：
from keras.applications.resnet50 import ResNet50
from keras.optimizers import Adam
from keras.preprocessing import image
from keras.models import Model
from keras.layers import Dense, GlobalAveragePooling2D, Dropout
from keras import backend as K
from keras_preprocessing.image import ImageDataGenerator
import tensorflow as tf
class ResNet:
def __init__(self):
self.img_width, self.img_height = 224, 224 # Dimensions of cropped image
self.classes_num = 2 # Number of classifications
# Training configurations
self.epochs = 32
self.batch_size = 16 # Play with this to determine number of images to train on per epoch
self.lr = 0.0001
def build_model(self, train_path):
train_data_path = train_path
train_datagen = ImageDataGenerator(rescale=1. / 255, validation_split=0.25)
train_generator = train_datagen.flow_from_directory(
train_data_path,
target_size=(self.img_height, self.img_width),
color_mode="rgb",
batch_size=self.batch_size,
class_mode='categorical',
subset='training')
validation_generator = train_datagen.flow_from_directory(
train_data_path,
target_size=(self.img_height, self.img_width),
color_mode="rgb",
batch_size=self.batch_size,
class_mode='categorical',
subset='validation')
# create the base pre-trained model
base_model = ResNet50(weights='imagenet', include_top=False, input_shape= (self.img_height, self.img_width, 3))
# add a global spatial average pooling layer
x = base_model.output
x = GlobalAveragePooling2D()(x)
# let's add a fully-connected layer
x = Dense(1024, activation='relu')(x)
#x = Dropout(0.3)(x)
# and a logistic layer -- let's say we have 200 classes
predictions = Dense(2, activation='softmax')(x)
# this is the model we will train
model = Model(inputs=base_model.input, outputs=predictions)
# first: train only the top layers (which were randomly initialized)
# i.e. freeze all convolutional InceptionV3 layers
for layer in base_model.layers:
layer.trainable = True
# compile the model (should be done *after* setting layers to non-trainable)
opt = Adam(self.lr) # , decay=self.INIT_LR / self.NUM_EPOCHS)
model.compile(opt, loss='binary_crossentropy', metrics=["accuracy"])
# train the model on the new data for a few epochs
from keras.callbacks import ModelCheckpoint, EarlyStopping
import matplotlib.pyplot as plt
checkpoint = ModelCheckpoint('resnetModel.h5', monitor='val_accuracy', verbose=1, save_best_only=True,
save_weights_only=False, mode='auto', period=1)
early = EarlyStopping(monitor='val_accuracy', min_delta=0, patience=16, verbose=1, mode='auto')
hist = model.fit_generator(steps_per_epoch=self.batch_size, generator=train_generator,
validation_data=validation_generator, validation_steps=self.batch_size, epochs=self.epochs,
callbacks=[checkpoint, early])
plt.plot(hist.history['accuracy'])
plt.plot(hist.history['val_accuracy'])
plt.plot(hist.history['loss'])
plt.plot(hist.history['val_loss'])
plt.title("model accuracy")
plt.ylabel("Accuracy")
plt.xlabel("Epoch")
plt.legend(["Accuracy", "Validation Accuracy", "loss", "Validation Loss"])
plt.show()
plt.figure(1)
import tensorflow as tf
if __name__ == '__main__':
x = ResNet()
config = tf.compat.v1.ConfigProto()
config.gpu_options.allow_growth = True
sess = tf.compat.v1.Session(config=config)
x.build_model("C:/Users/but/Desktop/dataScratch/Train")
这是模型的训练
resnet 失败但 vgg 和 inception 起作用的原因可能是什么？
我的脚本有什么错误吗？
至少对于代码，我没有看到任何可能影响训练过程的错误。
# and a logistic layer -- let's say we have 200 classes
predictions = Dense(2, activation='softmax')(x)
这些台词有点可疑。不过好像是评论上的错字，所以应该没问题。
# first: train only the top layers (which were randomly initialized)
# i.e. freeze all convolutional InceptionV3 layers
for layer in base_model.layers:
layer.trainable = True
这些也很可疑。如果你想冻结 ResNet-50 的图层，你需要做的是
...
base_model = ResNet50(weights='imagenet', include_top=False, input_shape=(self.img_height, self.img_width, 3))
for layer in base_model.layers:
layer.trainable = False
...
但结果layer.trainable = True其实是你的本意，所以也没关系。
首先，如果您使用的是用于训练 VGG16 和 Inception V3 的相同代码，则不太可能是代码问题。
为什么不检查以下易感原因？
- 模型可能太 small/big 而 underfits/overfits。 （参数数量）
- 模型可能需要更多时间收敛。 （训练更多 epochs）
- ResNet 可能不适合此分类。
- 您使用的预训练权重可能不适合此分类。
- 学习率可能太大small/big。
- 等...
我目前正在尝试对有缺陷和无缺陷图像中的集成电路进行分类。我已经尝试过 VGG16 和 InceptionV3，并且两者都获得了非常好的结果（95% 的验证准确率和低 val 损失）。现在我想尝试 resnet50，但我的模型没有收敛。它的准确率也是 95%，但验证损失不断增加，而 val acc 卡在 50%。
到目前为止，这是我的脚本：
from keras.applications.resnet50 import ResNet50
from keras.optimizers import Adam
from keras.preprocessing import image
from keras.models import Model
from keras.layers import Dense, GlobalAveragePooling2D, Dropout
from keras import backend as K
from keras_preprocessing.image import ImageDataGenerator
import tensorflow as tf
class ResNet:
def __init__(self):
self.img_width, self.img_height = 224, 224 # Dimensions of cropped image
self.classes_num = 2 # Number of classifications
# Training configurations
self.epochs = 32
self.batch_size = 16 # Play with this to determine number of images to train on per epoch
self.lr = 0.0001
def build_model(self, train_path):
train_data_path = train_path
train_datagen = ImageDataGenerator(rescale=1. / 255, validation_split=0.25)
train_generator = train_datagen.flow_from_directory(
train_data_path,
target_size=(self.img_height, self.img_width),
color_mode="rgb",
batch_size=self.batch_size,
class_mode='categorical',
subset='training')
validation_generator = train_datagen.flow_from_directory(
train_data_path,
target_size=(self.img_height, self.img_width),
color_mode="rgb",
batch_size=self.batch_size,
class_mode='categorical',
subset='validation')
# create the base pre-trained model
base_model = ResNet50(weights='imagenet', include_top=False, input_shape= (self.img_height, self.img_width, 3))
# add a global spatial average pooling layer
x = base_model.output
x = GlobalAveragePooling2D()(x)
# let's add a fully-connected layer
x = Dense(1024, activation='relu')(x)
#x = Dropout(0.3)(x)
# and a logistic layer -- let's say we have 200 classes
predictions = Dense(2, activation='softmax')(x)
# this is the model we will train
model = Model(inputs=base_model.input, outputs=predictions)
# first: train only the top layers (which were randomly initialized)
# i.e. freeze all convolutional InceptionV3 layers
for layer in base_model.layers:
layer.trainable = True
# compile the model (should be done *after* setting layers to non-trainable)
opt = Adam(self.lr) # , decay=self.INIT_LR / self.NUM_EPOCHS)
model.compile(opt, loss='binary_crossentropy', metrics=["accuracy"])
# train the model on the new data for a few epochs
from keras.callbacks import ModelCheckpoint, EarlyStopping
import matplotlib.pyplot as plt
checkpoint = ModelCheckpoint('resnetModel.h5', monitor='val_accuracy', verbose=1, save_best_only=True,
save_weights_only=False, mode='auto', period=1)
early = EarlyStopping(monitor='val_accuracy', min_delta=0, patience=16, verbose=1, mode='auto')
hist = model.fit_generator(steps_per_epoch=self.batch_size, generator=train_generator,
validation_data=validation_generator, validation_steps=self.batch_size, epochs=self.epochs,
callbacks=[checkpoint, early])
plt.plot(hist.history['accuracy'])
plt.plot(hist.history['val_accuracy'])
plt.plot(hist.history['loss'])
plt.plot(hist.history['val_loss'])
plt.title("model accuracy")
plt.ylabel("Accuracy")
plt.xlabel("Epoch")
plt.legend(["Accuracy", "Validation Accuracy", "loss", "Validation Loss"])
plt.show()
plt.figure(1)
import tensorflow as tf
if __name__ == '__main__':
x = ResNet()
config = tf.compat.v1.ConfigProto()
config.gpu_options.allow_growth = True
sess = tf.compat.v1.Session(config=config)
x.build_model("C:/Users/but/Desktop/dataScratch/Train")
这是模型的训练
resnet 失败但 vgg 和 inception 起作用的原因可能是什么？ 我的脚本有什么错误吗？
至少对于代码，我没有看到任何可能影响训练过程的错误。
# and a logistic layer -- let's say we have 200 classes
predictions = Dense(2, activation='softmax')(x)
这些台词有点可疑。不过好像是评论上的错字，所以应该没问题。
# first: train only the top layers (which were randomly initialized)
# i.e. freeze all convolutional InceptionV3 layers
for layer in base_model.layers:
layer.trainable = True
这些也很可疑。如果你想冻结 ResNet-50 的图层，你需要做的是
...
base_model = ResNet50(weights='imagenet', include_top=False, input_shape=(self.img_height, self.img_width, 3))
for layer in base_model.layers:
layer.trainable = False
...
但结果layer.trainable = True其实是你的本意，所以也没关系。
首先，如果您使用的是用于训练 VGG16 和 Inception V3 的相同代码，则不太可能是代码问题。
为什么不检查以下易感原因？
- 模型可能太 small/big 而 underfits/overfits。 （参数数量）
- 模型可能需要更多时间收敛。 （训练更多 epochs）
- ResNet 可能不适合此分类。
- 您使用的预训练权重可能不适合此分类。
- 学习率可能太大small/big。
- 等...