【发布时间】：2017-11-19 23:02:41
【问题描述】：
我基本上使用的是 Keras Inception 迁移学习 API 教程中的大部分代码，
https://faroit.github.io/keras-docs/2.0.0/applications/#inceptionv3
只需进行一些小的更改以适应我的数据。
我正在使用 Tensorflow-gpu 1.4、Windows 7 和 Keras 2.03（？最新的 Keras）。
代码：
from keras.applications.inception_v3 import InceptionV3
from keras.preprocessing import image
from keras.preprocessing.image import ImageDataGenerator
from keras.models import Model
from keras.layers import Dense, GlobalAveragePooling2D
from keras import backend as K
img_width, img_height = 299, 299
train_data_dir = r'C:\Users\Moondra\Desktop\Keras Applications\data\train'
nb_train_samples = 8
nb_validation_samples = 100
batch_size = 10
epochs = 5
train_datagen = ImageDataGenerator(
rescale = 1./255,
horizontal_flip = True,
zoom_range = 0.1,
rotation_range=15)
train_generator = train_datagen.flow_from_directory(
train_data_dir,
target_size = (img_height, img_width),
batch_size = batch_size,
class_mode = 'categorical') #class_mode = 'categorical'
# create the base pre-trained model
base_model = InceptionV3(weights='imagenet', include_top=False)
# 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)
# and a logistic layer -- let's say we have 200 classes
predictions = Dense(12, activation='softmax')(x)
# this is the model we will train
model = Model(input=base_model.input, output=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 = False
# compile the model (should be done *after* setting layers to non-trainable)
model.compile(optimizer='rmsprop', loss='categorical_crossentropy')
# train the model on the new data for a few epochs
model.fit_generator(
train_generator,
steps_per_epoch = 5,
epochs = epochs)
# at this point, the top layers are well trained and we can start fine-tuning
# convolutional layers from inception V3. We will freeze the bottom N layers
# and train the remaining top layers.
# let's visualize layer names and layer indices to see how many layers
# we should freeze:
for i, layer in enumerate(base_model.layers):
print(i, layer.name)
# we chose to train the top 2 inception blocks, i.e. we will freeze
# the first 172 layers and unfreeze the rest:
for layer in model.layers[:172]:
layer.trainable = False
for layer in model.layers[172:]:
layer.trainable = True
# we need to recompile the model for these modifications to take effect
# we use SGD with a low learning rate
from keras.optimizers import SGD
model.compile(optimizer=SGD(lr=0.0001, momentum=0.9), loss='categorical_crossentropy')
# we train our model again (this time fine-tuning the top 2 inception blocks
# alongside the top Dense layers
model.fit_generator(
train_generator,
steps_per_epoch = 5,
epochs = epochs)
输出（无法超过第一个 epoch）：
Epoch 1/5
1/5 [=====>........................] - ETA: 8s - loss: 2.4869
2/5 [===========>..................] - ETA: 3s - loss: 5.5591
3/5 [=================>............] - ETA: 1s - loss: 6.6299
4/5 [=======================>......] - ETA: 0s - loss: 8.4925
它只是挂在这里。
更新：
我使用 tensorflow 1.3（降级一个版本）和 Keras 2.03（最新的 pip 版本）创建了一个虚拟环境，但仍然遇到同样的问题。
更新 2
我不认为这是一个内存问题，就像我在 epoch 中更改步骤一样——它会一直运行到最后一步，然后就冻结了。
所以在一个 epoch 中执行 30 步，它将运行到 29。
5 步，它会一直运行到第 4 步，然后挂起。
更新 3
还按照 Keras API 中的建议尝试了第 249 层。
【问题讨论】：
-
据我所知，keras的最新版本是2.11
-
您的代码对我来说似乎很好。可能是内存溢出问题，请检查您的内存。另请检查 inceptionv3 网络中的层数，目前您正在考虑 172 层。
-
@TusharGupta 我将检查初始模型的层，但我假设它是正确的，因为此代码是在官方 Kera API 页面上提供的。至于内存泄漏——我不完全确定如何检查。我使用 tf 作为支持，并且已知 tensorflow 将所有空闲内存分配给它自己，即使它不使用内存。所以每次我使用显卡监控工具，内存在95%，谢谢。
标签： python deep-learning keras