无法超越第一个时代-挂了[Keras转移学习开始] [英] Can't get past first epoch -- just hangs [Keras Transfer Learning Inception]

问题描述

我基本上使用了Keras Inception转移学习API教程中的大部分代码，

I'm basically using most of the code from Keras Inception transfer learning API tutorial,

https://faroit.github.io/keras- docs/2.0.0/applications/#inceptionv3

仅需进行一些小改动即可适合我的数据.

just a few minor changes to fit my data.

我正在使用Tensorflow-gpu 1.4，Windows 7和Keras 2.03(最新的Keras).

I'm using Tensorflow-gpu 1.4, Windows 7 and Keras 2.03(? latest Keras).

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(不能超过第一个纪元):

 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.

我用tensorflow 1.3(降级一个版本)和Keras 2.03(最新pip版本)创建了一个虚拟环境，但仍然存在相同的问题.

I created a virtual env with tensorflow 1.3 (downgrade one version down) and Keras 2.03(latest pip version) and still having the same problem.

我不认为这是一个内存问题，好像我在纪元内更改了步骤一样–它将一直运行到最后一步，并且只是冻结.

I don't think it's a memory issue as if I change the steps within the epoch -- it will run fine all the way to the last step, and just freeze.

所以一个纪元要走30步，直到29步.

So 30 steps in an epoch and it will run till 29.

5个步骤，它将运行到第4步，然后挂起.

5 steps and it will run till the 4th step and then just hang.

还尝试了Keras API中建议的第249层.

Also tried layers 249 as suggested in the Keras API.

推荐答案

显然，这是通过Keras更新修复的错误(但是，有些错误仍然存​​在)

Apparently it was a bug that got fixed via Keras update (However, some are still experiencing the problem)

这篇关于无法超越第一个时代-挂了[Keras转移学习开始]的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！