Question

代码

import numpy as np
from keras.preprocessing.image import ImageDataGenerator
from keras.models import Sequential,Model
from keras.layers import LeakyReLU,Dropout, Flatten, Dense,Input
from keras import applications
from keras.preprocessing import image
from keras import backend as K
from keras import regularizers
from keras.optimizers import adam
K.set_image_dim_ordering('tf')
input_tensor = Input(shape=(150,150,3))

img_width, img_height = 150,150

top_model_weights_path = 'bottleneck_fc_model.h5'
train_data_dir = 'Cats and Dogs Dataset/train'
validation_data_dir = 'Cats and Dogs Dataset/validation'
nb_train_samples = 20000
nb_validation_samples = 5000
epochs = 50
batch_size = 128

base_model=applications.inception_v3.InceptionV3(include_top=False, weights='imagenet', input_tensor=input_tensor, pooling=None)
i=0;
for layer in base_model.layers:
    layer.trainable = False
    i+=1
base_model.output
top_model=Sequential()
top_model.add(Flatten(input_shape=base_model.output_shape[1:]))
top_model.add(Dense(1024,activation="relu"))
top_model.add(Dropout(0.5))
top_model.add(Dense(10,activation="relu"))//Layer with issue 
top_model.add(Dropout(0.8))//
top_model.add(Dense(2, activation='softmax'))
model = Model(inputs=base_model.input,outputs=top_model(base_model.output))

model.summary
datagen = ImageDataGenerator(rescale=1. / 255)

train_data = datagen.flow_from_directory(train_data_dir,target_size=(img_width, img_height),batch_size=batch_size,classes=[ 'cats','dogs'])#,class_mode="binary",shuffle=True)


validation_data = datagen.flow_from_directory(validation_data_dir,target_size=(img_width, img_height), batch_size=batch_size,classes=['cats','dogs'])#,class_mode="binary",shuffle=True)

adm=adam(lr=0.02)
model.compile(optimizer=adm,loss='categorical_crossentropy', metrics=['accuracy'])

model.fit_generator(train_data, steps_per_epoch=nb_train_samples//batch_size, epochs=epochs,validation_data=validation_data, shuffle=True,verbose=1)

我已经使用keras（使用初始网络学到的转移知识）在猫和狗的数据集（https://www.kaggle.com/c/dogs-vs-cats/data）上实现了图像分类器。代码运行时没有错误，但是从第一个时期开始，验证集和训练集的准确性停留在50％，损失没有减少。我正在将Atom与氢气一起使用。

当我删除标记的图层时，问题消失了，我似乎无法理解为什么会这样。我试图解决的问题

不同批次大小-4,16,64,256
更改优化器-尝试了adam，rmsprop和sgd，且学习率已修改
对该层尝试了不同的激活-relu，Sigmoid和Leakyrelu
更改了辍学-辍学为0.9时，该问题消失了（即，使层没用，这是显而易见的原因，但也指出我缺少了一些东西）
将最终激活更改为S型

有人可以告诉我我所缺少的内容吗，因为我无法想到添加图层停止学习的任何原因

Answer 1

import numpy as np
from keras.preprocessing.image import ImageDataGenerator
from keras.models import Sequential,Model
from keras.layers import LeakyReLU,Dropout, Flatten, Dense,Input
from keras import applications
from keras.preprocessing import image
from keras import backend as K
from keras import regularizers
from keras.optimizers import adam
K.set_image_dim_ordering('tf')
input_tensor = Input(shape=(150,150,3))

img_width, img_height = 150,150

top_model_weights_path = 'bottleneck_fc_model.h5'
train_data_dir = 'Cats and Dogs Dataset/train'
validation_data_dir = 'Cats and Dogs Dataset/validation'
nb_train_samples = 20000
nb_validation_samples = 5000
epochs = 50
batch_size = 64

base_model=applications.inception_v3.InceptionV3(include_top=False, weights='imagenet', input_tensor=input_tensor, pooling=None)
i=0;
for layer in base_model.layers:
    layer.trainable = False
    i+=1
base_model.output
top_model=Sequential()
top_model.add(Flatten(input_shape=base_model.output_shape[1:]))
top_model.add(Dense(512,activation="relu")) //decrease in units
top_model.add(Dropout(0.4)) // change the drop out
top_model.add(Dense(128,activation="relu")) //increase in units
top_model.add(Dropout(0.2)) // decrease in dropout
top_model.add(Dense(2, activation='softmax'))
model = Model(inputs=base_model.input,outputs=top_model(base_model.output))

model.summary
datagen = ImageDataGenerator(rescale=1. / 255)

train_data = datagen.flow_from_directory(train_data_dir,target_size=(img_width, img_height),batch_size=batch_size,classes=[ 'cats','dogs'])#,class_mode="binary",shuffle=True)


validation_data = datagen.flow_from_directory(validation_data_dir,target_size=(img_width, img_height), batch_size=batch_size,classes=['cats','dogs'])#,class_mode="binary",shuffle=True)

adm=adam(lr=0.02)
model.compile(optimizer=adm,loss='categorical_crossentropy', metrics=['accuracy'])

model.fit_generator(train_data, steps_per_epoch=nb_train_samples//batch_size, epochs=epochs,validation_data=validation_data, shuffle=True,verbose=1)

我减少了第一密集层中的单元数，同时增加了第二密集层中的单元数..并且还降低了辍学率..运行此代码，让我知道。还有一件事，网络越复杂，过度拟合的机会就越多..辍学价值的增加可能会导致该层无法学习。尽量使您的网络简单。

添加层停止学习Keras

1 个答案: