MNIST和转让与VGG16学习Keras-低精度验证

Question

最近，我开始服用Keras的flow_from_dataframe的优势（）功能项目，并决定与MNIST数据集进行测试。我有一个目录充满PNG格式MNIST样品，并在一列中具有绝对目录中的数据帧的每个而在其他的标签。

我还使用转印学习，导入VGG16作为碱，和为10的SOFTMAX层（对于数字0-9）之前加入我自己的512节点RELU致密层和0.5落出。我使用rmsprop（LR = 1E-4）作为优化器。

当我启动我的环境中，它调用从Git的，最新版本的keras_preprocessing的具有绝对目录支持和大写的文件扩展名。

我的问题是，我有一个非常高的训练精度和非常低的验证准确度。通过我的最后时期（10），我有0.94训练精度和0.01验证准确性。

我不知道是否有一些根本性的错误我的脚本？与其他数据集，我甚至划时代4后得到了我的两个训练和验证损耗值NaN的（我查了相关栏目，目前还没有任何空值！）

这里是我的代码。我是深表感谢的人是可以通过它一眼，看看是否有任何他们跳了出来。

import pandas as pd
import numpy as np

import keras
from keras_preprocessing.image import ImageDataGenerator

from keras import applications
from keras import optimizers
from keras.models import Model 
from keras.layers import Dropout, Flatten, Dense, GlobalAveragePooling2D
from keras import backend as k 
from keras.callbacks import ModelCheckpoint, CSVLogger

from keras.applications.vgg16 import VGG16, preprocess_input

# INITIALIZE MODEL

img_width, img_height = 32, 32
model = VGG16(weights = 'imagenet', include_top=False, input_shape = (img_width, img_height, 3))

# freeze all layers
for layer in model.layers:
    layer.trainable = False

# Adding custom Layers 
x = model.output
x = Flatten()(x)
x = Dense(512, activation='relu')(x)
x = Dropout(0.5)(x)
predictions = Dense(10, activation="softmax")(x)

# creating the final model 
model_final = Model(input = model.input, output = predictions)

# compile the model 
rms = optimizers.RMSprop(lr=1e-4)
#adadelta = optimizers.Adadelta(lr=0.001, rho=0.5, epsilon=None, decay=0.0)

model_final.compile(loss = "categorical_crossentropy", optimizer = rms, metrics=["accuracy"])

# LOAD AND DEFINE SOURCE DATA

train = pd.read_csv('MNIST_train.csv', index_col=0)
val = pd.read_csv('MNIST_test.csv', index_col=0)

nb_train_samples = 60000
nb_validation_samples = 10000
batch_size = 60
epochs = 10

# Initiate the train and test generators
train_datagen = ImageDataGenerator()
test_datagen = ImageDataGenerator()

train_generator = train_datagen.flow_from_dataframe(dataframe=train,
                                                    directory=None,
                                                    x_col='train_samples',
                                                    y_col='train_labels',
                                                    has_ext=True,
                                                    target_size = (img_height,
                                                                   img_width),
                                                    batch_size = batch_size, 
                                                    class_mode = 'categorical',
                                                    color_mode = 'rgb')

validation_generator = test_datagen.flow_from_dataframe(dataframe=val,
                                                        directory=None,
                                                        x_col='test_samples',
                                                        y_col='test_labels',
                                                        has_ext=True,
                                                        target_size = (img_height, 
                                                                       img_width),
                                                        batch_size = batch_size, 
                                                        class_mode = 'categorical',
                                                        color_mode = 'rgb')

# GET CLASS INDICES
print('****************')
for cls, idx in train_generator.class_indices.items():
    print('Class #{} = {}'.format(idx, cls))
print('****************')

# DEFINE CALLBACKS

path = './chk/epoch_{epoch:02d}-valLoss_{val_loss:.2f}-valAcc_{val_acc:.2f}.hdf5'

chk = ModelCheckpoint(path, monitor = 'val_acc', verbose = 1, save_best_only = True, mode = 'max')

logger = CSVLogger('./chk/training_log.csv', separator = ',', append=False)

nPlus = 1
samples_per_epoch = nb_train_samples * nPlus

# Train the model 
model_final.fit_generator(train_generator,
                          steps_per_epoch = int(samples_per_epoch/batch_size),
                          epochs = epochs,
                          validation_data = validation_generator,
                          validation_steps = int(nb_validation_samples/batch_size),
                          callbacks = [chk, logger])

Answer 1

您是否尝试过明确定义的图像的类？因此：

train_generator=image.ImageDataGenerator().flow_from_dataframe(classes=[0,1,2,3,4,5,6,7,8,9])

在火车和验证发电机两者。

我发现，有时火车和验证发电机产生不同的对应字典。