[英]Keras - .flow_from_directory(directory)
I am trying to run an example of Resnet with cifar10 dataset using .flow_from_directory(directory)
.我正在尝试使用
.flow_from_directory(directory)
运行带有 cifar10 数据集的 Resnet 示例。 The below code is below:下面的代码如下:
from __future__ import print_function
from keras.datasets import cifar10
from keras.preprocessing.image import ImageDataGenerator
from keras.utils import np_utils
from keras.callbacks import ReduceLROnPlateau, CSVLogger, EarlyStopping
import numpy as np
import resnet
import os
import cv2
import csv
#import keras
os.environ["CUDA_VISIBLE_DEVICES"] = "1"
# input image dimensions
img_rows, img_cols = 32, 32
# The CIFAR10 images are RGB.
img_channels = 3
nb_classes = 10
train_datagen = ImageDataGenerator(
rescale=1./255,
shear_range=0,
zoom_range=0,
horizontal_flip=False,
width_shift_range=0.1, # randomly shift images horizontally (fraction of total width)
height_shift_range=0.1) # randomly shift images vertically (fraction of total height))
test_datagen = ImageDataGenerator(rescale=1./255)
train_generator = train_datagen.flow_from_directory(
'/home/datasets/cifar10/train',
target_size=(32, 32),
batch_size=32,
shuffle=False)
validation_generator = test_datagen.flow_from_directory(
'/home/datasets/cifar10/test',
target_size=(32, 32),
batch_size=32,
shuffle=False)
model = resnet.ResnetBuilder.build_resnet_18((img_channels, img_rows, img_cols), nb_classes)
model.compile(loss='categorical_crossentropy',
optimizer='adam',
metrics=['accuracy'])
model.fit_generator(
train_generator,
steps_per_epoch=500,
epochs=50,
validation_data=validation_generator,
validation_steps=250)
However, I am obtaining the following accuracy value.但是,我获得了以下准确度值。
500/500 [==============================] - 22s - loss: 0.8139 - acc: 0.9254 - val_loss: 12.7198 - val_acc: 0.1250
Epoch 2/50
500/500 [==============================] - 19s - loss: 1.0645 - acc: 0.8856 - val_loss: 8.4179 - val_acc: 0.0560
Epoch 3/50
500/500 [==============================] - 19s - loss: 2.1014 - acc: 0.7492 - val_loss: 10.7770 - val_acc: 0.0956
Epoch 4/50
500/500 [==============================] - 19s - loss: 1.6806 - acc: 0.7772 - val_loss: 6.1023 - val_acc: 0.0741
Epoch 5/50
500/500 [==============================] - 19s - loss: 1.1798 - acc: 0.8669 - val_loss: 6.9016 - val_acc: 0.1253
Epoch 6/50
500/500 [==============================] - 19s - loss: 1.5448 - acc: 0.8369 - val_loss: 3.6371 - val_acc: 0.0370
Epoch 7/50
500/500 [==============================] - 19s - loss: 1.3763 - acc: 0.8599 - val_loss: 4.8012 - val_acc: 0.1204
Epoch 8/50
500/500 [==============================] - 19s - loss: 1.0186 - acc: 0.8891 - val_loss: 6.8395 - val_acc: 0.0912
Epoch 9/50
500/500 [==============================] - 19s - loss: 0.9477 - acc: 0.9081 - val_loss: 10.4287 - val_acc: 0.1253
Epoch 10/50
500/500 [==============================] - 19s - loss: 1.0689 - acc: 0.8686 - val_loss: 7.9931 - val_acc: 0.1253
I am using Resnet from this link .我正在使用此 链接中的 Resnet。 I tried numerous examples to sort the problem including the one on the official documentation.
我尝试了许多示例来解决问题,包括官方文档中的示例。 However, I am unable to resolve the problem.
但是,我无法解决问题。 Training accuracy is changing however val accuracy is somewhat constatn.
训练准确度在变化,但是验证准确度有些恒定。 Can some one point the problem
有人可以指出问题吗
According the Keras documentation.根据 Keras 文档。
flow_from_directory(directory)
, Description:Takes the path to a directory, and generates batches of augmented/normalized data. flow_from_directory(directory)
,描述:获取目录的路径,并生成成批的扩充/规范化数据。 Yields batches indefinitely, in an infinite loop.在无限循环中无限期地产生批次。
With shuffle = False
, it takes the same batch indefinitely.使用
shuffle = False
,它会无限期地采用同一批次。 leading to these accuracy values.导致这些精度值。 I changed
shuffle = True
and it works fine now.我更改了
shuffle = True
,现在它工作正常。
声明:本站的技术帖子网页,遵循CC BY-SA 4.0协议,如果您需要转载,请注明本站网址或者原文地址。任何问题请咨询:yoyou2525@163.com.