【深度学习】对CIFAR-10中的图片进行分类

最近在学习tensorflow框架，昨天做了一个利用tflearn对CIFAR-10中的图片进行分类的问题：

http://c.biancheng.net/view/1930.html

在jupyter notebook上运行代码的时候还是遇到了很多困难。

1.模块重复

KeyError: "Registering two gradient with name 'LSTMBlockCell'!

不太明白是什么意思，Google了也找不出答案。于是我换CPU的kernel重新运行了一遍，没有报错，但是接下来来的训练过程非常慢。。。而且loss一直保持在0也不知道为什么。

然后我查看了一下tensorflow的版本，发现CPU的是1.13.0-rc1，GPU的是2.0.0（什么时候升级了？）于是我在tensorflow-gpu环境下运行:

pip install --user --ignore-installed tensorflow-gpu==1.13.0-rc1

 更改版本以后，确实不报这个错误了。

2.curses缺失

curses is not supported on this machine (please install/reinstall curses for an optimal experience

查了一下这个词的意思，竟然是“诅咒”。。虽然不知道是用来干嘛的，但查一下怎么安装的就是了。需要先在这里找到whl文件下载安装：https://www.lfd.uci.edu/~gohlke/pythonlibs/

一开始下载了35版的，报错信息是不适合该平台，然后又下载了36，成功！

问题一一解决，接下来就是训练模型啦：

3.训练模型

from __future__ import division, print_function, absolute_import
import tflearn
from tflearn.data_utils import shuffle, to_categorical
from tflearn.layers.core import input_data, dropout, fully_connected
from tflearn.layers.conv import conv_2d, max_pool_2d
from tflearn.layers.estimator import regression
from tflearn.data_preprocessing import ImagePreprocessing
from tflearn.data_augmentation import ImageAugmentation

# Data loading and pregrocesssing
from tflearn.datasets import cifar10
(X, Y), (X_test, Y_test) = cifar10.load_data()
X, Y = shuffle(X, Y)
Y = to_categorical(Y, 10)
Y_test = to_categorical(Y_test, 10)

# Real-time data preprocessing
img_prep = ImagePreprocessing()
img_prep.add_featurewise_zero_center()
img_prep.add_featurewise_stdnorm()

# Real-time data augmentation
img_aug = ImageAugmentation()
img_aug.add_random_flip_leftright()
img_aug.add_random_rotation(max_angle = 25.)

# Convolutional network building
network = input_data(shape = [None, 32, 32, 3],
                    data_preprocessing = img_prep,
                    data_augmentation = img_aug)
network = conv_2d(network, 32, 3, activation = 'relu')
network = max_pool_2d(network, 2)
network = conv_2d(network, 64, 3, activation = 'relu')
network = conv_2d(network, 64, 3, activation = 'relu')
network = max_pool_2d(network, 2)
networ = fully_connected(network, 512, activation = 'relu')
network = dropout(network, 0.5)
network = fully_connected(network, 10, activation = 'softmax')
network = regression(network, optimizer = 'adam', loss = 'categorical_crossentropy',
                    learning_rate = 0.001)

#Train using classifier
model = tflearn.DNN(network, tensorboard_verbose = 0)
model.fit(X, Y, n_epoch = 50, shuffle = True, validation_set = (X_test, Y_test),
         show_metric = True, batch_size = 96, run_id = 'cifar10_cnn')

结果：

这样就Train好啦！哎，在cpu上跑过一遍才知道GPU有多快。

4.预测

教程上只写了怎么训练模型，我想试一下分类的效果如何。