master数据集测试

第一步，处理数据。

 

数据在data文件夹中，0，1，2表示三类图片，BMP2   0   BTR70  1    T72  2，图片没有区分开训练集和测试集，读取图片时根据标签来读。0类有1285张图片，1类429张图片，2类图片有1273张图片。图片偏少。train标签格式,指定文件路径和文件属性。指定1989张训练图片。998张测试图片，图片偏少且非整数张需注意。

dataload.py文件

import os.path
import gzip
import pickle
import os
import numpy as np

import os
from os.path import join as pjoin
from scipy import misc
from PIL import Image
dataset_dir = os.path.dirname(os.path.abspath(__file__))

def img_show(img):
    pil_img = Image.fromarray(np.uint8(img))
    pil_img.show()


def load_data(data_dir):
    fh = open(data_dir, 'r')  # 按照传入的路径和txt文本参数，打开这个文本，并读取内容
    labels = []
    data_img = []
    for line in fh:  # 迭代该列表#按行循环txt文本中的内
        line = line.strip('\n')
        line = line.rstrip('\n')  # 删除 本行string 字符串末尾的指定字符，这个方法的详细介绍自己查询python
        words = line.split()  # 用split将该行分割成列表  split的默认参数是空格，所以不传递任何参数时分割空格
          # 把txt里的内容读入imgs列表保存，具体是words几要看txt内容而定

        labels.append(words[1])    #word值是./data/2/HB04010.017.jpeg 2 这种类型，word[0] = ./data/2/HB04010.017.jpeg,word[1]=2
        img = Image.open(words[0]).convert('L')  # 读取图片
        image_arr = np.array(img,dtype="float32")   #将元组转为numpy数组格式，才有shape属性

        data_img.append(image_arr/255)
    data_img = np.array(data_img)
    labels = np.array(labels,dtype = 'int64')
    #data_img =data_img.reshape(-1, 1, 128, 128)   # data_img.shape输出为(1989, 1, 128, 128)
    print(data_img.shape)
    return data_img,labels,

#train_img,train_labels = load_data("data/train.txt")
#test_img,test_labels = load_data("data/test.txt")


第二步：训练模型

train_convnet.py

# coding: utf-8
import sys, os

sys.path.append(os.pardir)  # 为了导入父目录的文件而进行的设定
import numpy as np
import matplotlib.pyplot as plt

from simple_convnet import SimpleConvNet
from common.trainer import Trainer
from dataload import load_data

# 读入数据
#(x_train, t_train), (x_test, t_test) = load_mnist(flatten=False)  # flatten : 是否将图像展开为一维数组,false不展开
train_img,train_labels = load_data("data/train.txt")
test_img,test_labels = load_data("data/test.txt")

# 处理花费时间较长的情况下减少数据
#x_train, t_train = x_train[:20000], t_train[:20000]

max_epochs = 20

network = SimpleConvNet(input_dim=(1, 128, 128),
                        conv_param={'filter_num': 30, 'filter_size': 5, 'pad': 0, 'stride': 1},
                        hidden_size=100, output_size=3, weight_init_std=0.01)

trainer = Trainer(network, train_img, train_labels, test_img, test_labels,
                  epochs=max_epochs, mini_batch_size=100,
                  optimizer='Adam', optimizer_param={'lr': 0.001},
                  evaluate_sample_num_per_epoch=1000)
trainer.train()

# 保存参数
network.save_params("params.pkl")
print("Saved Network Parameters!")

# 绘制图形
markers = {'train': 'o', 'test': 's'}
x = np.arange(max_epochs)
plt.plot(x, trainer.train_acc_list, marker='o', label='train', markevery=2)
plt.plot(x, trainer.test_acc_list, marker='s', label='test', markevery=2)
plt.xlabel("epochs")
plt.ylabel("accuracy")
plt.ylim(0, 1.0)
plt.legend(loc='lower right')
plt.show()

第三步:定义简单的CNN网络

simple_convnet.py

# coding: utf-8
import sys, os

sys.path.append(os.pardir)  # 为了导入父目录的文件而进行的设定
import pickle
import numpy as np
from collections import OrderedDict
from common.layers import *
from common.gradient import numerical_gradient


class SimpleConvNet:
    """简单的ConvNet

    conv - relu - pool - affine - relu - affine - softmax

    Parameters
    ----------
    input_size : 输入大小（MNIST的情况下为784）
    hidden_size_list : 隐藏层的神经元数量的列表（e.g. [100, 100, 100]）
    output_size : 输出大小（MNIST的情况下为10）
    activation : 'relu' or 'sigmoid'
    weight_init_std : 指定权重的标准差（e.g. 0.01）
        指定'relu'或'he'的情况下设定“He的初始值”
        指定'sigmoid'或'xavier'的情况下设定“Xavier的初始值”
    stride:步幅
    pad：填充
    hidden_size:隐藏层全连接的神经元数量
    filter_num:滤波器数量
    input_dim输入数据的维度，通道，高，长
    """

    def __init__(self, input_dim=(1, 128, 128),
                 conv_param={'filter_num': 30, 'filter_size': 5, 'pad': 0, 'stride': 1},
                 hidden_size=100, output_size=3, weight_init_std=0.01):
        filter_num = conv_param['filter_num']
        filter_size = conv_param['filter_size']
        filter_pad = conv_param['pad']
        filter_stride = conv_param['stride']
        input_size = input_dim[1]
        # 卷积层的输出，28-5+1 = 24
        conv_output_size = (input_size - filter_size + 2 * filter_pad) / filter_stride + 1
        # 池化层的输出，
        pool_output_size = int(filter_num * (conv_output_size / 2) * (conv_output_size / 2))

        # 初始化权重  weight_init_std标准差0.01 randn函数返回一个或一组样本，具有标准正态分布。dn表格每个维度，返回值为指定维度的array
        self.params = {}
        self.params['W1'] = weight_init_std * \
                            np.random.randn(filter_num, input_dim[0], filter_size, filter_size)
        self.params['b1'] = np.zeros(filter_num)
        self.params['W2'] = weight_init_std * \
                            np.random.randn(pool_output_size, hidden_size)
        self.params['b2'] = np.zeros(hidden_size)
        self.params['W3'] = weight_init_std * \
                            np.random.randn(hidden_size, output_size)
        self.params['b3'] = np.zeros(output_size)

        # 生成层
        self.layers = OrderedDict()
        self.layers['Conv1'] = Convolution(self.params['W1'], self.params['b1'],
                                           conv_param['stride'], conv_param['pad'])
        self.layers['Relu1'] = Relu()
        self.layers['Pool1'] = Pooling(pool_h=2, pool_w=2, stride=2)  # 池化层，2*2，步幅是2
        self.layers['Affine1'] = Affine(self.params['W2'], self.params['b2'])
        self.layers['Relu2'] = Relu()
        self.layers['Affine2'] = Affine(self.params['W3'], self.params['b3'])

        self.last_layer = SoftmaxWithLoss()

    def predict(self, x):

        for layer in self.layers.values():
            x = layer.forward(x)

        return x

    def loss(self, x, t):

        """求损失函数
        参数x是输入数据、t是教师标签
        """
        y = self.predict(x)

        return self.last_layer.forward(y, t)

    def accuracy(self, x, t, batch_size=100):
        if t.ndim != 1: t = np.argmax(t, axis=1)

        acc = 0.0

        for i in range(int(x.shape[0] / batch_size)):
            tx = x[i * batch_size:(i + 1) * batch_size]
            tt = t[i * batch_size:(i + 1) * batch_size]
            y = self.predict(tx)
            y = np.argmax(y, axis=1)
            acc += np.sum(y == tt)  # 计算识别率

        return acc / x.shape[0]

    def numerical_gradient(self, x, t):
        """求梯度（数值微分）

        Parameters
        ----------
        x : 输入数据
        t : 教师标签

        Returns
        -------
        具有各层的梯度的字典变量
            grads['W1']、grads['W2']、...是各层的权重
            grads['b1']、grads['b2']、...是各层的偏置
        """
        loss_w = lambda w: self.loss(x, t)

        grads = {}
        for idx in (1, 2, 3):
            grads['W' + str(idx)] = numerical_gradient(loss_w, self.params['W' + str(idx)])
            grads['b' + str(idx)] = numerical_gradient(loss_w, self.params['b' + str(idx)])

        return grads

    def gradient(self, x, t):
        """求梯度（误差反向传播法）

        Parameters
        ----------
        x : 输入数据
        t : 教师标签

        Returns
        -------
        具有各层的梯度的字典变量
            grads['W1']、grads['W2']、...是各层的权重
            grads['b1']、grads['b2']、...是各层的偏置
        """
        # forward
        self.loss(x, t)

        # backward
        dout = 1
        dout = self.last_layer.backward(dout)

        layers = list(self.layers.values())
        layers.reverse()
        for layer in layers:
            dout = layer.backward(dout)

        # 设定
        grads = {}
        grads['W1'], grads['b1'] = self.layers['Conv1'].dW, self.layers['Conv1'].db
        grads['W2'], grads['b2'] = self.layers['Affine1'].dW, self.layers['Affine1'].db
        grads['W3'], grads['b3'] = self.layers['Affine2'].dW, self.layers['Affine2'].db

        return grads

    def save_params(self, file_name="params.pkl"):  # 保存训练好的参数
        params = {}
        for key, val in self.params.items():
            params[key] = val
        with open(file_name, 'wb') as f:
            pickle.dump(params, f)

    def load_params(self, file_name="params.pkl"):
        with open(file_name, 'rb') as f:
            params = pickle.load(f)
        for key, val in params.items():
            self.params[key] = val

        for i, key in enumerate(['Conv1', 'Affine1', 'Affine2']):
            self.layers[key].W = self.params['W' + str(i + 1)]
            self.layers[key].b = self.params['b' + str(i + 1)]

第四步：训练过程

trainer.py 在common文件夹中，另还有layer.py文件和function.py

# coding: utf-8
import sys, os

sys.path.append(os.pardir)  # 为了导入父目录的文件而进行的设定
import numpy as np
from common.optimizer import *


class Trainer:
    """进行神经网络的训练的类
    """

    def __init__(self, network, x_train, t_train, x_test, t_test,
                 epochs=20, mini_batch_size=100,
                 optimizer='SGD', optimizer_param={'lr': 0.01},
                 evaluate_sample_num_per_epoch=None, verbose=True):
        self.network = network
        self.verbose = verbose
        self.x_train = x_train
        self.t_train = t_train
        self.x_test = x_test
        self.t_test = t_test
        self.epochs = epochs
        self.batch_size = mini_batch_size
        self.evaluate_sample_num_per_epoch = evaluate_sample_num_per_epoch

        # optimzer
        optimizer_class_dict = {'sgd': SGD, 'momentum': Momentum, 'nesterov': Nesterov,
                                'adagrad': AdaGrad, 'rmsprpo': RMSprop, 'adam': Adam}
        self.optimizer = optimizer_class_dict[optimizer.lower()](**optimizer_param)

        self.train_size = x_train.shape[0]
        self.iter_per_epoch = 20     #train_size/mini_batch_size = 1989/100 =19.89非整数不可取
       # self.iter_per_epoch = max(self.train_size / mini_batch_size, 1)
        self.max_iter = int(epochs * self.iter_per_epoch)
        self.current_iter = 0
        self.current_epoch = 0

        self.train_loss_list = []
        self.train_acc_list = []
        self.test_acc_list = []

    def train_step(self):
        batch_mask = np.random.choice(self.train_size, self.batch_size)
        x_batch = self.x_train[batch_mask]
        t_batch = self.t_train[batch_mask]

        grads = self.network.gradient(x_batch, t_batch)
        self.optimizer.update(self.network.params, grads)

        loss = self.network.loss(x_batch, t_batch)
        self.train_loss_list.append(loss)


        if self.verbose: print("train loss:" + str(loss))

        if self.current_iter % self.iter_per_epoch == 0:
            self.current_epoch += 1
            print("---------------------")
            print(self.iter_per_epoch)
            print(self.current_epoch)
            x_train_sample, t_train_sample = self.x_train, self.t_train
            x_test_sample, t_test_sample = self.x_test, self.t_test
            if not self.evaluate_sample_num_per_epoch is None:
                t = self.evaluate_sample_num_per_epoch

                x_train_sample, t_train_sample = self.x_train[:t], self.t_train[:t]
                x_test_sample, t_test_sample = self.x_test[:t], self.t_test[:t]

            train_acc = self.network.accuracy(x_train_sample, t_train_sample)
            test_acc = self.network.accuracy(x_test_sample, t_test_sample)
            self.train_acc_list.append(train_acc)
            self.test_acc_list.append(test_acc)

            if self.verbose: print(
                "=== epoch:" + str(self.current_epoch) + ", train acc:" + str(train_acc) + ", test acc:" + str(
                    test_acc) + " ===")
        self.current_iter += 1

    def train(self):
        for i in range(self.max_iter):
            self.train_step()

        test_acc = self.network.accuracy(self.x_test, self.t_test)

        if self.verbose:
            print("=============== Final Test Accuracy ===============")
            print("test acc:" + str(test_acc))

layer.py保存各类激活函数和梯度下降函数

# coding: utf-8
import numpy as np
from common.functions import *
from common.util import im2col, col2im


class Relu:
    def __init__(self):
        self.mask = None

    def forward(self, x):
        self.mask = (x <= 0)
        out = x.copy()
        out[self.mask] = 0

        return out

    def backward(self, dout):
        dout[self.mask] = 0
        dx = dout

        return dx


class Sigmoid:
    def __init__(self):
        self.out = None

    def forward(self, x):
        out = sigmoid(x)
        self.out = out
        return out

    def backward(self, dout):
        dx = dout * (1.0 - self.out) * self.out

        return dx


class Affine:
    def __init__(self, W, b):
        self.W =W
        self.b = b
        
        self.x = None
        self.original_x_shape = None
        # 权重和偏置参数的导数
        self.dW = None
        self.db = None

    def forward(self, x):
        # 对应张量
        self.original_x_shape = x.shape
        x = x.reshape(x.shape[0], -1)
        self.x = x

        out = np.dot(self.x, self.W) + self.b

        return out

    def backward(self, dout):
        dx = np.dot(dout, self.W.T)
        self.dW = np.dot(self.x.T, dout)
        self.db = np.sum(dout, axis=0)
        
        dx = dx.reshape(*self.original_x_shape)  # 还原输入数据的形状（对应张量）
        return dx


class SoftmaxWithLoss:
    def __init__(self):
        self.loss = None
        self.y = None # softmax的输出
        self.t = None # 监督数据

    def forward(self, x, t):
        self.t = t

        self.y = softmax(x)
        self.loss = cross_entropy_error(self.y, self.t)
        
        return self.loss

    def backward(self, dout=1):
        batch_size = self.t.shape[0]
        if self.t.size == self.y.size: # 监督数据是one-hot-vector的情况
            dx = (self.y - self.t) / batch_size
        else:
            dx = self.y.copy()
            dx[np.arange(batch_size), self.t] -= 1
            dx = dx / batch_size
        
        return dx


class Dropout:
    """
    http://arxiv.org/abs/1207.0580
    """
    def __init__(self, dropout_ratio=0.5):
        self.dropout_ratio = dropout_ratio
        self.mask = None

    def forward(self, x, train_flg=True):
        if train_flg:
            self.mask = np.random.rand(*x.shape) > self.dropout_ratio
            return x * self.mask
        else:
            return x * (1.0 - self.dropout_ratio)

    def backward(self, dout):
        return dout * self.mask


class BatchNormalization:
    """
    http://arxiv.org/abs/1502.03167
    """
    def __init__(self, gamma, beta, momentum=0.9, running_mean=None, running_var=None):
        self.gamma = gamma
        self.beta = beta
        self.momentum = momentum
        self.input_shape = None # Conv层的情况下为4维，全连接层的情况下为2维  

        # 测试时使用的平均值和方差
        self.running_mean = running_mean
        self.running_var = running_var  
        
        # backward时使用的中间数据
        self.batch_size = None
        self.xc = None
        self.std = None
        self.dgamma = None
        self.dbeta = None

    def forward(self, x, train_flg=True):
        self.input_shape = x.shape
        if x.ndim != 2:
            N, C, H, W = x.shape
            x = x.reshape(N, -1)

        out = self.__forward(x, train_flg)
        
        return out.reshape(*self.input_shape)
            
    def __forward(self, x, train_flg):
        if self.running_mean is None:
            N, D = x.shape
            self.running_mean = np.zeros(D)
            self.running_var = np.zeros(D)
                        
        if train_flg:
            mu = x.mean(axis=0)
            xc = x - mu
            var = np.mean(xc**2, axis=0)
            std = np.sqrt(var + 10e-7)
            xn = xc / std
            
            self.batch_size = x.shape[0]
            self.xc = xc
            self.xn = xn
            self.std = std
            self.running_mean = self.momentum * self.running_mean + (1-self.momentum) * mu
            self.running_var = self.momentum * self.running_var + (1-self.momentum) * var            
        else:
            xc = x - self.running_mean
            xn = xc / ((np.sqrt(self.running_var + 10e-7)))
            
        out = self.gamma * xn + self.beta 
        return out

    def backward(self, dout):
        if dout.ndim != 2:
            N, C, H, W = dout.shape
            dout = dout.reshape(N, -1)

        dx = self.__backward(dout)

        dx = dx.reshape(*self.input_shape)
        return dx

    def __backward(self, dout):
        dbeta = dout.sum(axis=0)
        dgamma = np.sum(self.xn * dout, axis=0)
        dxn = self.gamma * dout
        dxc = dxn / self.std
        dstd = -np.sum((dxn * self.xc) / (self.std * self.std), axis=0)
        dvar = 0.5 * dstd / self.std
        dxc += (2.0 / self.batch_size) * self.xc * dvar
        dmu = np.sum(dxc, axis=0)
        dx = dxc - dmu / self.batch_size
        
        self.dgamma = dgamma
        self.dbeta = dbeta
        
        return dx


class Convolution:
    def __init__(self, W, b, stride=1, pad=0):
        self.W = W
        self.b = b
        self.stride = stride
        self.pad = pad
        
        # 中间数据（backward时使用）
        self.x = None   
        self.col = None
        self.col_W = None
        
        # 权重和偏置参数的梯度
        self.dW = None
        self.db = None

    def forward(self, x):
        FN, C, FH, FW = self.W.shape
        N, C, H, W = x.shape
        out_h = 1 + int((H + 2*self.pad - FH) / self.stride)
        out_w = 1 + int((W + 2*self.pad - FW) / self.stride)

        col = im2col(x, FH, FW, self.stride, self.pad)
        col_W = self.W.reshape(FN, -1).T

        out = np.dot(col, col_W) + self.b
        out = out.reshape(N, out_h, out_w, -1).transpose(0, 3, 1, 2)

        self.x = x
        self.col = col
        self.col_W = col_W

        return out

    def backward(self, dout):
        FN, C, FH, FW = self.W.shape
        dout = dout.transpose(0,2,3,1).reshape(-1, FN)

        self.db = np.sum(dout, axis=0)
        self.dW = np.dot(self.col.T, dout)
        self.dW = self.dW.transpose(1, 0).reshape(FN, C, FH, FW)

        dcol = np.dot(dout, self.col_W.T)
        dx = col2im(dcol, self.x.shape, FH, FW, self.stride, self.pad)

        return dx


class Pooling:
    def __init__(self, pool_h, pool_w, stride=1, pad=0):
        self.pool_h = pool_h
        self.pool_w = pool_w
        self.stride = stride
        self.pad = pad
        
        self.x = None
        self.arg_max = None

    def forward(self, x):
        N, C, H, W = x.shape
        out_h = int(1 + (H - self.pool_h) / self.stride)
        out_w = int(1 + (W - self.pool_w) / self.stride)

        col = im2col(x, self.pool_h, self.pool_w, self.stride, self.pad)
        col = col.reshape(-1, self.pool_h*self.pool_w)

        arg_max = np.argmax(col, axis=1)
        out = np.max(col, axis=1)
        out = out.reshape(N, out_h, out_w, C).transpose(0, 3, 1, 2)

        self.x = x
        self.arg_max = arg_max

        return out

    def backward(self, dout):
        dout = dout.transpose(0, 2, 3, 1)
        
        pool_size = self.pool_h * self.pool_w
        dmax = np.zeros((dout.size, pool_size))
        dmax[np.arange(self.arg_max.size), self.arg_max.flatten()] = dout.flatten()
        dmax = dmax.reshape(dout.shape + (pool_size,)) 
        
        dcol = dmax.reshape(dmax.shape[0] * dmax.shape[1] * dmax.shape[2], -1)
        dx = col2im(dcol, self.x.shape, self.pool_h, self.pool_w, self.stride, self.pad)
        
        return dx

训练结果

样本数少，过拟合

=== epoch:1, train acc:0.856, test acc:0.42985971943887774 ===
=== epoch:2, train acc:0.443, test acc:0.5420841683366734 ===
=== epoch:3, train acc:0.737, test acc:0.6382765531062125 ===
=== epoch:4, train acc:0.794, test acc:0.7334669338677354 ===
=== epoch:5, train acc:0.862, test acc:0.7474949899799599 ===
=== epoch:6, train acc:0.929, test acc:0.782565130260521 ===
=== epoch:7, train acc:0.949, test acc:0.842685370741483 ===
=== epoch:8, train acc:0.922, test acc:0.8366733466933868 ===
=== epoch:9, train acc:0.912, test acc:0.8206412825651302 ===
=== epoch:10, train acc:0.942, test acc:0.8466933867735471 ===
=== epoch:11, train acc:0.952, test acc:0.8366733466933868 ===
=== epoch:12, train acc:0.966, test acc:0.8577154308617234 ===
=== epoch:13, train acc:0.987, test acc:0.872745490981964 ===
=== epoch:14, train acc:0.995, test acc:0.872745490981964 ===
=== epoch:15, train acc:0.992, test acc:0.8767535070140281 ===
=== epoch:16, train acc:0.97, test acc:0.8567134268537074 ===
=== epoch:17, train acc:0.997, test acc:0.8787575150300602 ===
=== epoch:18, train acc:0.999, test acc:0.8837675350701403 ===
=== epoch:19, train acc:0.998, test acc:0.8797595190380761 ===
=== epoch:20, train acc:1.0, test acc:0.8807615230460922 ===

test acc:0.8807615230460922