赞
踩
飞百度架构师手把手带你零基础实践深度学习——21日学习打卡(第二周第三日)
首先声明,不详细讲解代码部分,主要是针对课程的理解及对作业的分析。(要是有代码相关问题可以私信)
课程链接:飞百度架构师手把手带你零基础实践深度学习
前文:
飞桨PaddlePaddle-百度架构师手把手带你零基础实践深度学习——21日学习打卡(第二周第一日)
飞桨PaddlePaddle-百度架构师手把手带你零基础实践深度学习——21日学习打卡(第二周第二日)
该课程分类专栏:深度学习课程——飞桨paddlepaddle
让我们回顾一下昨天学到的知识,昨天详细讲了神经网络的激活函数、批归一化、Dropout丢弃法这些基础概念并且介绍了卷积神经网络常用的一些基本模块。
今天我们就用这些基础概念来对眼疾识别数据集进行图像的分类(模型详细讲解页面链接),今天孙老师着重讲了四个经典的神经网络分类模型(AlexNet、VGG、GoogLeNet、Resnet),基于眼疾分类数据集iChallenge-PM,对图像分类领域的经典卷积神经网络进行剖析,介绍如何应用这些基础模块构建卷积神经网络,解决图像分类问题。
import cv2 import random import numpy as np # 对读入的图像数据进行预处理 def transform_img(img): # 将图片尺寸缩放道 224x224 img = cv2.resize(img, (224, 224)) # 读入的图像数据格式是[H, W, C] # 使用转置操作将其变成[C, H, W] img = np.transpose(img, (2,0,1)) img = img.astype('float32') # 将数据范围调整到[-1.0, 1.0]之间 img = img / 255. img = img * 2.0 - 1.0 return img # 定义训练集数据读取器 def data_loader(datadir, batch_size=10, mode = 'train'): # 将datadir目录下的文件列出来,每条文件都要读入 filenames = os.listdir(datadir) def reader(): if mode == 'train': # 训练时随机打乱数据顺序 random.shuffle(filenames) batch_imgs = [] batch_labels = [] for name in filenames: filepath = os.path.join(datadir, name) img = cv2.imread(filepath) img = transform_img(img) if name[0] == 'H' or name[0] == 'N': # H开头的文件名表示高度近似,N开头的文件名表示正常视力 # 高度近视和正常视力的样本,都不是病理性的,属于负样本,标签为0 label = 0 elif name[0] == 'P': # P开头的是病理性近视,属于正样本,标签为1 label = 1 else: raise('Not excepted file name') # 每读取一个样本的数据,就将其放入数据列表中 batch_imgs.append(img) batch_labels.append(label) if len(batch_imgs) == batch_size: # 当数据列表的长度等于batch_size的时候, # 把这些数据当作一个mini-batch,并作为数据生成器的一个输出 imgs_array = np.array(batch_imgs).astype('float32') labels_array = np.array(batch_labels).astype('float32').reshape(-1, 1) yield imgs_array, labels_array batch_imgs = [] batch_labels = [] if len(batch_imgs) > 0: # 剩余样本数目不足一个batch_size的数据,一起打包成一个mini-batch imgs_array = np.array(batch_imgs).astype('float32') labels_array = np.array(batch_labels).astype('float32').reshape(-1, 1) yield imgs_array, labels_array return reader # 定义验证集数据读取器 def valid_data_loader(datadir, csvfile, batch_size=10, mode='valid'): # 训练集读取时通过文件名来确定样本标签,验证集则通过csvfile来读取每个图片对应的标签 # 请查看解压后的验证集标签数据,观察csvfile文件里面所包含的内容 # csvfile文件所包含的内容格式如下,每一行代表一个样本, # 其中第一列是图片id,第二列是文件名,第三列是图片标签, # 第四列和第五列是Fovea的坐标,与分类任务无关 # ID,imgName,Label,Fovea_X,Fovea_Y # 1,V0001.jpg,0,1157.74,1019.87 # 2,V0002.jpg,1,1285.82,1080.47 # 打开包含验证集标签的csvfile,并读入其中的内容 filelists = open(csvfile).readlines() def reader(): batch_imgs = [] batch_labels = [] for line in filelists[1:]: line = line.strip().split(',') name = line[1] label = int(line[2]) # 根据图片文件名加载图片,并对图像数据作预处理 filepath = os.path.join(datadir, name) img = cv2.imread(filepath) img = transform_img(img) # 每读取一个样本的数据,就将其放入数据列表中 batch_imgs.append(img) batch_labels.append(label) if len(batch_imgs) == batch_size: # 当数据列表的长度等于batch_size的时候, # 把这些数据当作一个mini-batch,并作为数据生成器的一个输出 imgs_array = np.array(batch_imgs).astype('float32') labels_array = np.array(batch_labels).astype('float32').reshape(-1, 1) yield imgs_array, labels_array batch_imgs = [] batch_labels = [] if len(batch_imgs) > 0: # 剩余样本数目不足一个batch_size的数据,一起打包成一个mini-batch imgs_array = np.array(batch_imgs).astype('float32') labels_array = np.array(batch_labels).astype('float32').reshape(-1, 1) yield imgs_array, labels_array return reader # -*- coding: utf-8 -*- # LeNet 识别眼疾图片 import os import random import paddle import paddle.fluid as fluid import numpy as np DATADIR = '/home/aistudio/work/palm/PALM-Training400/PALM-Training400' DATADIR2 = '/home/aistudio/work/palm/PALM-Validation400' CSVFILE = '/home/aistudio/labels.csv' # 定义训练过程 def train(model): with fluid.dygraph.guard(): print('start training ... ') model.train() epoch_num = 5 # 定义优化器 opt = fluid.optimizer.Momentum(learning_rate=0.001, momentum=0.9, parameter_list=model.parameters()) # 定义数据读取器,训练数据读取器和验证数据读取器 train_loader = data_loader(DATADIR, batch_size=10, mode='train') valid_loader = valid_data_loader(DATADIR2, CSVFILE) for epoch in range(epoch_num): for batch_id, data in enumerate(train_loader()): x_data, y_data = data img = fluid.dygraph.to_variable(x_data) label = fluid.dygraph.to_variable(y_data) # 运行模型前向计算,得到预测值 logits = model(img) # 进行loss计算 loss = fluid.layers.sigmoid_cross_entropy_with_logits(logits, label) avg_loss = fluid.layers.mean(loss) if batch_id % 10 == 0: print("epoch: {}, batch_id: {}, loss is: {}".format(epoch, batch_id, avg_loss.numpy())) # 反向传播,更新权重,清除梯度 avg_loss.backward() opt.minimize(avg_loss) model.clear_gradients() model.eval() accuracies = [] losses = [] for batch_id, data in enumerate(valid_loader()): x_data, y_data = data img = fluid.dygraph.to_variable(x_data) label = fluid.dygraph.to_variable(y_data) # 运行模型前向计算,得到预测值 logits = model(img) # 二分类,sigmoid计算后的结果以0.5为阈值分两个类别 # 计算sigmoid后的预测概率,进行loss计算 pred = fluid.layers.sigmoid(logits) loss = fluid.layers.sigmoid_cross_entropy_with_logits(logits, label) # 计算预测概率小于0.5的类别 pred2 = pred * (-1.0) + 1.0 # 得到两个类别的预测概率,并沿第一个维度级联 pred = fluid.layers.concat([pred2, pred], axis=1) acc = fluid.layers.accuracy(pred, fluid.layers.cast(label, dtype='int64')) accuracies.append(acc.numpy()) losses.append(loss.numpy()) print("[validation] accuracy/loss: {}/{}".format(np.mean(accuracies), np.mean(losses))) model.train() # save params of model fluid.save_dygraph(model.state_dict(), 'palm') # save optimizer state fluid.save_dygraph(opt.state_dict(), 'palm') # 导入需要的包 import paddle import paddle.fluid as fluid import numpy as np from paddle.fluid.dygraph.nn import Conv2D, Pool2D, Linear # 定义 LeNet 网络结构 class LeNet(fluid.dygraph.Layer): def __init__(self, num_classes=1): super(LeNet, self).__init__() self.conv1 = Conv2D(num_channels=3, num_filters=6, filter_size=5, act='relu') self.pool1 = Pool2D(pool_size=2, pool_stride=2, pool_type='max') self.conv2 = Conv2D(num_channels=6, num_filters=16, filter_size=5, act='relu') self.pool2 = Pool2D(pool_size=2, pool_stride=2, pool_type='max') # 创建第3个卷积层 self.conv3 = Conv2D(num_channels=16, num_filters=120, filter_size=4, act='relu') # 创建全连接层,第一个全连接层的输出神经元个数为64, 第二个全连接层输出神经元个数为分类标签的类别数 self.fc1 = Linear(input_dim=300000, output_dim=64, act='sigmoid') self.fc2 = Linear(input_dim=64, output_dim=num_classes) # 网络的前向计算过程 def forward(self, x, label=None): x = self.conv1(x) x = self.pool1(x) x = self.conv2(x) x = self.pool2(x) x = self.conv3(x) x = fluid.layers.reshape(x, [x.shape[0], -1]) x = self.fc1(x) x = self.fc2(x) if label is not None: acc = fluid.layers.accuracy(input=x, label=label) return x, acc else: return x if __name__ == '__main__': # 创建模型 with fluid.dygraph.guard(): model = LeNet(num_classes=1) train(model)
结果:
start training ... epoch: 0, batch_id: 0, loss is: [0.80509055] epoch: 0, batch_id: 10, loss is: [0.68919075] epoch: 0, batch_id: 20, loss is: [0.46361116] epoch: 0, batch_id: 30, loss is: [0.63713] [validation] accuracy/loss: 0.7949999570846558/0.40998899936676025 epoch: 1, batch_id: 0, loss is: [0.05862291] epoch: 1, batch_id: 10, loss is: [0.059012] epoch: 1, batch_id: 20, loss is: [0.4808681] epoch: 1, batch_id: 30, loss is: [0.23313868] [validation] accuracy/loss: 0.9325000047683716/0.1934463381767273 epoch: 2, batch_id: 0, loss is: [0.04319196] epoch: 2, batch_id: 10, loss is: [0.05719509] epoch: 2, batch_id: 20, loss is: [0.15007056] epoch: 2, batch_id: 30, loss is: [0.2530269] [validation] accuracy/loss: 0.9399999380111694/0.16418571770191193 epoch: 3, batch_id: 0, loss is: [0.07580633] epoch: 3, batch_id: 10, loss is: [0.09643873] epoch: 3, batch_id: 20, loss is: [0.22165939] epoch: 3, batch_id: 30, loss is: [0.03506085] [validation] accuracy/loss: 0.9299999475479126/0.18996192514896393 epoch: 4, batch_id: 0, loss is: [0.0507292] epoch: 4, batch_id: 10, loss is: [0.17943501] epoch: 4, batch_id: 20, loss is: [0.11925531] epoch: 4, batch_id: 30, loss is: [0.23927791] [validation] accuracy/loss: 0.9225000143051147/0.17611104249954224
完美。
有什么不对或者可以改进的地方欢迎评论,互相交流
Copyright © 2003-2013 www.wpsshop.cn 版权所有,并保留所有权利。