1.引入python包,启用GPU模式
import numpy as np import matplotlib.pyplot as plt import os import torch import torch.nn as nn import torchvision from torchvision import models,transforms,datasets import time import json # 判断是否存在GPU设备 device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu") print('Using gpu: %s ' % torch.cuda.is_available())
2.下载数据
! wget https://static.leiphone.com/cat_dog.rar ! unrar x'cat_dog.rar
3.处理数据
图片将被整理成224×224×3的大小,同时进行归一化处理。
torchvision 支持对输入数据进行一些复杂的预处理/变换 (normalization, cropping, flipping, jittering 等)。具体可以参照 torchvision.tranforms 的官方文档说明。
normalize = transforms.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225]) vgg_format = transforms.Compose([ transforms.CenterCrop(224), transforms.ToTensor(), normalize, ]) data_dir = './dogscats' dsets = {x: datasets.ImageFolder(os.path.join(data_dir, x), vgg_format) for x in ['train', 'valid']} dset_sizes = {x: len(dsets[x]) for x in ['train', 'valid']} dset_classes = dsets['train'].classes
# 通过下面代码可以查看 dsets 的一些属性 print(dsets['train'].classes) print(dsets['train'].class_to_idx) print(dsets['train'].imgs[:5]) print('dset_sizes: ', dset_sizes)
# 显示图片的小程序 def imshow(inp, title=None): # Imshow for Tensor. inp = inp.numpy().transpose((1, 2, 0)) mean = np.array([0.485, 0.456, 0.406]) std = np.array([0.229, 0.224, 0.225]) inp = np.clip(std * inp + mean, 0,1) plt.imshow(inp) if title is not None: plt.title(title) plt.pause(0.001) # pause a bit so that plots are updated
# 显示 labels_try 的5张图片,即valid里第一个batch的5张图片 out = torchvision.utils.make_grid(inputs_try) imshow(out, title=[dset_classes[x] for x in labels_try])
4.创建VGG Model
!wget https://s3.amazonaws.com/deep-learning-models/image-models/imagenet_class_index.json
model_vgg = models.vgg16(pretrained=True) with open('./imagenet_class_index.json') as f: class_dict = json.load(f) dic_imagenet = [class_dict[str(i)][1] for i in range(len(class_dict))] inputs_try , labels_try = inputs_try.to(device), labels_try.to(device) model_vgg = model_vgg.to(device) outputs_try = model_vgg(inputs_try) print(outputs_try) print(outputs_try.shape) ''' 可以看到结果为5行,1000列的数据,每一列代表对每一种目标识别的结果。 但是我也可以观察到,结果非常奇葩,有负数,有正数, 为了将VGG网络输出的结果转化为对每一类的预测概率,我们把结果输入到 Softmax 函数 ''' m_softm = nn.Softmax(dim=1) probs = m_softm(outputs_try) vals_try,pred_try = torch.max(probs,dim=1) print( 'prob sum: ', torch.sum(probs,1)) print( 'vals_try: ', vals_try) print( 'pred_try: ', pred_try) print([dic_imagenet[i] for i in pred_try.data]) imshow(torchvision.utils.make_grid(inputs_try.data.cpu()), title=[dset_classes[x] for x in labels_try.data.cpu()])
5.修改最后一层,冻结前面层的参数
VGG 模型如下图所示,注意该网络由三种元素组成:
-
卷积层(CONV)是发现图像中局部的 pattern
-
全连接层(FC)是在全局上建立特征的关联
-
池化(Pool)是给图像降维以提高特征的 invariance
为了使用预训练好的模型,我们需要把最后的 nn.Linear 层由1000类,替换为2类。为了在训练中冻结前面层的参数,需要设置 required_grad=False。这样,反向传播训练梯度时,前面层的权重就不会自动更新了,训练中,只会更新最后一层的参数。
print(model_vgg) model_vgg_new = model_vgg; for param in model_vgg_new.parameters(): param.requires_grad = False model_vgg_new.classifier._modules['6'] = nn.Linear(4096, 2) model_vgg_new.classifier._modules['7'] = torch.nn.LogSoftmax(dim = 1) model_vgg_new = model_vgg_new.to(device) print(model_vgg_new.classifier)
6.训练并测试全连接层
第1步,创建损失函数和优化器;
第2步,训练模型;
第3步,测试模型。
''' 第一步:创建损失函数和优化器 损失函数 NLLLoss() 的 输入 是一个对数概率向量和一个目标标签. 它不会为我们计算对数概率,适合最后一层是log_softmax()的网络. ''' criterion = nn.NLLLoss() # 学习率 lr = 0.001 # 随机梯度下降 optimizer_vgg = torch.optim.SGD(model_vgg_new.classifier[6].parameters(),lr = lr) ''' 第二步:训练模型 ''' def train_model(model,dataloader,size,epochs=1,optimizer=None): model.train() for epoch in range(epochs): running_loss = 0.0 running_corrects = 0 count = 0 for inputs,classes in dataloader: inputs = inputs.to(device) classes = classes.to(device) outputs = model(inputs) loss = criterion(outputs,classes) optimizer = optimizer optimizer.zero_grad() loss.backward() optimizer.step() _,preds = torch.max(outputs.data,1) # statistics running_loss += loss.data.item() running_corrects += torch.sum(preds == classes.data) count += len(inputs) print('Training: No. ', count, ' process ... total: ', size) epoch_loss = running_loss / size epoch_acc = running_corrects.data.item() / size print('Loss: {:.4f} Acc: {:.4f}'.format( epoch_loss, epoch_acc)) # 模型训练 train_model(model_vgg_new,loader_train,size=dset_sizes['train'], epochs=1, optimizer=optimizer_vgg)
torch.optim 是实现各种优化算法的软件包,通过torch.optim构造一个优化器对象,该对象将保持当前状态并根据所计算的梯度来更新参数。 这里使用Adam优化器,Adam在很多情况下算作默认工作性能比较优秀的优化器。 根据预测的最好的情况通过torch.save()保存训练好的模型,后期对测试集进行测试时通过torch.load()加载模型。
def test_model(model,dataloader,size): model.eval() predictions = np.zeros(size) all_classes = np.zeros(size) all_proba = np.zeros((size,2)) i = 0 running_loss = 0.0 running_corrects = 0 for inputs,classes in dataloader: inputs = inputs.to(device) classes = classes.to(device) outputs = model(inputs) loss = criterion(outputs,classes) _,preds = torch.max(outputs.data,1) # statistics running_loss += loss.data.item() running_corrects += torch.sum(preds == classes.data) predictions[i:i+len(classes)] = preds.to('cpu').numpy() all_classes[i:i+len(classes)] = classes.to('cpu').numpy() all_proba[i:i+len(classes),:] = outputs.data.to('cpu').numpy() i += len(classes) print('Testing: No. ', i, ' process ... total: ', size) epoch_loss = running_loss / size epoch_acc = running_corrects.data.item() / size print('Loss: {:.4f} Acc: {:.4f}'.format( epoch_loss, epoch_acc)) return predictions, all_proba, all_classes predictions, all_proba, all_classes = test_model(model_vgg_new,loader_valid,size=dset_sizes['valid'])
可以看到,测试成功率为96.8%
7.可视化模型预测结果(主观分析)
-
随机查看一些预测正确的图片
-
随机查看一些预测错误的图片
-
预测正确,同时具有较大的probability的图片
-
预测错误,同时具有较大的probability的图片
-
最不确定的图片,比如说预测概率接近0.5的图片