基于深度学习的花卉识别

import os import matplotlib.pyplot as plt import numpy as np import torch from torch import nn import torch.optim as optim import torchvision #pip install torchvision 需要提前安装好这个模块 from torchvision import transforms, models, datasets #https://pytorch.org/docs/stable/torchvision/index.html import imageio import time import warnings import random import sys import copy import json from PIL import Image #神经网络数据集 from flower_dataset import dataloaders filename='checkpoint.pth' """""""""""""""冻结神经网络权重函数open""""""""""""""" def set_parameter_requires_grad(model, feature_extracting): if feature_extracting: #这里为true for param in model.parameters(): param.requires_grad = False #把除了最后全连接层，前面所有层权重冻结不能修改 """""""""""""""冻结神经网络权重函数end""""""""""""""" """""""""""""""修改全连接层函数（官方）open""""""""""""""" #（模型名字、得到类别个数、模型权重、 def initialize_model(model_name, num_classes, feature_extract, use_pretrained=True): # 选择合适的模型，不同模型的初始化方法稍微有点区别 model_ft = None input_size = 0 if model_name == "resnet": """ Resnet152 """ #加载模型（下载） model_ft = models.resnet152(pretrained=use_pretrained) #有选择性的选需要冻住哪些层 set_parameter_requires_grad(model_ft, feature_extract) #取出最后一层 num_ftrs = model_ft.fc.in_features #重新做全连接层（102这里需要修改，因为本任务分类类别是102） model_ft.fc = nn.Sequential(nn.Linear(num_ftrs, 102), nn.LogSoftmax(dim=1)) input_size = 224 elif model_name == "alexnet": """ Alexnet """ model_ft = models.alexnet(pretrained=use_pretrained) set_parameter_requires_grad(model_ft, feature_extract) num_ftrs = model_ft.classifier[6].in_features model_ft.classifier[6] = nn.Linear(num_ftrs,num_classes) input_size = 224 elif model_name == "vgg": """ VGG11_bn """ model_ft = models.vgg16(pretrained=use_pretrained) set_parameter_requires_grad(model_ft, feature_extract) num_ftrs = model_ft.classifier[6].in_features model_ft.classifier[6] = nn.Linear(num_ftrs,num_classes) input_size = 224 elif model_name == "squeezenet": """ Squeezenet """ model_ft = models.squeezenet1_0(pretrained=use_pretrained) set_parameter_requires_grad(model_ft, feature_extract) model_ft.classifier[1] = nn.Conv2d(512, num_classes, kernel_size=(1,1), stride=(1,1)) model_ft.num_classes = num_classes input_size = 224 elif model_name == "densenet": """ Densenet """ model_ft = models.densenet121(pretrained=use_pretrained) set_parameter_requires_grad(model_ft, feature_extract) num_ftrs = model_ft.classifier.in_features model_ft.classifier = nn.Linear(num_ftrs, num_classes) input_size = 224 elif model_name == "inception": """ Inception v3 Be careful, expects (299,299) sized images and has auxiliary output """ model_ft = models.inception_v3(pretrained=use_pretrained) set_parameter_requires_grad(model_ft, feature_extract) # Handle the auxilary net num_ftrs = model_ft.AuxLogits.fc.in_features model_ft.AuxLogits.fc = nn.Linear(num_ftrs, num_classes) # Handle the primary net num_ftrs = model_ft.fc.in_features model_ft.fc = nn.Linear(num_ftrs,num_classes) input_size = 299 else: print("Invalid model name, exiting...") exit() return model_ft, input_size """""""""""""""修改全连接层函数（官方）end""""""""""""""" """""""""""""""训练模型函数open""""""""""""""" #得到并保存神经网络模型checkpoint.pth #（模型，数据，损失函数，优化器 def train_model(model, dataloaders, criterion, optimizer, num_epochs=25, is_inception=False, filename=filename): since = time.time() #保存最好的准确率 best_acc = 0 """ checkpoint = torch.load(filename) best_acc = checkpoint['best_acc'] model.load_state_dict(checkpoint['state_dict']) optimizer.load_state_dict(checkpoint['optimizer']) model.class_to_idx = checkpoint['mapping'] """ #指定CPU做训练 model.to(device) val_acc_history = [] train_acc_history = [] train_losses = [] valid_losses = [] LRs = [optimizer.param_groups[0]['lr']] #最好的一次存下来 best_model_wts = copy.deepcopy(model.state_dict()) for epoch in range(num_epochs): print('Epoch {}/{}'.format(epoch, num_epochs - 1)) print('-' * 10) # 训练和验证 for phase in ['train', 'valid']: if phase == 'train': model.train() # 训练 else: model.eval() # 验证 running_loss = 0.0 running_corrects = 0 # 把数据都取个遍 for inputs, labels in dataloaders[phase]: inputs = inputs.to(device) labels = labels.to(device) # 清零 optimizer.zero_grad() # 只有训练的时候计算和更新梯度 with torch.set_grad_enabled(phase == 'train'): #resnet不执行这个 if is_inception and phase == 'train': outputs, aux_outputs = model(inputs) loss1 = criterion(outputs, labels) loss2 = criterion(aux_outputs, labels) loss = loss1 + 0.4 * loss2 else: # resnet执行的是这里 outputs = model(inputs) loss = criterion(outputs, labels) _, preds = torch.max(outputs, 1) # 训练阶段更新权重 if phase == 'train': loss.backward() optimizer.step() # 计算损失 running_loss += loss.item() * inputs.size(0) running_corrects += torch.sum(preds == labels.data) epoch_loss = running_loss / len(dataloaders[phase].dataset) epoch_acc = running_corrects.double() / len(dataloaders[phase].dataset) time_elapsed = time.time() - since print('Time elapsed {:.0f}m {:.0f}s'.format(time_elapsed // 60, time_elapsed % 60)) print('{} Loss: {:.4f} Acc: {:.4f}'.format(phase, epoch_loss, epoch_acc)) # 得到最好那次的模型 if phase == 'valid' and epoch_acc > best_acc: best_acc = epoch_acc best_model_wts = copy.deepcopy(model.state_dict()) state = { 'state_dict': model.state_dict(), 'best_acc': best_acc, 'optimizer': optimizer.state_dict(), } torch.save(state, filename) if phase == 'valid': val_acc_history.append(epoch_acc) valid_losses.append(epoch_loss) scheduler.step(epoch_loss) if phase == 'train': train_acc_history.append(epoch_acc) train_losses.append(epoch_loss) print('Optimizer learning rate : {:.7f}'.format(optimizer.param_groups[0]['lr'])) LRs.append(optimizer.param_groups[0]['lr']) print() time_elapsed = time.time() - s