正文
网络搭建
有的小伙伴会有疑惑，怎么先模型训练后网络搭建了，其实不是哈，上面只是训练的一个类，下面才是实例化。因为是迁移学习嘛，而且pytorch内置了许多网络供我们选择，因此，此处省去了许多网络搭建，也就是卷积层的搭建过程。此举，意在让我们更快实现分类的目的，而不是过多的重复已有的工作。
model_conv = torchvision.models.resnet18(pretrained=True) for param in model_conv.parameters(): param.requires_grad = False # Parameters of newly constructed modules have requires_grad=True by default num_ftrs = model_conv.fc.in_features model_conv.fc = nn.Linear(num_ftrs, 2) model_conv = model_conv.to(device) criterion = nn.CrossEntropyLoss() # Observe that only parameters of final layer are being optimized as # opposed to before. optimizer_conv = optim.SGD(model_conv.fc.parameters(), lr=0.001, momentum=0.9) # Decay LR by a factor of 0.1 every 7 epochs exp_lr_scheduler = lr_scheduler.StepLR(optimizer_conv, step_size=7, gamma=0.1)
可以看到：
model_conv = torchvision.models.resnet18(pretrained=True)
此模型采用了resnet18网络，大家都知道这个残差网络具有很好的训练效果，而我们只是一行代码就使用了该网络，可见pytorh的方便之处。
odel_conv.fc = nn.Linear(num_ftrs, 2)
如果你要进行多类的分类任务，那么你除了在数据集进行变化之外，还需要将上面2这个数字改为 你分类的类别量。
criterion = nn.CrossEntropyLoss()
并且这里运用了交叉熵损失函数进行费分类任务，可见损失函数也无需我们进行过多书写，也给我们内置好了函数。
上面说到了上面进行了数据集训练类的书写，下面实例化就完成了类的调用，
model_ft = train_model(model_ft, criterion, optimizer_ft, exp_lr_scheduler, num_epochs=25)
为了训练精确，你需要更改 num_epochs=25这里的参数，以及增加你的数据集数量。在我的博客也将写道如何获取想要的数据集。
到此就完成了对图像二分类任务的实现。
本次图像分类任务的精确度较好，由以下看出：
Training complete in 1m 11s Best val Acc: 0.921569
图像二分类任务精度达92%，就问你喜不喜欢。
下面的结果，也证实了准确率：
分类结果
模型保存
模型保存就不再赘述啦，可以私信本人获取，单张图像预测的代码也可以找我！
你要的整体代码如下：
from __future__ import print_function, division import torch import torch.nn as nn import torch.optim as optim from torch.optim import lr_scheduler import torch.backends.cudnn as cudnn import numpy as np import torchvision from torchvision import datasets, models, transforms import matplotlib.pyplot as plt import time import os import copy cudnn.benchmark = True plt.ion() # interactive mode ###################################################################### # Load Data # --------- # data_transforms = { 'train': transforms.Compose([ transforms.RandomResizedCrop(224), transforms.RandomHorizontalFlip(), transforms.ToTensor(), transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225]) ]), 'val': transforms.Compose([ transforms.Resize(256), transforms.CenterCrop(224), transforms.ToTensor(), transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225]) ]), } data_dir = 'data/hymenoptera_data' image_datasets = {x: datasets.ImageFolder(os.path.join(data_dir, x), data_transforms[x]) for x in ['train', 'val']} dataloaders = {x: torch.utils.data.DataLoader(image_datasets[x], batch_size=4, shuffle=True, num_workers=4) for x in ['train', 'val']} dataset_sizes = {x: len(image_datasets[x]) for x in ['train', 'val']} class_names = image_datasets['train'].classes device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu") ###################################################################### # Visualize a few images # ^^^^^^^^^^^^^^^^^^^^^^ # Let's visualize a few training images so as to understand the data # augmentations. 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 = std * inp + mean inp = np.clip(inp, 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 # Get a batch of training data inputs, classes = next(iter) # Make a grid from batch out = torchvision.utils.make_grid(inputs) imshow(out, title=[class_names[x] for x in classes]) ###################################################################### # Training the model # ------------------ # # Now, let's write a general function to train a model. Here, we will # illustrate: # # - Scheduling the learning rate # - Saving the best model # # In the following, parameter ``scheduler`` is an LR scheduler object from # ``torch.optim.lr_scheduler``. def train_model(model, criterion, optimizer, scheduler, num_epochs=25): since = time.time() best_model_wts = copy.deepcopy(model.state_dict()) best_acc = 0.0 for epoch in range(num_epochs): print(f'Epoch {epoch}/{num_epochs - 1}') print('-' * 10) # Each epoch has a training and validation phase for phase in ['train', 'val']: if phase == 'train': model.train() # Set model to training mode else: model.eval() # Set model to evaluate mode running_loss = 0.0 running_corrects = 0 # Iterate over data. for inputs, labels in dataloaders[phase]: inputs = inputs.to(device) labels = labels.to(device) # zero the parameter gradients optimizer.zero_grad() # forward # track history if only in train with torch.set_grad_enabled(phase == 'train'): outputs = model(inputs) _, preds = torch.max(outputs, 1) loss = criterion(outputs, labels) # backward + optimize only if in training phase if phase == 'train': loss.backward() optimizer.step() # statistics running_loss += loss.item() * inputs.size(0) running_corrects += torch.sum(preds == labels.data) if phase == 'train': scheduler.step() epoch_loss = running_loss / dataset_sizes[phase] epoch_acc = running_corrects.double() / dataset_sizes[phase] print(f'{phase} Loss: {epoch_loss:.4f} Acc: {epoch_acc:.4f}') # deep copy the model if phase == 'val' and epoch_acc > best_acc: best_acc = epoch_acc best_model_wts = copy.deepcopy(model.state_dict()) print() time_elapsed = time.time() - since print(f'Training complete in {time_elapsed // 60:.0f}m {time_elapsed % 60:.0f}s') print(f'Best val Acc: {best_acc:4f}') # load best model weights model.load_state_dict(best_model_wts) return model ###################################################################### # Visualizing the model predictions # ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ # # Generic function to display predictions for a few images # def visualize_model(model, num_images=6): was_training = model.training model.eval() images_so_far = 0 fig = plt.figure() with torch.no_grad(): for i, (inputs, labels) in enumerate(dataloaders['val']): inputs = inputs.to(device) labels = labels.to(device) outputs = model(inputs) _, preds = torch.max(outputs, 1) for j in range(inputs.size()[0]): images_so_far += 1 ax = plt.subplot(num_images//2, 2, images_so_far) ax.axis('off') ax.set_title(f'predicted: {class_names[preds[j]]}') imshow(inputs.cpu().data[j]) if images_so_far == num_images: model.train(mode=was_training) return model.train(mode=was_training) ###################################################################### # Finetuning the convnet # ---------------------- # # Load a pretrained model and reset final fully connected layer. # model_ft = models.resnet18(pretrained=True) num_ftrs = model_ft.fc.in_features # Here the size of each output sample is set to 2. # Alternatively, it can be generalized to nn.Linear(num_ftrs, len(class_names)). model_ft.fc = nn.Linear(num_ftrs, 2) model_ft = model_ft.to(device) criterion = nn.CrossEntropyLoss() # Observe that all parameters are being optimized optimizer_ft = optim.SGD(model_ft.parameters(), lr=0.001, momentum=0.9) # Decay LR by a factor of 0.1 every 7 epochs exp_lr_scheduler = lr_scheduler.StepLR(optimizer_ft, step_size=7, gamma=0.1) ###################################################################### # Train and evaluate # ^^^^^^^^^^^^^^^^^^ # # It should take around 15-25 min on CPU. On GPU though, it takes less than a # minute. # model_ft = train_model(model_ft, criterion, optimizer_ft, exp_lr_scheduler, num_epochs=25) ###################################################################### # visualize_model(model_ft) ###################################################################### # ConvNet as fixed feature extractor # ---------------------------------- # # Here, we need to freeze all the network except the final layer. We need # to set ``requires_grad = False`` to freeze the parameters so that the # gradients are not computed in ``backward()``. # # You can read more about this in the documentation # `here <https://pytorch.org/docs/notes/autograd.html#excluding-subgraphs-from-backward>`__. # model_conv = torchvision.models.resnet18(pretrained=True) for param in model_conv.parameters(): param.requires_grad = False # Parameters of newly constructed modules have requires_grad=True by default num_ftrs = model_conv.fc.in_features model_conv.fc = nn.Linear(num_ftrs, 2) model_conv = model_conv.to(device) criterion = nn.CrossEntropyLoss() # Observe that only parameters of final layer are being optimized as # opposed to before. optimizer_conv = optim.SGD(model_conv.fc.parameters(), lr=0.001, momentum=0.9) # Decay LR by a factor of 0.1 every 7 epochs exp_lr_scheduler = lr_scheduler.StepLR(optimizer_conv, step_size=7, gamma=0.1) ###################################################################### # Train and evaluate # ^^^^^^^^^^^^^^^^^^ # # On CPU this will take about half the time compared to previous scenario. # This is expected as gradients don't need to be computed for most of the # network. However, forward does need to be computed. # model_conv = train_model(model_conv, criterion, optimizer_conv, exp_lr_scheduler, num_epochs=25) ###################################################################### # visualize_model(model_conv) plt.ioff() plt.show()
