python - 为什么我写的这个VGG16无法收敛

import torchvision import torch from torchvision import utils from torchvision import transforms from matplotlib import pyplot as plt from visdom import Visdom import torch.nn.functional as F import torch.nn as nn import time import torchvision from sklearn.metrics import cohen_kappa_score from sklearn.metrics import classification_report class VGG16(nn.Module): def __init__(self, num_classes=2): super(VGG16, self).__init__() self.features = nn.Sequential( nn.Conv2d(3, 64, kernel_size=3, padding=1), nn.ReLU(inplace=True), nn.Conv2d(64, 64, kernel_size=3, padding=1), # nn.BatchNorm2d(64, affine=True), nn.ReLU(inplace=True), nn.MaxPool2d(kernel_size=2, stride=2), nn.Conv2d(64, 128, kernel_size=3, padding=1), nn.ReLU(inplace=True), nn.Conv2d(128, 128, kernel_size=3, padding=1), nn.ReLU(inplace=True), nn.MaxPool2d(kernel_size=2, stride=2), nn.Conv2d(128, 256, kernel_size=3, padding=1), nn.ReLU(inplace=True), nn.Conv2d(256, 256, kernel_size=3, padding=1), nn.ReLU(inplace=True), nn.Conv2d(256, 256, kernel_size=3, padding=1), nn.ReLU(inplace=True), nn.MaxPool2d(kernel_size=2, stride=2), nn.Conv2d(256, 512, kernel_size=3, padding=1), nn.ReLU(inplace=True), nn.Conv2d(512, 512, kernel_size=3, padding=1), nn.ReLU(inplace=True), nn.Conv2d(512, 512, kernel_size=3, padding=1), nn.ReLU(inplace=True), nn.MaxPool2d(kernel_size=2, stride=2), nn.Conv2d(512, 512, kernel_size=3, padding=1), nn.ReLU(inplace=True), nn.Conv2d(512, 512, kernel_size=3, padding=1), nn.ReLU(inplace=True), nn.Conv2d(512, 512, kernel_size=3, padding=1), nn.ReLU(inplace=True), nn.MaxPool2d(kernel_size=2, stride=2), ) self.classifier = nn.Sequential( nn.Linear(512 * 7 * 7, 4096), nn.ReLU(True), nn.Dropout(), nn.Linear(4096, 4096), nn.ReLU(True), nn.Dropout(), nn.Linear(4096, num_classes), ) def forward(self, x): x = self.features(x) x = x.view(x.size(0), -1) x = self.classifier(x) return x img_data = torchvision.datasets.ImageFolder(r'E:\\Datasets\\catanddog/', transform=transforms.Compose([ transforms.Resize(256), transforms.CenterCrop(224), transforms.ToTensor(), transforms.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225])]) ) print('img_data size:',len(img_data),'\\n') train_size = int(0.08 * len(img_data)) test_size = int(0.02 * len(img_data)) valide_size = len(img_data) - train_size - test_size train_dataset, test_dataset, valide_size = torch.utils.data.random_split(img_data, [train_size, test_size, valide_size]) print('train_dataset size:',len(train_dataset)) print('test_dataset size:',len(test_dataset),'\\n') batch_size = 30 train_loader = torch.utils.data.DataLoader(dataset=train_dataset, batch_size=batch_size) test_loader = torch.utils.data.DataLoader(dataset=test_dataset, batch_size=batch_size) print('train_loader size:',len(train_loader)) print('test_loader size:',len(test_loader)) ############################################################################## import time device = torch.device('cuda' if torch.cuda.is_available() else 'cpu') net = VGG16() net.cuda() criterion = torch.nn.CrossEntropyLoss() optimizer = torch.optim.Adam(net.parameters(), lr=0.00005) num_epochs = 300 start_time =time.time() current_time = time.strftime("%Y-%m-%dT%H:%M", time.localtime()) viz = Visdom() viz.line([0.], [0], win='train_loss', opts=dict(title='train_loss')) viz.line([0.], [0], win='Acc', opts=dict(title='Acc')) # /0: pass/1:save if_save = 0 test_intervel = 5 for epoch in range(num_epochs): for x,y in train_loader: x = x.cuda() y = y.cuda() optimizer.zero_grad() preds = net(x) loss = criterion(preds, y) loss.backward() optimizer.step() viz.line([loss.detach().cpu().numpy()], [epoch], win='train_loss', update='append') time.sleep(0.5) if epoch % test_intervel ==0: test_loss = 0 test_correct = 0 total = 0 for batch_num, (data, target) in enumerate(test_loader): data, target = data.to(device), target.to(device) output = net.eval()(data) prediction = torch.max(output, 1) total += target.size(0) test_correct += np.sum(prediction[1].cpu().numpy() == target.cpu().numpy()) print(100. * test_correct / total) print(loss.cpu().detach().numpy()) ACC = 100. * test_correct / total viz.line([ACC], [epoch], win='Acc', update='append') if if_save == 1: if epoch == num_epochs-1: print('') save_path = r'C:\\Users\\Xavier\\Desktop\\save_path/Alexnet.pth' torch.save(net.state_dict(), save_path) finish_time =time.time() print('time_comsume:', finish_time-start_time)