def eval(args):
device = torch.device(f"cuda:{args.device_id}")
model = AlexNet(n_cls = 100)
model.to(device)
model.load_state_dict(torch.load(args.pretrained_path))
model.eval()
test_loader = getLoaders(split="eval", batch_size = args.batch_size, num_workers=args.num_workers )
pred_arr = []
label_arr = []
with torch.no_grad():
for idx, (img, label) in tqdm(enumerate(test_loader),total= len(test_loader)):
img = img.to(device)
pred = model.pred(img)
# mean of softmax prob from 10 different aug
pred = pred.view(-1, 10, 100)
pred = pred.mean(dim = 1)
pred_arr.append(pred.detach().cpu().numpy())
label_arr.append(label.detach().numpy())
pred_np = np.concatenate(pred_arr)
label_np = np.concatenate(label_arr)
top_1 = utils.top_k_acc(k = 1, pred = pred_np, label= label_np)
top_5 = utils.top_k_acc(k = 5, pred = pred_np, label= label_np)
confusion = utils.confusion_matrix(100, pred_np, label_np)
torch.save({
"top_1": top_1,
"top_5": top_5,
"confusion": confusion,
}, "result.pth")
print(f"top_1: {top_1*100:.2f}, top_5: {top_5*100:.2f}")
def test():
if torch.cuda.device_count() > 1:
model = torch.nn.parallel.DataParallel(
AlexNet(num_classes=opt.num_classes))
else:
model = AlexNet(num_classes=opt.num_classes)
model.load_state_dict(
torch.load(MODEL_PATH, map_location=lambda storage, loc: storage))
model.to(device)
# init value
correct1 = 0.
correct5 = 0.
total = len(test_dataloader.dataset)
with torch.no_grad():
for i, data in enumerate(test_dataloader):
# get the inputs; data is a list of [inputs, labels]
inputs, targets = data
inputs = inputs.to(device)
targets = targets.to(device)
outputs = model(inputs)
# cal top 1 accuracy
prec1 = outputs.argmax(dim=1)
correct1 += torch.eq(prec1, targets).sum().item()
# cal top 5 accuracy
maxk = max((1, 2))
targets_resize = targets.view(-1, 1)
_, prec5 = outputs.topk(maxk, 1, True, True)
correct5 += torch.eq(prec5, targets_resize).sum().item()
return correct1 / total, correct5 / total
def main(args=None):
logging.basicConfig(format='%(levelname)s:%(message)s',
level=logging.DEBUG)
logging.info('Arquitetura AlexNet')
parser = argparse.ArgumentParser()
parser.add_argument('--num_classes',
help='Num. de classes.',
type=int,
default=1000)
parser.add_argument('--pretrained',
help='Serão utilizados pesos pré-treinados.',
type=bool,
default=True)
parser.add_argument('--model_url',
help='Caminho para os pesos.',
default="./pesos/alexnet-owt-4df8aa71.pth")
opt = parser.parse_args(args)
# Dados
proc = Preprocessador()
imagem_url = "./imagens/raposa.jpg"
imagem = Image.open(imagem_url)
imagem = proc.executa(imagem)
#https://jhui.github.io/2018/02/09/PyTorch-Basic-operations/
imagem = imagem.unsqueeze(0)
# Instancia do modelo
model = AlexNet(opt.num_classes)
model.eval()
# Caso deseje utilizar os pesos pré-treinados
if opt.pretrained:
checkpoint = torch.load(opt.model_url)
model.load_state_dict(checkpoint)
# Utiliza a GPU se existir no computador
if torch.cuda.is_available():
model.to('cuda')
with torch.no_grad():
saida = model(imagem)
# Obtem o indice melhor ranqueado
index = np.argmax(saida[0]).item()
acuracia = torch.max(saida).item()
print(getLabel(index), acuracia)
def test(imageFolder): #测试部分
is_paramatter = False #置False为导入整个模型，置True为导入参数文件
if (is_paramatter):
net = AlexNet()
model = torch.load('./model_parameter.pth',
map_location=torch.device(device)) #模型参数文件
net.load_state_dict(model)
else:
net = torch.load('./model.pkl', map_location=torch.device(device))
net = net.to(device)
torch.set_grad_enabled(False)
torch.no_grad()
net.eval()
data_num = MyDataSet(imageFolder).__len__()
for i in range(data_num):
img, ori, name = MyDataSet(imageFolder, data_transform).__getitem__(i)
out = net(img.to(device, torch.float))
predict = out.argmax(dim=1) #预测的label
probability = out[:, predict] #该label的概率
s = 'Predict result: This is a '
if predict == 0:
s += 'CAT'
else:
s += 'DOG'
s += ' with the probability of '
s += str(round(float(probability), 4))
plt.title(s)
plt.imshow(ori)
plt.savefig("./result/" + name.replace('.jpg', '') + ".png",
dpi=300) #将结果保存在result文件夹内
plt.show() #显示图片
print(name + ' Success!')
def main():
start_epoch = args.start_epoch # start from epoch 0 or last checkpoint epoch
# Data
print('==> Preparing dataset %s' % args.dataset)
transform_train = transforms.Compose([
transforms.RandomCrop(32, padding=4),
transforms.RandomHorizontalFlip(),
transforms.ToTensor(),
transforms.Normalize((0.4914, 0.4822, 0.4465), (0.2023, 0.1994, 0.2010)),
])
transform_test = transforms.Compose([
transforms.ToTensor(),
transforms.Normalize((0.4914, 0.4822, 0.4465), (0.2023, 0.1994, 0.2010)),
])
if args.dataset == 'cifar10':
dataloader = datasets.CIFAR10
num_classes = 10
else:
dataloader = datasets.CIFAR100
num_classes = 100
trainset = dataloader(root=args.dataroot, train=True, download=True, transform=transform_train)
sampler = torch.utils.data.distributed.DistributedSampler(trainset,num_replicas=hvd.size(), rank=hvd.rank())
trainloader = data.DataLoader(dataset=trainset, batch_size=args.train_batch * world_size, shuffle=False, sampler=sampler)
testset = dataloader(root=args.dataroot, train=False, download=False, transform=transform_test)
testloader = data.DataLoader(testset, batch_size=args.test_batch * world_size, shuffle=False, num_workers=args.workers)
# Model
print("==> creating model '{}'".format("Alexnet"))
model = AlexNet(num_classes=num_classes)
device = torch.device('cuda', local_rank)
model = model.to(device)
# model = torch.nn.parallel.DistributedDataParallel(model, device_ids=[local_rank], output_device=local_rank)
print('Model on cuda:%d' % local_rank)
print(' Total params: %.2fM' % (sum(p.numel() for p in model.parameters())/1000000.0))
criterion = nn.CrossEntropyLoss()
optimizer = optim.SGD(model.parameters(), lr=args.lr, momentum=args.momentum, weight_decay=args.weight_decay)
# 用horovod封装优化器
optimizer = hvd.DistributedOptimizer(optimizer, named_parameters=model.named_parameters())
# 广播参数
hvd.broadcast_parameters(model.state_dict(), root_rank=0)
# Train and val
for epoch in range(start_epoch, args.epochs):
adjust_learning_rate(optimizer, epoch)
train_loss, train_acc = train(trainloader, model, criterion, optimizer, epoch, use_cuda)
test_loss, test_acc = test(testloader, model, criterion, epoch, use_cuda)
print('Rank:{} Epoch[{}/{}]: LR: {:.3f}, Train loss: {:.5f}, Test loss: {:.5f}, Train acc: {:.2f}, Test acc: {:.2f}.'.format(local_rank,epoch+1, args.epochs, state['lr'],
train_loss, test_loss, train_acc, test_acc))
def get_prediction(image_bytes):
# 异常处理：防止传入非图片的东西
try:
weights_path = "./Alexnet.pth"
class_json_path = "./class_indices.json"
assert os.path.exists(weights_path), "weights path does not exist..."
assert os.path.exists(class_json_path), "class json path does not exist..."
# select device
device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
print(device)
# create model
model = AlexNet(num_classes=5)
# load model weights
model.load_state_dict(torch.load(weights_path, map_location=device))
model.to(device)
model.eval()
# load class info
json_file = open(class_json_path, 'rb')
class_indict = json.load(json_file)
tensor = transform_image(image_bytes=image_bytes)
outputs = torch.softmax(model.forward(tensor).squeeze(), dim=0)
# detach去除梯度信息
prediction = outputs.detach().cpu().numpy()
# < 左对齐
template = "class:{:<15} probability:{:.3f}"
index_pre = [(class_indict[str(index)], float(p)) for index, p in enumerate(prediction)]
# sort probability
index_pre.sort(key=lambda x: x[1], reverse=True)
text = [template.format(k, v) for k, v in index_pre]
return_info = {"result": text}
except Exception as e:
return_info = {"result": [str(e)]}
return return_info
def _main(data_dir, batch_size, learning_rate, n_epoch):
'''
main function
'''
# Create dataloader
dataloaders_dict = create_dataloader(data_dir, batch_size)
# Detect if we have a GPU available
device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
# Create model
model = AlexNet()
model = model.to(device)
# Observe that all parameters are being optimized
optimizer_ft = optim.Adam(model.parameters(), lr=learning_rate)
criterion = nn.CrossEntropyLoss()
model = train_model(model, dataloaders_dict, criterion, optimizer_ft,
device, n_epoch)
torch.save(model, 'model.pt')
def main():
device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu") #指定设备
print("using {} device.".format(device))
data_transform = { #数据预处理
"train": transforms.Compose([transforms.RandomResizedCrop(224),# key 为trian 返回这些方法 随机裁剪 224*224
transforms.RandomHorizontalFlip(),#随机反转
transforms.ToTensor(),#转成
transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))]),#标准化处理
"val": transforms.Compose([transforms.Resize((224, 224)), # cannot 224, must (224, 224)
transforms.ToTensor(),
transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))])}
data_root = os.path.abspath(os.path.join(os.getcwd(), "../..")) # get data root path
image_path = os.path.join(data_root, "data_set", "dog_data") # flower data set path
assert os.path.exists(image_path), "{} path does not exist.".format(image_path)
train_dataset = datasets.ImageFolder(root=os.path.join(image_path, "train"),
transform=data_transform["train"])#数据预处理
train_num = len(train_dataset) #个数
# {'daisy':0, 'dandelion':1, 'roses':2, 'sunflower':3, 'tulips':4}
flower_list = train_dataset.class_to_idx #获取名称所对应索引
cla_dict = dict((val, key) for key, val in flower_list.items()) #遍历 key value 对调
# write dict into json file
json_str = json.dumps(cla_dict, indent=4)
with open('class_indices.json', 'w') as json_file:#生成json 便于打开
json_file.write(json_str)
batch_size = 32
nw = min([os.cpu_count(), batch_size if batch_size > 1 else 0, 8]) # number of workers
print('Using {} dataloader workers every process'.format(nw))
train_loader = torch.utils.data.DataLoader(train_dataset,
batch_size=batch_size, shuffle=True,
num_workers=nw) #加载
validate_dataset = datasets.ImageFolder(root=os.path.join(image_path, "val"),
transform=data_transform["val"])
val_num = len(validate_dataset)
validate_loader = torch.utils.data.DataLoader(validate_dataset,
batch_size=4, shuffle=False,
num_workers=nw)
print("using {} images for training, {} images fot validation.".format(train_num,
val_num))
# test_data_iter = iter(validate_loader)
# test_image, test_label = test_data_iter.next()
#
# def imshow(img):
# img = img / 2 + 0.5 # unnormalize
# npimg = img.numpy()
# plt.imshow(np.transpose(npimg, (1, 2, 0)))
# plt.show()
#
# print(' '.join('%5s' % cla_dict[test_label[j].item()] for j in range(4)))
# imshow(utils.make_grid(test_image))
net = AlexNet(num_classes=5, init_weights=True) #类别5
net.to(device) #网络设备
loss_function = nn.CrossEntropyLoss() #损失函数
# pata = list(net.parameters())
optimizer = optim.Adam(net.parameters(), lr=0.0002) #adam优化器 对象是网络中可训练参数 学习率 自己调参
save_path = './AlexNet.pth' #保存模型路径
best_acc = 0.0
for epoch in range(10):#训练
# train
net.train() #管理神经元失活
running_loss = 0.0 #统计平均损失
t1 = time.perf_counter() #训练时间
for step, data in enumerate(train_loader, start=0): #遍历数据集
images, labels = data #分为图像 标签
optimizer.zero_grad() #清空梯度信息
outputs = net(images.to(device)) #正向传播 指定设备
loss = loss_function(outputs, labels.to(device)) #损失
loss.backward() #反向传播
optimizer.step() #更新结点参数
# print statistics
running_loss += loss.item() #损失累加
# print train process
rate = (step + 1) / len(train_loader) #打印训练进度
a = "*" * int(rate * 50)
b = "." * int((1 - rate) * 50)
print("\rtrain loss: {:^3.0f}%[{}->{}]{:.3f}".format(int(rate * 100), a, b, loss), end="")
print()
print(time.perf_counter()-t1)
# validate
net.eval() #关闭失活
acc = 0.0 # accumulate accurate number / epoch
with torch.no_grad():
for val_data in validate_loader:
val_images, val_labels = val_data
outputs = net(val_images.to(device))
predict_y = torch.max(outputs, dim=1)[1] #最大就是类别
acc += (predict_y == val_labels.to(device)).sum().item() #预测与真实对比 累加
val_accurate = acc / val_num #准确率
if val_accurate > best_acc: #如果准确率大于历史最优
best_acc = val_accurate #更新
torch.save(net.state_dict(), save_path) #保存权重
print('[epoch %d] train_loss: %.3f test_accuracy: %.3f' % #打印信息
(epoch + 1, running_loss / step, val_accurate))
print('Finished Training')
optimizer = optim.Adam(model.parameters(), lr=learning_rate, betas=(0.9, 0.99))
criterion = nn.CrossEntropyLoss()
writer = SummaryWriter(outf + '/exp')
best_acc = float('-inf')
best_since_last = 0
for ep in range(start_epoch, epochs + 1):
if best_since_last == 20: break
elif best_since_last % 8 == 0 and best_since_last != 0:
adjust_learning_rate(optimizer, 0.5)
train_metrics = train(model, train_loader, optimizer, criterion, ep)
test_metrics = test(model, test_loader, criterion)
# print(train_metrics)
# print(test_metrics)
writer.add_scalar('train-acc', train_metrics['acc'], global_step=ep)
writer.add_scalar('train-loss', train_metrics['loss'], global_step=ep)
writer.add_scalar('test-acc', test_metrics['acc'], global_step=ep)
writer.add_scalar('test-loss', test_metrics['loss'], global_step=ep)
if best_acc < test_metrics['acc']:
best_since_last = 0
print(f'Found best at epoch {ep}\n')
best_acc = test_metrics['acc']
torch.save(model.cpu().state_dict(), outf + '/best.pth')
else:
best_since_last += 1
torch.save(model.cpu().state_dict(), outf + '/last.pth')
model.to(device)
def train(args):
device = torch.device(f"cuda:{args.device_id}")
model = AlexNet(n_cls=100, useLRN=args.useLRN, useDropOut=args.useDropOut)
# model = AlexNet(num_classes= 100)
criterion = nn.CrossEntropyLoss()
model.to(device)
optimizer = Adam(model.parameters(), lr=args.lr)
train_loader, valid_loader = getLoaders(split="train",
batch_size=args.batch_size,
num_workers=args.num_workers,
aug=args.useAug)
train_loss_arr = []
valid_loss_arr = []
valid_acc_arr = []
valid_top5_arr = []
n_iter = 0
best_loss = float('inf')
best_top1_acc = 0
best_top5_acc = 0
for ep in range(args.epoch):
model.train()
for _, (img, label) in tqdm(enumerate(train_loader),
total=len(train_loader)):
img, label = img.to(device), label.to(device)
optimizer.zero_grad()
pred = model(img)
loss = criterion(pred, label)
# loss = model.criterion(pred, label)
loss.backward()
optimizer.step()
train_loss_arr.append(loss.item())
n_iter += 1
model.eval()
ep_valid_loss_arr = []
ep_acc_arr = []
ep_top5_arr = []
with torch.no_grad():
for _, (img, label) in tqdm(enumerate(valid_loader),
total=len(valid_loader)):
img, label = img.to(device), label.to(device)
pred = model(img)
loss = criterion(pred, label)
# loss = model.criterion(pred, label)
acc = utils.top_k_acc(k=1,
pred=pred.detach().cpu().numpy(),
label=label.detach().cpu().numpy())
acc5 = utils.top_k_acc(k=5,
pred=pred.detach().cpu().numpy(),
label=label.detach().cpu().numpy())
ep_acc_arr.append(acc)
ep_top5_arr.append(acc5)
ep_valid_loss_arr.append(loss.item())
valid_loss = np.mean(ep_valid_loss_arr)
valid_acc = np.mean(ep_acc_arr)
valid_top5 = np.mean(ep_top5_arr)
train_loss = np.mean(train_loss_arr[-len(train_loader):])
valid_loss_arr.append(valid_loss)
if valid_loss < best_loss:
best_loss = valid_loss
best_top1_acc = valid_acc
best_top5_acc = valid_top5
model.cpu()
torch.save(model.state_dict(), "best_model.pth")
model.to(device)
if (ep + 1) % 10 == 0:
model.cpu()
torch.save(
{
"model": model.state_dict(),
"optimizer": optimizer.state_dict(),
"train_loss": train_loss_arr,
"valid_loss": valid_loss_arr,
"valid_acc": valid_acc_arr,
"valid_top5": valid_top5_arr,
"best_loss": best_loss,
"ep": ep,
"n_iter": n_iter,
}, "model_checkpoint.pth")
model.to(device)
print(
f"[{ep}, {n_iter}] train: {train_loss:.4f}, valid: {valid_loss:.4f}, acc: {valid_acc:.4f}, top5: {valid_top5:.4f}"
)
with open("exp_result.txt", "a+") as f:
f.write(
f"{args}, loss: {best_loss:.4f}, top1: {best_top1_acc*100:.1f}, top5: {best_top5_acc*100:.1f}\n"
)
def main():
device = torch.device('cuda:0' if torch.cuda.is_available() else 'cpu')
print("using {} device.".format(device))
tbwriter = SummaryWriter(log_dir="./logs")
data_transform = {
"train":
transforms.Compose([
transforms.RandomResizedCrop(360),
transforms.ToTensor(),
transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))
]),
"val":
transforms.Compose([
transforms.Resize(360, 360), # cannot 360, must (360,360)
transforms.ToTensor(),
transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))
])
}
data_root = os.path.abspath(os.path.join(os.getcwd(),
"./DATA")) # get data root path
image_path = os.path.join(data_root, "male") # flower data set path
assert os.path.exists(image_path), "{} path does not exist.".format(
image_path)
train_dataset = datasets.ImageFolder(root=os.path.join(
image_path, "train"),
transform=data_transform["train"])
train_num = len(train_dataset)
flower_list = train_dataset.class_to_idx
cla_dict = dict((val, key) for key, val in flower_list.items())
# write dict into json file
json_str = json.dumps(cla_dict, indent=2)
with open('class_indices.json', 'w') as json_file:
json_file.write(json_str)
batch_size = 8
nw = min([os.cpu_count(), batch_size if batch_size > 1 else 0,
8]) # number of workers
print('Using {} dataloader workers every process'.format(nw))
train_loader = torch.utils.data.DataLoader(train_dataset,
batch_size=batch_size,
shuffle=True,
num_workers=nw)
validate_dataset = datasets.ImageFolder(root=os.path.join(
image_path, "val"),
transform=data_transform["val"])
val_num = len(validate_dataset)
validate_loader = torch.utils.data.DataLoader(validate_dataset,
batch_size=8,
shuffle=True,
num_workers=nw)
print("using {} images for training, {} images fot validation.".format(
train_num, val_num))
if os.path.exists("./log360.pth"):
net = AlexNet()
#net.load_state_dict(torch.load("./log360.pth", map_location='cuda:2'))
net = torch.load("./log360.pth", 'cpu')
print("continue training")
else:
net = AlexNet(num_classes=3, init_weights=True)
net.to(device)
print("start training anew")
loss_function = nn.CrossEntropyLoss()
optimizer = optim.Adam(net.parameters(), lr=0.0001)
scheduler = optim.lr_scheduler.StepLR(optimizer, step_size=30, gamma=0.98)
epochs = 2000
save_path = './AlexNet.pth'
best_acc = 0.0
train_steps = len(train_loader)
#json_path = './class_indices.json'
#json_file = open(json_path, "r")
#class_indict = json.load(json_file)
#model = AlexNet(num_classed=6).to(device)
trainLOSS = [] #save loss
testLOSS = [] #save loss
valACC = [] #save val acc
for epoch in range(epochs):
scheduler.step()
print('LR:{}'.format(scheduler.get_lr()[0]))
# train
net.train()
running_loss = 0.0
train_bar = tqdm(train_loader)
for step, data in enumerate(train_bar):
images, labels = data
optimizer.zero_grad()
outputs = net(images.to(device))
loss = loss_function(outputs, labels.to(device))
loss.backward()
optimizer.step()
# print statistics
running_loss += loss.item()
train_bar.desc = "train epoch[{}/{}] loss:{:.3f}".format(
epoch + 1, epochs, loss)
# validate
net.eval()
acc = 0.0 # accumulate accurate number / epoch
with torch.no_grad():
val_bar = tqdm(validate_loader, colour='green')
for val_data in val_bar:
val_images, val_labels = val_data
outputs = net(val_images.to(device))
predict_y = torch.max(outputs, dim=1)[1]
acc += torch.eq(predict_y, val_labels.to(device)).sum().item()
val_accurate = acc / val_num
tbwriter.add_scalar('train/loss', running_loss / train_steps, epoch)
tbwriter.add_scalar('val/acc', val_accurate, epoch)
trainLOSS.append(running_loss / train_steps)
valACC.append(val_accurate)
print('[epoch %d] train_loss: %.3f val_accuracy: %.3f' %
(epoch + 1, running_loss / train_steps, val_accurate))
print(' ')
if val_accurate > best_acc:
best_acc = val_accurate
torch.save(net.state_dict(), save_path)
#predict
#weights_path="./AlexNet.pth"
#model.load_state_dict(torch.load(weights_path))
#model.eval()
#with torch.no_grad():
# putput = torch.squeeze(model(img.to(device))).cpu()
# predict = torch.softmax(output, dim=0)
# predict_cla = torch.argmax(predict.numpy)
npLOSS = np.array(trainLOSS)
npVALACC = np.array(valACC)
np.save('./save/loss_epoch_{}'.format(epoch), npLOSS)
np.save('./save/valacc_epoch_{}'.format(epoch), npVALACC)
print('Finished Training')
def main():
# viz = Visdom()
# viz.line([0.], [0.], win='train_loss', opts=dict(title='train loss'))
device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
print("using {} device.".format(device))
data_transform = {
"train":
transforms.Compose([
transforms.RandomResizedCrop(224),
transforms.RandomHorizontalFlip(),
transforms.ToTensor()
]),
"val":
transforms.Compose([
transforms.Resize((224, 224)), # cannot 224, must (224, 224)
transforms.ToTensor()
])
}
data_root = "/home/zhongsy/datasets/dataset/" # get data root path
train_dataset = datasets.ImageFolder(root=os.path.join(data_root, "train"),
transform=data_transform["train"])
# print(train_dataset.imgs)
train_num = len(train_dataset)
# {'daisy':0, 'dandelion':1, 'roses':2, 'sunflower':3, 'tulips':4}
flower_list = train_dataset.class_to_idx
cla_dict = dict((val, key) for key, val in flower_list.items())
# write dict into json file
json_str = json.dumps(cla_dict, indent=4)
with open('class_indices.json', 'w') as json_file:
json_file.write(json_str)
batch_size = 1
# number of workers
nw = min([os.cpu_count(), batch_size if batch_size > 1 else 0, 8])
print('Using {} dataloader workers every process'.format(nw))
train_loader = torch.utils.data.DataLoader(train_dataset,
batch_size=32,
shuffle=True,
num_workers=nw)
validate_dataset = datasets.ImageFolder(root=os.path.join(
data_root, "val"),
transform=data_transform["val"])
val_num = len(validate_dataset)
validate_loader = torch.utils.data.DataLoader(validate_dataset,
batch_size=4,
shuffle=False,
num_workers=nw)
print("using {} images for training, {} images for validation.".format(
train_num, val_num))
# test_data_iter = iter(validate_loader)
# test_image, test_label = test_data_iter.next()
#
# def imshow(img):
# img = img / 2 + 0.5 # unnormalize
# npimg = img.numpy()
# plt.imshow(np.transpose(npimg, (1, 2, 0)))
# plt.show()
#
# print(' '.join('%5s' % cla_dict[test_label[j].item()] for j in range(4)))
# imshow(utils.make_grid(test_image))
net = AlexNet(num_classes=2, init_weights=True)
net.to(device)
loss_function = nn.CrossEntropyLoss()
# pata = list(net.parameters())
optimizer = optim.Adam(net.parameters(), lr=0.0001)
epochs = 30
save_path = './AlexNet.pt'
best_acc = 0.0
train_steps = len(train_loader)
global_step = 0
for epoch in range(epochs):
# train
epochloss = 100000
net.train()
running_loss = 0.0
train_bar = tqdm(train_loader)
for step, data in enumerate(train_bar):
images, labels = data
# print("label: ", labels, labels.dtype)
optimizer.zero_grad()
outputs = net(images.to(device))
# print("imges: ", images, images.dtype)
# outputs_ = outputs.squeeze()
# print("output__ : ", outputs_)
# outputs_ = outputs.to(torch.float)
loss = loss_function(outputs, labels.to(device))
# loss = loss.to(torch.float)
if epochloss > loss:
epochloss = loss
loss.backward()
optimizer.step()
# print statistics
running_loss += loss.item()
train_bar.desc = "train epoch[{}/{}] loss:{:.3f}".format(
epoch + 1, epochs, loss)
# viz.line([epochloss.cpu().detach().numpy()], [global_step],
# win='train_loss', update='append')
global_step += 1
print("[ start val ]")
# validate
net.eval()
acc = 0.0 # accumulate accurate number / epoch
with torch.no_grad():
val_bar = tqdm(validate_loader)
for val_data in val_bar:
val_images, val_labels = val_data
val_labels.unsqueeze(1)
outputs = net(val_images.to(device))
predict_y = torch.max(outputs, dim=1)[1]
# print("prect ;", predict_y)
# outputs = outputs.squeeze()
# print("out_puts: ", outputs)
# a = torch.gt(outputs, 0.5)
# print("a ", a)
# for i, (data, label_) in enumerate(zip(outputs, val_labels)):
# if abs(data-label_) <= 0.5:
# acc += 1
# viz.images(val_images.view(-1, 3, 224, 224), win='x')
# viz.text(str(predict_y.detach().cpu().numpy()),
# win='pred', opts=dict(title='pred'))
acc += torch.eq(predict_y, val_labels.to(device)).sum().item()
val_accurate = acc / val_num
print('[epoch %d] train_loss: %.3f val_accuracy: %.3f' %
(epoch + 1, running_loss / train_steps, val_accurate))
if val_accurate > best_acc:
best_acc = val_accurate
torch.save(net, save_path)
print('Finished Training')
# test_data_iter = iter(validate_loader)
# test_image, test_label = test_data_iter.next()
#
# def imshow(img):
# img = img / 2 + 0.5 # unnormalize
# npimg = img.numpy()
# plt.imshow(np.transpose(npimg, (1, 2, 0)))
# plt.show()
#
# print(' '.join('%5s' % cla_dict[test_label[j].item()] for j in range(4)))
# imshow(utils.make_grid(test_image))
net = AlexNet(num_classes=5, init_weights=True) # 构造一个新模型
#net.load_state_dict(torch.load("./AlexNet.pth"))
net.to(device) # 将数据迁移到GPU（如果有的话）
loss_function = nn.CrossEntropyLoss() # 损失函数
#pata = list(net.parameters())
optimizer = optim.Adam(net.parameters(), lr=0.0002) # 梯度下降优化器
save_path = './AlexNet.pth'
best_acc = 0.0 # 历史最高准确率（每一个epoch得到的模型都有一个新的准确率）
for epoch in range(10):
net.train() # 训练模式开启
running_loss = 0.0
t1 = time.perf_counter()
for step, data in enumerate(train_loader, start=0):
images, labels = data
optimizer.zero_grad() # 各参数梯度置零，否则梯度会累加
outputs = net(images.to(device)) # 将数据正向过一遍网络，得到一个输出
loss = loss_function(outputs, labels.to(device)) # 计算输出值和期望值的某种误差
def main():
device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
print("using {} device.".format(device))
data_transform = {
"train":
transforms.Compose([
transforms.RandomResizedCrop(224),
transforms.RandomHorizontalFlip(),
transforms.ToTensor(),
transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))
]),
"val":
transforms.Compose([
transforms.Resize((224, 224)), # cannot 224, must (224, 224)
transforms.ToTensor(),
transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))
])
}
data_root = os.path.abspath(os.path.join(os.getcwd(),
"../..")) # get data root path
image_path = os.path.join(data_root, "data_set",
"flower_data") # flower data set path
assert os.path.exists(image_path), "{} path does not exist.".format(
image_path)
train_dataset = datasets.ImageFolder(root=os.path.join(
image_path, "train"),
transform=data_transform["train"])
train_num = len(train_dataset)
# {'daisy':0, 'dandelion':1, 'roses':2, 'sunflower':3, 'tulips':4}
flower_list = train_dataset.class_to_idx
cla_dict = dict((val, key) for key, val in flower_list.items())
# write dict into json file
json_str = json.dumps(cla_dict, indent=4)
with open('class_indices.json', 'w') as json_file:
json_file.write(json_str)
batch_size = 32
nw = min([os.cpu_count(), batch_size if batch_size > 1 else 0,
8]) # number of workers
print('Using {} dataloader workers every process'.format(nw))
train_loader = torch.utils.data.DataLoader(train_dataset,
batch_size=batch_size,
shuffle=True,
num_workers=nw)
validate_dataset = datasets.ImageFolder(root=os.path.join(
image_path, "val"),
transform=data_transform["val"])
val_num = len(validate_dataset)
validate_loader = torch.utils.data.DataLoader(validate_dataset,
batch_size=4,
shuffle=False,
num_workers=nw)
print("using {} images for training, {} images for validation.".format(
train_num, val_num))
# test_data_iter = iter(validate_loader)
# test_image, test_label = test_data_iter.next()
#
# def imshow(img):
# img = img / 2 + 0.5 # unnormalize
# npimg = img.numpy()
# plt.imshow(np.transpose(npimg, (1, 2, 0)))
# plt.show()
#
# print(' '.join('%5s' % cla_dict[test_label[j].item()] for j in range(4)))
# imshow(utils.make_grid(test_image))
net = AlexNet(num_classes=5, init_weights=True)
net.to(device)
loss_function = nn.CrossEntropyLoss()
# pata = list(net.parameters())
optimizer = optim.Adam(net.parameters(), lr=0.0002)
epochs = 10
save_path = './AlexNet.pth'
best_acc = 0.0
train_steps = len(train_loader)
for epoch in range(epochs):
# train
net.train()
running_loss = 0.0
train_bar = tqdm(train_loader)
for step, data in enumerate(train_bar):
images, labels = data
optimizer.zero_grad()
outputs = net(images.to(device))
loss = loss_function(outputs, labels.to(device))
loss.backward()
optimizer.step()
# print statistics
running_loss += loss.item()
train_bar.desc = "train epoch[{}/{}] loss:{:.3f}".format(
epoch + 1, epochs, loss)
# validate
net.eval()
acc = 0.0 # accumulate accurate number / epoch
with torch.no_grad():
val_bar = tqdm(validate_loader)
for val_data in val_bar:
val_images, val_labels = val_data
outputs = net(val_images.to(device))
predict_y = torch.max(outputs, dim=1)[1]
acc += torch.eq(predict_y, val_labels.to(device)).sum().item()
val_accurate = acc / val_num
print('[epoch %d] train_loss: %.3f val_accuracy: %.3f' %
(epoch + 1, running_loss / train_steps, val_accurate))
if val_accurate > best_acc:
best_acc = val_accurate
torch.save(net.state_dict(), save_path)
print('Finished Training')
bps = 115200
flag = False # 判断串口打开是否成功
data = ''
# 自定义灰度界限，大于这个值为白色，小于这个值为黑色(与原图黑白颠倒)
threshold = 100
# 二值化处理表
table = []
for i in range(256):
if i < threshold:
table.append(1)
else:
table.append(0)
model = AlexNet()
model.load_state_dict(torch.load('./logs/mnist/best.pth'))
model = model.to(device)
try:
# 打开串口，并得到串口对象
ser = serial.Serial(port, bps)
# 判断是否打开成功
if ser.is_open:
flag = True
print('Server start!')
except Exception as e:
print("ERROR: ", e)
if flag:
while True:
time.sleep(0.5)
data += ser.read_all().decode('ascii')
def main():
device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
print("using {} device.".format(device))
batch_size = 16
epochs = 20
data_transform = {
"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_root = os.path.abspath(os.path.join(os.getcwd(),
".")) # get data root path
image_path = os.path.join(data_root, "data_set",
"flower_data") # flower data set path
assert os.path.exists(image_path), "{} path does not exist.".format(
image_path)
train_dataset = datasets.ImageFolder(root=os.path.join(
image_path, "train"),
transform=data_transform["train"])
train_num = len(train_dataset)
# {'daisy':0, 'dandelion':1, 'roses':2, 'sunflower':3, 'tulips':4}
flower_list = train_dataset.class_to_idx
cla_dict = dict((val, key) for key, val in flower_list.items())
# write dict into json file
json_str = json.dumps(cla_dict, indent=4)
with open('class_indices.json', 'w') as json_file:
json_file.write(json_str)
nw = min([os.cpu_count(), batch_size if batch_size > 1 else 0,
8]) # number of workers
print('Using {} dataloader workers every process'.format(nw))
train_loader = torch.utils.data.DataLoader(train_dataset,
batch_size=batch_size,
shuffle=True,
num_workers=nw)
validate_dataset = datasets.ImageFolder(root=os.path.join(
image_path, "val"),
transform=data_transform["val"])
val_num = len(validate_dataset)
validate_loader = torch.utils.data.DataLoader(validate_dataset,
batch_size=batch_size,
shuffle=False,
num_workers=nw)
print("using {} images for training, {} images for validation.".format(
train_num, val_num))
# create model
net = AlexNet(num_classes=5)
net.to(device)
# define loss function
loss_function = nn.CrossEntropyLoss()
# construct an optimizer
params = [p for p in net.parameters() if p.requires_grad]
optimizer = optim.Adam(params, lr=0.0001)
best_acc = 0.0
save_path = 'weights/alexnet.pth'
train_steps = len(train_loader)
for epoch in range(epochs):
# train
net.train()
running_loss = 0.0
train_bar = tqdm(train_loader)
for step, data in enumerate(train_bar):
images, labels = data
optimizer.zero_grad()
logits = net(images.to(device))
loss = loss_function(logits, labels.to(device))
loss.backward()
optimizer.step()
# print statistics
running_loss += loss.item()
train_bar.desc = "train epoch[{}/{}] loss:{:.3f}".format(
epoch + 1, epochs, loss)
# validate
net.eval()
acc = 0.0 # accumulate accurate number / epoch
with torch.no_grad():
val_bar = tqdm(validate_loader)
for val_data in val_bar:
val_images, val_labels = val_data
outputs = net(val_images.to(device))
# loss = loss_function(outputs, test_labels)
predict_y = torch.max(outputs, dim=1)[1]
acc += torch.eq(predict_y, val_labels.to(device)).sum().item()
val_bar.desc = "valid epoch[{}/{}]".format(epoch + 1, epochs)
val_accurate = acc / val_num
print('[epoch %d] train_loss: %.3f val_accuracy: %.3f' %
(epoch + 1, running_loss / train_steps, val_accurate))
if val_accurate > best_acc:
best_acc = val_accurate
torch.save(net.state_dict(), save_path)
print('Finished Training')
# test_data_iter = iter(validate_loader)
# test_image, test_label = test_data_iter.next()
#
# def imshow(img):
# img = img / 2 + 0.5 # unnormalize
# npimg = img.numpy()
# plt.imshow(np.transpose(npimg, (1, 2, 0)))
# plt.show()
#
# print(' '.join('%5s' % cla_dict[test_label[j].item()] for j in range(4)))
# imshow(utils.make_grid(test_image))
net = AlexNet(num_classes=5, init_weights=True)
net.to(device)
loss_function = nn.CrossEntropyLoss()
# pata = list(net.parameters())
# lr: learning_rate
optimizer = optim.Adam(net.parameters(), lr=0.0002)
save_path = r'D:\Document\GitHub\deep-learning-for-image-processing\pytorch_classification\Test2_alexnet\AlexNet.pth'
best_acc = 0.0
epo = 20
for epoch in range(epo):
# train
net.train()
running_loss = 0.0
t1 = time.perf_counter()
#从train_loader,加载一个batch
def train():
try:
os.makedirs(opt.checkpoints_dir)
except OSError:
pass
if torch.cuda.device_count() > 1:
model = torch.nn.parallel.DataParallel(
AlexNet(num_classes=opt.num_classes))
else:
model = AlexNet(num_classes=opt.num_classes)
if os.path.exists(MODEL_PATH):
model.load_state_dict(
torch.load(MODEL_PATH, map_location=lambda storage, loc: storage))
model.to(device)
################################################
# Set loss function and Adam optimizer
################################################
criterion = torch.nn.CrossEntropyLoss()
optimizer = optim.Adam(model.parameters(), lr=opt.lr)
for epoch in range(opt.epochs):
# train for one epoch
print(f"\nBegin Training Epoch {epoch + 1}")
# Calculate and return the top-k accuracy of the model
# so that we can track the learning process.
losses = AverageMeter()
top1 = AverageMeter()
top5 = AverageMeter()
for i, data in enumerate(train_dataloader):
# get the inputs; data is a list of [inputs, labels]
inputs, targets = data
inputs = inputs.to(device)
targets = targets.to(device)
# compute output
output = model(inputs)
loss = criterion(output, targets)
# measure accuracy and record loss
prec1, prec5 = accuracy(output, targets, topk=(1, 2))
losses.update(loss.item(), inputs.size(0))
top1.update(prec1, inputs.size(0))
top5.update(prec5, inputs.size(0))
# compute gradients in a backward pass
optimizer.zero_grad()
loss.backward()
# Call step of optimizer to update model params
optimizer.step()
print(
f"Epoch [{epoch + 1}] [{i + 1}/{len(train_dataloader)}]\t"
f"Loss {loss.item():.4f}\t"
f"Prec@1 {top1.val:.3f} ({top1.avg:.3f})\t"
f"Prec@5 {top5.val:.3f} ({top5.avg:.3f})",
end="\r")
# save model file
torch.save(model.state_dict(), MODEL_PATH)
def main():
device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
print(device)
data_transform = {
"train":
transforms.Compose([
transforms.RandomResizedCrop(224),
transforms.RandomHorizontalFlip(),
transforms.ToTensor(),
transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))
]),
"val":
transforms.Compose([
transforms.Resize((224, 224)), # cannot 224, must (224, 224)
transforms.ToTensor(),
transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))
])
}
data_root = os.path.abspath(os.path.join(os.getcwd(), "./"))
image_path = os.path.join(data_root, "flower_data")
train_dataset = datasets.ImageFolder(root=image_path + "/train",
transform=data_transform['train'])
train_num = len(train_dataset)
# {'daisy':0, 'dandelion':1, 'roses':2, 'sunflower':3, 'tulips':4}
flower_list = train_dataset.class_to_idx
cla_dict = dict((val, key) for key, val in flower_list.items())
# write dict into json file
json_str = json.dumps(cla_dict, indent=4)
with open('class_indices.json', 'w') as json_file:
json_file.write(json_str)
batch_size = 8
train_loader = torch.utils.data.DataLoader(train_dataset,
batch_size=batch_size,
shuffle=True,
num_workers=0)
validate_dataset = datasets.ImageFolder(root=image_path + "/val",
transform=data_transform["val"])
val_num = len(validate_dataset)
validate_loader = torch.utils.data.DataLoader(validate_dataset,
batch_size=4,
shuffle=True,
num_workers=0)
# test_data_iter = iter(validate_loader)
# test_image, test_label = test_data_iter.next()
#
# def imshow(img):
# img = img / 2 + 0.5 # unnormalize
# npimg = img.numpy()
# plt.imshow(np.transpose(npimg, (1, 2, 0)))
# plt.show()
#
# print(' '.join('%5s' % cla_dict[test_label[j].item()] for j in range(4)))
# imshow(utils.make_grid(test_image))
net = AlexNet(num_class=5)
print(net)
net.to(device)
loss_function = nn.CrossEntropyLoss()
# pata = list(net.parameters())
optimizer = optim.Adam(net.parameters(), lr=0.0002)
save_path = './AlexNet.pth'
best_acc = 0.0
for epoch in range(10):
# train
net.train()
running_loss = 0.0
t1 = time.perf_counter()
for step, data in enumerate(train_loader, start=0):
images, labels = data
optimizer.zero_grad()
outputs = net(images.to(device))
loss = loss_function(outputs, labels.to(device))
loss.backward()
optimizer.step()
# print statistics
running_loss += loss.item()
# print train process
rate = (step + 1) / len(train_loader)
a = "*" * int(rate * 50)
b = "." * int((1 - rate) * 50)
print("\rtrain loss: {:^3.0f}%[{}->{}]{:.3f}".format(
int(rate * 100), a, b, loss),
end="")
print()
print(time.perf_counter() - t1)
# validate
net.eval()
acc = 0.0 # accumulate accurate number / epoch
# 验证过程中不计算损失梯度
with torch.no_grad():
for val_data in validate_loader:
val_images, val_labels = val_data
outputs = net(val_images.to(device))
predict_y = torch.max(outputs, dim=1)[1]
acc += (predict_y == val_labels.to(device)).sum().item()
val_accurate = acc / val_num
if val_accurate > best_acc:
best_acc = val_accurate
torch.save(net.state_dict(), save_path)
print('[epoch %d] train_loss: %.3f test_accuracy: %.3f' %
(epoch + 1, running_loss / step, val_accurate))
print('Finished Training')
num_workers=0)
# 存储 索引：标签 的字典
# 字典，类别：索引 {'daisy':0, 'dandelion':1, 'roses':2, 'sunflower':3, 'tulips':4}
flower_list = train_dataset.class_to_idx
# 将 flower_list 中的 key 和 val 调换位置
cla_dict = dict((val, key) for key, val in flower_list.items())
# 将 cla_dict 写入 json 文件中
json_str = json.dumps(cla_dict, indent=4)
with open('class_indices.json', 'w') as json_file:
json_file.write(json_str)
#训练过程
net = AlexNet(num_classes=5, init_weights=True) # 实例化网络（输出类型为5，初始化权重）
net.to(device) # 分配网络到指定的设备（GPU/CPU）训练
loss_function = nn.CrossEntropyLoss() # 交叉熵损失
optimizer = optim.Adam(net.parameters(), lr=0.0002) # 优化器（训练参数，学习率）
save_path = './AlexNet.pth'
best_acc = 0.0
for epoch in range(150):
########################################## train ###############################################
net.train() # 训练过程中开启 Dropout
running_loss = 0.0 # 每个 epoch 都会对 running_loss 清零
time_start = time.perf_counter() # 对训练一个 epoch 计时
for step, data in enumerate(train_loader, start=0): # 遍历训练集，step从0开始计算
images, labels = data # 获取训练集的图像和标签
optimizer.zero_grad() # 清除历史梯度
# print(alexnet_dict.keys())
print("Load from pretrained")
# Freeze parameter
if freeze_layer:
for name, value in alexnet.named_parameters():
if (name != "classifier.6.weight") and (name != "classifier.6.bias"):
value.requires_grad = False
print("Freeze layer")
# train on multiple GPUs
DEVICE_IDS = list(range(GPU_NUM))
# alexnet = alexnet.to(device)
if GPU_NUM > 1:
alexnet = torch.nn.parallel.DataParallel(alexnet, device_ids=DEVICE_IDS)
alexnet = alexnet.to(device)
print(alexnet)
print("Network created")
# data normalization
normalize = transforms.Normalize(mean=[0.485, 0.456, 0.406],
std=[0.229, 0.224, 0.225])
if not testing_only:
# create data loader
dataloader_train = DataLoader(
datasets.CIFAR10(root='./data', train=True, transform=transforms.Compose([
transforms.RandomHorizontalFlip(),
transforms.RandomCrop(32, 4),
transforms.ToTensor(),
normalize,
def model_retrain(number_class):
model = AlexNet(number_class)
model = model.to(device)
return model
def main():
device = torch.device("cuda:0" if torch.cuda.is_available() else
"cpu") # torch.device规定训练中所使用的设备
print("using {} device.".format(device))
data_transform = { # data_transform数据预处理
"train":
transforms.Compose([
transforms.RandomResizedCrop(224), # 随机裁剪为224*224
transforms.RandomHorizontalFlip(), # 水平方向随机翻转
transforms.ToTensor(), # 转化为tensor
transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))
]), # 标准化处理
"val":
transforms.Compose([
transforms.Resize((224, 224)), # * cannot 224, must (224, 224)
transforms.ToTensor(),
transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))
])
}
print(os.getcwd())
# data_root = os.path.abspath(os.path.join(os.getcwd(), "../..")) # get data root path
# 先获取数据集所在的根目录os.getcwd()
# ^ os.getcwd() 返回当前进程的工作目录，并非当前文件所在的目录
# "../.."表示的是上两层目录，这个要看具体的情况，这是一个相对路径的写法
# ^ os.path.join 路径拼接，拼接后得到的就是当前目录的上两级目录
# ^ os.path.abspath() 获取指定文件或目录的绝对路径（完整路径）
data_root = os.path.abspath(os.getcwd())
image_path = os.path.join(data_root, "data_set",
"flower_data") # flower data set path
# 等价于 image_path = data_root + "data_set/flower_data"
# assert os.path.exists(image_path), "{} path does not exist.".format(image_path)
train_dataset = datasets.ImageFolder(
root=os.path.join(image_path, "train"), # 下载数据集 ，"train"表示是训练集数据
transform=data_transform["train"]) # 使用"train"的预处理方式
train_num = len(train_dataset) # 查看训练集有多少张图片
# {'daisy':0, 'dandelion':1, 'roses':2, 'sunflower':3, 'tulips':4}
flower_list = train_dataset.class_to_idx # * .class_to_idx 得到分类名称对应的索引
cla_dict = dict(
(val, key) for key, val in flower_list.items()) # * 将刚刚字典的键值对 变为 值键对
# write dict into json file
json_str = json.dumps(cla_dict, indent=4) # 将刚刚的字典变为json形式
with open('class_indices.json', 'w') as json_file:
json_file.write(json_str)
batch_size = 32
nw = min([os.cpu_count(), batch_size if batch_size > 1 else 0,
8]) # number of workers
print('Using {} dataloader workers every process'.format(nw))
train_loader = torch.utils.data.DataLoader(
train_dataset, # 加载数据集
batch_size=batch_size,
shuffle=True, # 通过batchsize和随机参数从样本中获取一批批数据
num_workers=nw) # wins下num_workers一般设置为0，linux下num_workers设置可以分布式计算
validate_dataset = datasets.ImageFolder(
root=os.path.join(
image_path, "val"
), # root=os.path.join(image_path, "val")等价于 root=image_path+"val"
transform=data_transform["val"])
val_num = len(validate_dataset)
validate_loader = torch.utils.data.DataLoader(
validate_dataset,
batch_size=batch_size,
shuffle=False, # batch_size=4, shuffle=True,
num_workers=nw)
print("using {} images for training, {} images for validation.".format(
train_num, val_num))
# 下面是查看数据集的demo
# 注意，第60行的batch_size=4, shuffle=True再查看：
# test_data_iter = iter(validate_loader)
# test_image, test_label = test_data_iter.next()
# def imshow(img):
# img = img / 2 + 0.5 # unnormalize
# npimg = img.numpy()
# plt.imshow(np.transpose(npimg, (1, 2, 0)))
# plt.show()
# print(' '.join('%5s' % cla_dict[test_label[j].item()] for j in range(4)))
# imshow(utils.make_grid(test_image))
net = AlexNet(num_classes=5, init_weights=True) # 5个类别的花数据集，初始化权重为True
# 实例化模型对象 net
net.to(device) # ^ net.to(device)将网络放入刚刚指定的设备中
loss_function = nn.CrossEntropyLoss() # 定义损失函数，多类别的交叉熵函数
# pata = list(net.parameters()) # 调试所用，查看模型的参数
optimizer = optim.Adam(
net.parameters(),
lr=0.0002) # 定义Adam优化器，优化对象是网络中所有的可训练参数net.parameters(),以及学习了lr=0.0002
epochs = 10
save_path = './AlexNet.pth' # 保存权重的路径
best_acc = 0.0 # 最佳准确率 best_acc，首先初始化为0，后面再更新
train_steps = len(train_loader)
for epoch in range(epochs): # 迭代10次
# * 因为使用了dropout，只在训练中使用，预测中不使用
# train # & 训练阶段
net.train() # 调用net.train()进入训练阶段，同时使用 dropout 方法
running_loss = 0.0 # 统计训练中的平均损失
train_bar = tqdm(train_loader) # 为了统计训练一个epoch所需时间
for step, data in enumerate(train_bar): # 遍历数据集；数据集分为图像和标签
images, labels = data
optimizer.zero_grad() # 梯度清0
outputs = net(
images.to(device)) # 正向传播，图像放入设备中，然后实例化AlexNet的网络net中
loss = loss_function(
outputs, labels.to(device)) # 计算损失，计算预测值与真实值的损失，这里label也要放入设备中
loss.backward() # 反向传播到每一个节点
optimizer.step() # 更新每一个节点的参数
# print statistics
running_loss += loss.item() # 累加loss值
train_bar.desc = "train epoch[{}/{}] loss:{:.3f}".format(
epoch + 1, epochs, loss) # 为了或者训练进度
# validate # & 测试阶段
net.eval() # 调用net.eval() 进入测试阶段，同时关闭 dropout 方法
acc = 0.0 # accumulate accurate number / epoch
with torch.no_grad(): # * with torch.no_grad() 禁止参数跟踪：验证中不计算损失梯度
val_bar = tqdm(validate_loader)
for val_data in val_bar:
val_images, val_labels = val_data # 数据划分为图片和对应的标签
outputs = net(
val_images.to(device)) # 放入网络net中得到输出，输出的维度是 [batch， 10]
predict_y = torch.max(
outputs, dim=1
)[1] # 求出输出的第1个维度（dim=1类别维度）max（只关注最大值对应的位置[1]，不关心数值 ），得到预测值 predict_y
acc += torch.eq(predict_y, val_labels.to(
device)).sum().item() # 统计预测正确的个数 # ^ 通过.item()得到相应的数值
# acc += (predict_y == val_labels.to(device)).sum().item() # 等价的
val_accurate = acc / val_num # 累加的准确率除以样本个数，得到平均准确率
print('[epoch %d] train_loss: %.3f val_accuracy: %.3f' %
(epoch + 1, running_loss / train_steps, val_accurate))
if val_accurate > best_acc: # 如果当前准确率大于历史最优准确率
best_acc = val_accurate # 更新
torch.save(net.state_dict(), save_path)
print('Finished Training')
