我对神经网络是新手，正在尝试在一个自定义数据集（单一目录中的猫和狗图片）上训练一个CNN模型。所以我想我在这里做的是大多数教程中常见的操作，但以防万一，我会在这里提供我的完整代码。

首先，我生成要处理的.csv文件：

import osimport torchdevice = ("cuda" if torch.cuda.is_available() else "cpu")train_df = pd.DataFrame(columns=["img_name","label"])train_df["img_name"] = os.listdir("train/")for idx, i in enumerate(os.listdir("train/")):    if "cat" in i:        train_df["label"][idx] = 0    if "dog" in i:        train_df["label"][idx] = 1train_df.to_csv (r'train_csv.csv', index = False, header=True)

然后我准备数据集：

from torch.utils.data import Datasetimport pandas as pdimport osfrom PIL import Imageimport torchclass CatsAndDogsDataset(Dataset):    def __init__(self, root_dir, annotation_file, transform=None):        self.root_dir = root_dir        self.annotations = pd.read_csv(annotation_file)        self.transform = transform    def __len__(self):        return len(self.annotations)    def __getitem__(self, index):        img_id = self.annotations.iloc[index, 0]        img = Image.open(os.path.join(self.root_dir, img_id)).convert("RGB")        y_label = torch.tensor(float(self.annotations.iloc[index, 1]))        if self.transform is not None:            img = self.transform(img)        return (img, y_label)

这是我的模型：

import torch.nn as nnimport torchvision.models as modelsclass CNN(nn.Module):    def __init__(self, train_CNN=False, num_classes=1):        super(CNN, self).__init__()        self.train_CNN = train_CNN        self.inception = models.inception_v3(pretrained=True, aux_logits=False)        self.inception.fc = nn.Linear(self.inception.fc.in_features, num_classes)        self.relu = nn.ReLU()        self.dropout = nn.Dropout(0.5)        self.sigmoid = nn.Sigmoid()    def forward(self, images):        features = self.inception(images)        return self.sigmoid(self.dropout(self.relu(features))).squeeze(1)

这是我的超参数、变换和数据加载器：

from torch.utils.data import DataLoaderimport torchvision.transforms as transformsnum_epochs = 10learning_rate = 0.00001train_CNN = Falsebatch_size = 32shuffle = Truepin_memory = Truenum_workers = 0transform = transforms.Compose(        [            transforms.Resize((356, 356)),            transforms.RandomCrop((299, 299)),            transforms.ToTensor(),            transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5)),        ]    )dataset = CatsAndDogsDataset("train","train_csv.csv",transform=transform)print(len(dataset))train_set, validation_set = torch.utils.data.random_split(dataset,[162,40])train_loader = DataLoader(dataset=train_set, shuffle=shuffle, batch_size=batch_size,num_workers=num_workers,pin_memory=pin_memory)validation_loader = DataLoader(dataset=validation_set, shuffle=shuffle, batch_size=batch_size,num_workers=num_workers, pin_memory=pin_memory)model = CNN().to(device)criterion = nn.BCELoss()optimizer = torch.optim.Adam(model.parameters(), lr=learning_rate)for name, param in model.inception.named_parameters():    if "fc.weight" in name or "fc.bias" in name:        param.requires_grad = True    else:        param.requires_grad = train_CNN

以及准确率检查：

def check_accuracy(loader, model):    if loader == train_loader:        print("Checking accuracy on training data")    else:        print("Checking accuracy on validation data")    num_correct = 0    num_samples = 0    model.eval()    with torch.no_grad():        for x, y in loader:            x = x.to(device=device)            y = y.to(device=device)            scores = model(x)            predictions = torch.tensor([1.0 if i >= 0.5 else 0.0 for i in scores]).to(device)            num_correct += (predictions == y).sum()            num_samples += predictions.size(0)    print(            f"Got {num_correct} / {num_samples} with accuracy {float(num_correct)/float(num_samples)*100:.2f}"        )    model.train()    return f"{float(num_correct)/float(num_samples)*100:.2f}"    

这是我的训练函数：

from tqdm import tqdmdef train():    model.train()    for epoch in range(num_epochs):        loop = tqdm(train_loader, total = len(train_loader), leave = True)        if epoch % 2 == 0:            loop.set_postfix(val_acc = check_accuracy(validation_loader, model))        for imgs, labels in loop:            imgs = imgs.to(device)            labels = labels.to(device)            outputs = model(imgs)            loss = criterion(outputs, labels)            optimizer.zero_grad()            loss.backward()            optimizer.step()            loop.set_description(f"Epoch [{epoch}/{num_epochs}]")            loop.set_postfix(loss = loss.item())if __name__ == "__main__":    train()

0%|          | 0/6 [00:00<?, ?it/s]Checking accuracy on validation data0%|          | 0/6 [01:13<?, ?it/s, val_acc=60.00]Got 24 / 40 with accuracy 60.00Epoch [0/10]: 100%|██████████| 6/6 [06:02<00:00, 60.39s/it, loss=0.693]Epoch [1/10]: 100%|██████████| 6/6 [04:49<00:00, 48.23s/it, loss=0.693]...Epoch [8/10]: 100%|██████████| 6/6 [06:07<00:00, 61.29s/it, loss=0.693]Epoch [9/10]: 100%|██████████| 6/6 [04:55<00:00, 49.19s/it, loss=0.781]

模型训练得很好，但当我尝试使用它进行预测时，每次在我的Jupyter Notebooks中运行最后一段代码时都会得到不同的结果：

model.eval()img = Image.open('train/cat.22.png').convert("RGB")img_t = transform(img)batch_t = torch.unsqueeze(img_t, 0)out = model(batch_t)print(out)

tensor([0.5276], grad_fn=)

tensor([0.5000], grad_fn=)

tensor([0.5064], grad_fn=)

等等。对于同一张图片每次得到不同的结果。这正常吗？为什么会这样？

回答：

我没有看到你加载训练好的模型。这意味着每次你初始化CNN模块时，inception.fc层将被随机权重初始化，这很可能是你每次推理时得到不同结果的原因。

编辑：你在变换流程中有一个随机变换，即RandomCrop。