deep-learning - UNet 模型准确率精确地停留在 0.5（或多或少）（没有类不平衡，尝试调整学习率）

Question

这是使用 PyTorch

我一直在尝试在我的图像上实现 UNet 模型，但是，我的模型精度始终精确为 0.5。损失确实减少了。

我还检查了班级不平衡。我也试过玩学习率。学习率影响损失，但不影响准确性。

我在下面的架构（来自这里）

""" `UNet` class is based on https://arxiv.org/abs/1505.04597

The U-Net is a convolutional encoder-decoder neural network.
Contextual spatial information (from the decoding,
expansive pathway) about an input tensor is merged with
information representing the localization of details
(from the encoding, compressive pathway).

Modifications to the original paper:
(1) padding is used in 3x3 convolutions to prevent loss
    of border pixels
(2) merging outputs does not require cropping due to (1)
(3) residual connections can be used by specifying
    UNet(merge_mode='add')
(4) if non-parametric upsampling is used in the decoder
    pathway (specified by upmode='upsample'), then an
    additional 1x1 2d convolution occurs after upsampling
    to reduce channel dimensionality by a factor of 2.
    This channel halving happens with the convolution in
    the tranpose convolution (specified by upmode='transpose')


    Arguments:
        in_channels: int, number of channels in the input tensor.
                     Default is 3 for RGB images. Our SPARCS dataset is 13 channel.
              depth: int, number of MaxPools in the U-Net. During training, input size needs to be 
                     (depth-1) times divisible by 2
        start_filts: int, number of convolutional filters for the first conv.
            up_mode: string, type of upconvolution. Choices: 'transpose' for transpose convolution 

"""

class UNet(nn.Module):

    def __init__(self, num_classes, depth, in_channels, start_filts=16, up_mode='transpose', merge_mode='concat'):

        super(UNet, self).__init__()

        if up_mode in ('transpose', 'upsample'):
            self.up_mode = up_mode
        else:
            raise ValueError("\"{}\" is not a valid mode for upsampling. Only \"transpose\" and \"upsample\" are allowed.".format(up_mode))

        if merge_mode in ('concat', 'add'):
            self.merge_mode = merge_mode
        else:
            raise ValueError("\"{}\" is not a valid mode for merging up and down paths.Only \"concat\" and \"add\" are allowed.".format(up_mode))

        # NOTE: up_mode 'upsample' is incompatible with merge_mode 'add'
        if self.up_mode == 'upsample' and self.merge_mode == 'add':
            raise ValueError("up_mode \"upsample\" is incompatible with merge_mode \"add\" at the moment "
                             "because it doesn't make sense to use nearest neighbour to reduce depth channels (by half).")

        self.num_classes = num_classes
        self.in_channels = in_channels
        self.start_filts = start_filts
        self.depth = depth

        self.down_convs = []
        self.up_convs = []

        # create the encoder pathway and add to a list
        for i in range(depth):
            ins = self.in_channels if i == 0 else outs
            outs = self.start_filts*(2**i)
            pooling = True if i < depth-1 else False

            down_conv = DownConv(ins, outs, pooling=pooling)
            self.down_convs.append(down_conv)

        # create the decoder pathway and add to a list
        # - careful! decoding only requires depth-1 blocks
        for i in range(depth-1):
            ins = outs
            outs = ins // 2
            up_conv = UpConv(ins, outs, up_mode=up_mode, merge_mode=merge_mode)
            self.up_convs.append(up_conv)


        self.conv_final = conv1x1(outs, self.num_classes)

        # add the list of modules to current module
        self.down_convs = nn.ModuleList(self.down_convs)
        self.up_convs = nn.ModuleList(self.up_convs)

        self.reset_params()

    @staticmethod
    def weight_init(m):
        if isinstance(m, nn.Conv2d):

            #https://prateekvjoshi.com/2016/03/29/understanding-xavier-initialization-in-deep-neural-networks/ 
            ##Doc: https://pytorch.org/docs/stable/nn.init.html?highlight=xavier#torch.nn.init.xavier_normal_ 
            init.xavier_normal_(m.weight)
            init.constant_(m.bias, 0)



    def reset_params(self):
        for i, m in enumerate(self.modules()):
            self.weight_init(m)


    def forward(self, x):
        encoder_outs = []

        # encoder pathway, save outputs for merging
        for i, module in enumerate(self.down_convs):
            x, before_pool = module(x)
            encoder_outs.append(before_pool)

        for i, module in enumerate(self.up_convs):
            before_pool = encoder_outs[-(i+2)]
            x = module(before_pool, x)

        # No softmax is used. This means we need to use
        # nn.CrossEntropyLoss is your training script,
        # as this module includes a softmax already.
        x = self.conv_final(x)
        return x

参数是：

device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
x,y = train_sequence[0] ; batch_size = x.shape[0]
model = UNet(num_classes = 2, depth=5, in_channels=5, merge_mode='concat').to(device)
optim = torch.optim.Adam(model.parameters(),lr=0.01, weight_decay=1e-3)
criterion = nn.BCEWithLogitsLoss() #has sigmoid internally
epochs = 1000

训练的功能是：

import torch.nn.functional as f


def train_model(epoch,train_sequence):
    """Train the model and report validation error with training error
    Args:
        model: the model to be trained
        criterion: loss function
        data_train (DataLoader): training dataset
    """
    model.train()
    for idx in range(len(train_sequence)):        
        X, y = train_sequence[idx]             
        images = Variable(torch.from_numpy(X)).to(device) # [batch, channel, H, W]
        masks = Variable(torch.from_numpy(y)).to(device) 

        outputs = model(images)
        print(masks.shape, outputs.shape)
        loss = criterion(outputs, masks)
        optim.zero_grad()
        loss.backward()
        # Update weights
        optim.step()
    # total_loss = get_loss_train(model, data_train, criterion)

我计算损失和准确率的函数如下：

def get_loss_train(model, train_sequence):
    """
        Calculate loss over train set
    """
    model.eval()
    total_acc = 0
    total_loss = 0
    for idx in range(len(train_sequence)):        
        with torch.no_grad():
            X, y = train_sequence[idx]             
            images = Variable(torch.from_numpy(X)).to(device) # [batch, channel, H, W]
            masks = Variable(torch.from_numpy(y)).to(device) 

            outputs = model(images)
            loss = criterion(outputs, masks)
            preds = torch.argmax(outputs, dim=1).float()
            acc = accuracy_check_for_batch(masks.cpu(), preds.cpu(), images.size()[0])
            total_acc = total_acc + acc
            total_loss = total_loss + loss.cpu().item()
    return total_acc/(len(train_sequence)), total_loss/(len(train_sequence))

编辑：运行（调用）函数的代码：

for epoch in range(epochs):
    train_model(epoch, train_sequence)
    train_acc, train_loss = get_loss_train(model,train_sequence)
    print("Train Acc:", train_acc)
    print("Train loss:", train_loss)

有人可以帮我确定为什么准确度总是精确到 0.5 吗？

标签： deep-learningcomputer-visionpytorchconv-neural-networkimage-segmentation