为什么我对模型backbone进行了修改，训练时候一直为0的准确率呢，就比如说我采用了mobileNetV4这个模型，

[yulongPan]

请问为什么我采用这这个模型，我将模型最后一层的输出改为嵌入向量维度不就可以吗，为什么准确率一直是0呢，请问问题出在哪里呢，我看着B导mobileNetV1的模型也是这么做的啊，为啥这么做就不可以呢

class MobileNetV4(nn.Module): def init(self, model,embedding_size=128,dropout_keep_prob=0.5, pretrained=False): # MobileNetV4ConvSmall MobileNetV4ConvMedium MobileNetV4ConvLarge # MobileNetV4HybridMedium MobileNetV4HybridLarge """Params to initiate MobilenNetV4 Args: model : support 5 types of models as indicated in "https://github.com/tensorflow/models/blob/master/official/vision/modeling/backbones/mobilenet.py" """ super().init() assert model in MODEL_SPECS.keys() self.model = model self.spec = MODEL_SPECS[self.model]

    # conv0
    self.conv0 = build_blocks(self.spec['conv0'])
    # layer1
    self.layer1 = build_blocks(self.spec['layer1'])
    # layer2
    self.layer2 = build_blocks(self.spec['layer2'])
    # layer3
    self.layer3 = build_blocks(self.spec['layer3'])
    # layer4
    self.layer4 = build_blocks(self.spec['layer4'])
    # layer5
    self.layer5 = build_blocks(self.spec['layer5'])
    self.layer6 = nn.Conv2d(1280,512,kernel_size=1)
    #embeding
    self.layer7 = nn.Linear(512*49, embedding_size)
    # self.layer6 = nn.Conv2d(1280,embedding_size,1)
    self.features = nn.BatchNorm1d(embedding_size, eps=1e-05)
    self.dropout = nn.Dropout(p=dropout_keep_prob, inplace=True)
def forward(self, x):
    x0 = self.conv0(x)

    x1 = self.layer1(x0)
    x2 = self.layer2(x1)
    x3 = self.layer3(x2)
    x4 = self.layer4(x3)
    x5 = self.layer5(x4)
    x6 = self.layer6(x5)

    x7 = torch.flatten(x6, 1)
    # 或者 x5 = x5.view(x5.size(0), -1)
    x8 = self.layer7(x7)
  #  x6 = self.features(x6)
    print(x8.shape)
    return x8

[x710777335]

你好，请问你解决这个问题了吗？我也遇到这个问题了，backbone换成efficient训练的时候acc一直为0，loss也不下降。测试过梯度是正常的，数据也没问题

[yulongPan]

不好意思，我有些忘记了，好像是因为使用的损失里它有一行代码是出现了问题，比如说arc或者cos的损失，好像是归零行出现了问题。具体我也忘记了

发自我的iPhone

------------------ 原始邮件 ------------------ 发件人: x710777335 @.> 发送时间: 2025年4月30日 16:44 收件人: bubbliiiing/arcface-pytorch @.> 抄送: yulongPan @.>, Author @.> 主题: Re: [bubbliiiing/arcface-pytorch] 为什么我对模型backbone进行了修改，训练时候一直为0的准确率呢，就比如说我采用了mobileNetV4这个模型， (Issue #38)

x710777335 left a comment (bubbliiiing/arcface-pytorch#38)

你好，请问你解决这个问题了吗？我也遇到这个问题了，backbone换成efficient训练的时候acc一直为0，loss也不下降。测试过梯度是正常的，数据也没问题

— Reply to this email directly, view it on GitHub, or unsubscribe. You are receiving this because you authored the thread.Message ID: @.***>