测试集精度反复横跳，这样算过拟合吗？

题主做的是二分类问题，改写别人的老代码

导入数据集忘记标准化会导致上图这种结果吗？
网络结构代码如下

```python
class VGG16x(Model):
    def __init__(self):
        super(VGG16, self).__init__()
        self.p1 = MaxPool2D(pool_size=(7, 1), padding='valid')

        self.c1 = Conv2D(filters=96, kernel_size=(3, 3), padding='same')
        self.b1 = BatchNormalization()
        self.a1 = Activation('relu')

        self.c2 = Conv2D(filters=64, kernel_size=(3, 3), padding='same')
        self.b2 = BatchNormalization()
        self.a2 = Activation('relu')

        self.p2 = MaxPool2D(pool_size=(2, 8), padding='same')
        self.d1 = Dropout(0.2)

        self.c3 = Conv2D(filters=48, kernel_size=(3, 3), padding='same')
        self.b3 = BatchNormalization()
        self.a3 = Activation('relu')

        self.c4 = Conv2D(filters=32, kernel_size=(3, 3), padding='same')
        self.b4 = BatchNormalization()
        self.a4 = Activation('relu')

        self.p3 = MaxPool2D(pool_size=(3, 4), padding='same')
        self.d2 = Dropout(0.2)

        self.flatten = Flatten()
        self.f1 = Dense(14, activation='relu')
        self.f2 = Dense(1, activation='sigmoid')

    def call(self, x):
        x = self.p1(x)

        x = self.c1(x)
        x = self.b1(x)
        x = self.a1(x)

        x = self.c2(x)
        x = self.b2(x)
        x = self.a2(x)

        x = self.p2(x)
        # x = self.d1(x)

        x = self.c3(x)
        x = self.b3(x)
        x = self.a3(x)

        x = self.c4(x)
        x = self.b4(x)
        x = self.a4(x)

        x = self.p3(x)
        x = self.d2(x)

        x = self.flatten(x)
        x = self.f1(x)
        y = self.f2(x)

        return y
model = VGGx16()

model.compile(optimizer='adam', loss='binary_crossentropy', metrics=['acc'])

这个也有可能是数据量太小而导致计算异常