torch.nn.Embedding(num

就远: 谢谢博主

喵喵908: 博主，请问我按照你上面改之后出现这种情况是为啥呀，有解决办法吗

喵喵908: timeError: Error(s) in loading state_dict for VGG: Missing key(s) in state_dict: "features.0.weight", "features.0.bias", "features.2.weight", "features.2.bias", "features.5.weight", "features.5.bias", "features.7.weight", "features.7.bias", "features.10.weight", "features.10.bias", "features.12.weight", "features.12.bias", "features.14.weight", "features.14.bias", "features.17.weight", "features.17.bias", "features.19.weight", "features.19.bias", "features.21.weight", "features.21.bias", "features.24.weight", "features.24.bias", "features.26.weight", "features.26.bias", "features.28.weight", "features.28.bias", "classifier.1.weight", "classifier.1.bias", "classifier.4.weight", "classifier.4.bias", "classifier.6.weight", "classifier.6.bias". Unexpected key(s) in state_dict: "c1.weight", "c1.bias", "c2.weight", "c2.bias", "c3.weight", "c3.bias", "c5_1.weight", "c5_1.bias", "c5_2_1.weight", "c5_2_1.bias", "c5_2_2.weight", "c5_2_2.bias", "c5_3_1.weight", "c5_3_1.bias", "c5_3_2.weight

德彪稳坐倒骑驴: 1）卷积层 卷积层的参数就是卷积核的总数加上偏置数，例如一个14* 14* 6 (6为通道数)的特征图，经过5* 5* 16的卷积核，那么这层的参数为5* 5* 16* 6+16=2416个参数(注意要乘上一层的通道数)。 （2）池化层 池化层很有意思的特点就是，它有一组超参数，但并没有参数需要学习。实际上，梯度下降没有什么可学的，一旦确定了kernel的stride，它就是一个固定运算，梯度下降无需改变任何值。 （3）全连接层 全连接也有偏置的，例如一个5* 5* 16 (16是通

颂.: 太妙了