我修改了alphabet为我自己的字典,训练模型也没有出现问题,但是测试时(demo.py)提示
size mismatch for rnn.1.embedding.weight: copying a param with shape torch.Size([6736, 512]) from checkpoint, the shape in current model is torch.Size([12, 512]).
size mismatch for rnn.1.embedding.bias: copying a param with shape torch.Size([6736]) from checkpoint, the shape in current model is torch.Size([12]).
我查看了神经网络,我没有看到embedding在哪里^,为自己的识别模型只有数字,字母表长度为12,如何修改才能运行,望诸位告知。
我修改了alphabet为我自己的字典,训练模型也没有出现问题,但是测试时(demo.py)提示 size mismatch for rnn.1.embedding.weight: copying a param with shape torch.Size([6736, 512]) from checkpoint, the shape in current model is torch.Size([12, 512]). size mismatch for rnn.1.embedding.bias: copying a param with shape torch.Size([6736]) from checkpoint, the shape in current model is torch.Size([12]). 我查看了神经网络,我没有看到embedding在哪里^,为自己的识别模型只有数字,字母表长度为12,如何修改才能运行,望诸位告知。