Ryan Zzz

> A simple `nn.Embeddng(vocab_size, embedding_size)` will work. Or you can refer to our example on [language modeling](https://github.com/microsoft/torchscale/blob/main/examples/fairseq/models/language_modeling.py#L215). from fairseq.models.transformer import DEFAULT_MIN_PARAMS_TO_WRAP, Embedding I can't find the transformer.

When I run pytorch2onnx.py, it occurs an error. How can I get the onnx model? AttributeError: 'Anchor3DLane' object has no attribute 'decode_head'