justinge
commented
3 days ago 修改这里后，后面的transformer模型的前馈计算的方法传参数量也不对
Open justinge opened 3 days ago
justinge
commented
3 days ago 修改这里后，后面的transformer模型的前馈计算的方法传参数量也不对
Traceback (most recent call last): File "/home/justin/Desktop/code/python_project/pytorch-Tutorial-2nd/chapter-9/c_transformer/inference_transformer.py", line 115, in
main()
File "/home/justin/Desktop/code/python_project/pytorch-Tutorial-2nd/chapter-9/c_transformer/inference_transformer.py", line 62, in main
transformer.load_state_dict(checkpoint['model'])
File "/home/justin/miniconda3/envs/pytorchbook/lib/python3.9/site-packages/torch/nn/modules/module.py", line 1497, in load_state_dict
raise RuntimeError('Error(s) in loading state_dict for {}:\n\t{}'.format(
RuntimeError: Error(s) in loading state_dict for Transformer:
size mismatch for encoder.src_word_emb.weight: copying a param with shape torch.Size([2556, 512]) from checkpoint, the shape in current model is torch.Size([3000, 512]).