kevinGit777
commented
3 years ago just realized that I clone an older version, the problem was solved by downgrading PyTorch...
Closed kevinGit777 closed 3 years ago
kevinGit777
commented
3 years ago just realized that I clone an older version, the problem was solved by downgrading PyTorch...
hi, I get this error when running:
Traceback (most recent call last): File "/home/hxw170013/APR/chai/src/lib/OpenNMT-py/translate.py", line 35, in
main(opt)
File "/home/hxw170013/APR/chai/src/lib/OpenNMT-py/translate.py", line 15, in main
translator.translate(
File "/home/hxw170013/APR/chai/src/lib/OpenNMT-py/onmt/translate/translator.py", line 209, in translate
batch_data = self.translate_batch(
File "/home/hxw170013/APR/chai/src/lib/OpenNMT-py/onmt/translate/translator.py", line 354, in translate_batch
return self._translate_batch(batch, data)
File "/home/hxw170013/APR/chai/src/lib/OpenNMT-py/onmt/translate/translator.py", line 707, in _translate_batch
out, beam_attn = self._decode_and_generate(
File "/home/hxw170013/APR/chai/src/lib/OpenNMT-py/onmt/translate/translator.py", line 397, in _decode_and_generate
dec_out, dec_attn = self.model.decoder(
File "/home/hxw170013/miniconda3/lib/python3.8/site-packages/torch/nn/modules/module.py", line 722, in _call_impl
result = self.forward(*input, kwargs)
File "/home/hxw170013/APR/chai/src/lib/OpenNMT-py/onmt/decoders/decoder.py", line 160, in forward
dec_state, dec_outs, attns = self._run_forward_pass(
File "/home/hxw170013/APR/chai/src/lib/OpenNMT-py/onmt/decoders/decoder.py", line 323, in _run_forward_pass
emb = self.embeddings(tgt)
File "/home/hxw170013/miniconda3/lib/python3.8/site-packages/torch/nn/modules/module.py", line 722, in _call_impl
result = self.forward(*input, *kwargs)
File "/home/hxw170013/APR/chai/src/lib/OpenNMT-py/onmt/modules/embeddings.py", line 205, in forward
source = self.make_embedding(source)
File "/home/hxw170013/miniconda3/lib/python3.8/site-packages/torch/nn/modules/module.py", line 722, in _call_impl
result = self.forward(input, kwargs)
File "/home/hxw170013/miniconda3/lib/python3.8/site-packages/torch/nn/modules/container.py", line 117, in forward
input = module(input)
File "/home/hxw170013/miniconda3/lib/python3.8/site-packages/torch/nn/modules/module.py", line 722, in _call_impl
result = self.forward(*input, *kwargs)
File "/home/hxw170013/APR/chai/src/lib/OpenNMT-py/onmt/modules/utilclass.py", line 26, in forward
outputs = [f(x) for f, x in zip(self, inputs)]
File "/home/hxw170013/APR/chai/src/lib/OpenNMT-py/onmt/modules/utilclass.py", line 26, in
outputs = [f(x) for f, x in zip(self, inputs )]
File "/home/hxw170013/miniconda3/lib/python3.8/site-packages/torch/nn/modules/module.py", line 722, in _call_impl
result = self.forward(input, **kwargs)
File "/home/hxw170013/miniconda3/lib/python3.8/site-packages/torch/nn/modules/sparse.py", line 124, in forward
return F.embedding(
File "/home/hxw170013/miniconda3/lib/python3.8/site-packages/torch/nn/functional.py", line 1814, in embedding
return torch.embedding(weight, input, padding_idx, scale_grad_by_freq, sparse)
RuntimeError: Expected tensor for argument #1 'indices' to have scalar type Long; but got torch.FloatTensor instead (while checking arguments for embedding)
my pytorch version is: 1.6.0+cu101 and python version is 3.8 64 bit. Please help!