使用自己的数据训练关键信息抽取中的SER模型

[kkiskkk]

[2024/06/04 16:22:29] ppocr INFO: train dataloader has 41 iters
[2024/06/04 16:22:29] ppocr INFO: valid dataloader has 11 iters
[2024/06/04 16:22:29] ppocr INFO: During the training process, after the 0th iteration, an evaluation is run every 19 iterations
[2024/06/04 16:43:14] ppocr INFO: epoch: [1/200], global_step: 10, lr: 0.000003, loss: 2.032407, avg_reader_cost: 0.06060 s, avg_batch_cost: 124.52930 s, avg_samples: 8.0, ips: 0.06424 samples/s, eta: 11 days, 19:18:14
eval model:: 9%|████████████████▉ | 1/11 [00:23<03:52, 23.30s/it]Traceback (most recent call last):
File "tools/train.py", line 227, in
main(config, device, logger, vdl_writer)
File "tools/train.py", line 198, in main
program.train(config, train_dataloader, valid_dataloader, device, model,
File "E:\work\trace\ocr\PaddleOCR\PaddleOCR-release-2.7\tools\program.py", line 392, in train
cur_metric = eval(
File "E:\work\trace\ocr\PaddleOCR\PaddleOCR-release-2.7\tools\program.py", line 540, in eval
preds = model(batch)
File "e:\users\WangK16.conda\envs\paddle_env\lib\site-packages\paddle\nn\layer\layers.py", line 1254, in call
return self.forward(*inputs, **kwargs)
File "E:\work\trace\ocr\PaddleOCR\PaddleOCR-release-2.7\ppocr\modeling\architectures\base_model.py", line 86, in forward
x = self.backbone(x)
File "e:\users\WangK16.conda\envs\paddle_env\lib\site-packages\paddle\nn\layer\layers.py", line 1254, in call
return self.forward(*inputs, **kwargs)
File "E:\work\trace\ocr\PaddleOCR\PaddleOCR-release-2.7\ppocr\modeling\backbones\vqa_layoutlm.py", line 166, in forward
x = self.model(
File "e:\users\WangK16.conda\envs\paddle_env\lib\site-packages\paddle\nn\layer\layers.py", line 1254, in call
return self.forward(*inputs, **kwargs)
File "e:\users\WangK16.conda\envs\paddle_env\lib\site-packages\paddlenlp\transformers\layoutxlm\modeling.py", line 951, in forward
outputs = self.layoutxlm(
File "e:\users\WangK16.conda\envs\paddle_env\lib\site-packages\paddle\nn\layer\layers.py", line 1254, in call
return self.forward(*inputs, **kwargs)
File "e:\users\WangK16.conda\envs\paddle_env\lib\site-packages\paddlenlp\transformers\layoutxlm\modeling.py", line 872, in forward
text_layout_emb = self._calc_text_embeddings(
File "e:\users\WangK16.conda\envs\paddle_env\lib\site-packages\paddlenlp\transformers\layoutxlm\modeling.py", line 740, in _calc_text_embeddings
spatial_position_embeddings = self.embeddings._cal_spatial_position_embeddings(bbox)
File "e:\users\WangK16.conda\envs\paddle_env\lib\site-packages\paddlenlp\transformers\layoutxlm\modeling.py", line 137, in _cal_spatial_position_embeddings
lower_position_embeddings = self.y_position_embeddings(bbox[:, :, 3])
File "e:\users\WangK16.conda\envs\paddle_env\lib\site-packages\paddle\nn\layer\layers.py", line 1254, in call
return self.forward(*inputs, **kwargs)
File "e:\users\WangK16.conda\envs\paddle_env\lib\site-packages\paddle\nn\layer\common.py", line 1515, in forward
return F.embedding(
File "e:\users\WangK16.conda\envs\paddle_env\lib\site-packages\paddle\nn\functional\input.py", line 205, in embedding
return _C_ops.embedding(x, weight, padding_idx, sparse)
ValueError: (InvalidArgument) Variable value (input) of OP(fluid.layers.embedding) expected >= 0 and < 1024, but got 1058. Please check input value.
[Hint: Expected ids[i] < row_number, but received ids[i]:1058 >= row_number:1024.] (at ..\paddle\phi\kernels\cpu\embedding_kernel.cc:67)

eval model:: 9%|████████████████▉

请问这个是什么原因？是我的标签有问题吗？

[matcovic]

Did you find any solution