我得到了错误("AssertionError:发现没有需要填充的字段;我们很惊讶你得到了这个错误，请在github上打开一个问题;).
"AssertionError:没有需要填充的字段;我们很惊讶你得到这个错误，请打开github">
我不知道为什么会出现这个错误。
我的配置文件如下。
"""
{
"dataset_reader": {
"type": "tbmse_drop",
"answer_field_generators": {
"arithmetic_answer": {
"type": "arithmetic_answer_generator",
"special_numbers": [
100,
1
]
},
"count_answer": {
"type": "count_answer_generator"
},
"passage_span_answer": {
"type": "span_answer_generator",
"text_type": "passage"
},
"question_span_answer": {
"type": "span_answer_generator",
"text_type": "question"
},
"tagged_answer": {
"type": "tagged_answer_generator",
"ignore_question": false,
"labels": {
"I": 1,
"O": 0
}
}
},
"answer_generator_names_per_type": {
"date": [
"arithmetic_answer",
"passage_span_answer",
"question_span_answer",
"tagged_answer"
],
"multiple_span": [
"tagged_answer"
],
"number": [
"arithmetic_answer",
"count_answer",
"passage_span_answer",
"question_span_answer",
"tagged_answer"
],
"single_span": [
"tagged_answer",
"passage_span_answer",
"question_span_answer"
]
},
"is_training": true,
"old_reader_behavior": true,
"pickle": {
"action": "load",
"file_name": "all_heads_IO_roberta-large",
"path": "../pickle/drop"
},
"tokenizer": {
"type": "huggingface_transformers",
"pretrained_model": "roberta-large"
}
},
"model": {
"type": "multi_head",
"dataset_name": "drop",
"head_predictor": {
"activations": [
"relu",
"linear"
],
"dropout": [
0.1,
0
],
"hidden_dims": [
1024,
5
],
"input_dim": 2048,
"num_layers": 2
},
"heads": {
"arithmetic": {
"type": "arithmetic_head",
"output_layer": {
"activations": [
"relu",
"linear"
],
"dropout": [
0.1,
0
],
"hidden_dims": [
1024,
3
],
"input_dim": 2048,
"num_layers": 2
},
"special_embedding_dim": 1024,
"special_numbers": [
100,
1
],
"training_style": "soft_em"
},
"count": {
"type": "count_head",
"max_count": 10,
"output_layer": {
"activations": [
"relu",
"linear"
],
"dropout": [
0.1,
0
],
"hidden_dims": [
1024,
11
],
"input_dim": 1024,
"num_layers": 2
}
},
"multi_span": {
"type": "multi_span_head",
"decoding_style": "at_least_one",
"ignore_question": false,
"labels": {
"I": 1,
"O": 0
},
"output_layer": {
"activations": [
"relu",
"linear"
],
"dropout": [
0.1,
0
],
"hidden_dims": [
1024,
2
],
"input_dim": 1024,
"num_layers": 2
},
"prediction_method": "viterbi",
"training_style": "soft_em"
},
"passage_span": {
"type": "passage_span_head",
"end_output_layer": {
"activations": "linear",
"hidden_dims": 1,
"input_dim": 1024,
"num_layers": 1
},
"start_output_layer": {
"activations": "linear",
"hidden_dims": 1,
"input_dim": 1024,
"num_layers": 1
},
"training_style": "soft_em"
},
"question_span": {
"type": "question_span_head",
"end_output_layer": {
"activations": [
"relu",
"linear"
],
"dropout": [
0.1,
0
],
"hidden_dims": [
1024,
1
],
"input_dim": 2048,
"num_layers": 2
},
"training_style": "soft_em"
}
},
"passage_summary_vector_module": {
"activations": "linear",
"hidden_dims": 1,
"input_dim": 1024,
"num_layers": 1
},
"pretrained_model": "roberta-large",
"question_summary_vector_module": {
"activations": "linear",
"hidden_dims": 1,
"input_dim": 1024,
"num_layers": 1
}
},
"train_data_path": "drop_data/drop_dataset_train.json",
"validation_data_path": "drop_data/drop_dataset_dev.json",
"trainer": {
"num_epochs": 15,
"optimizer": {
"type": "adam",
"lr": 5e-06
},
"patience": 10,
"validation_metric": "+f1"
},
"data_loader": {
"batch_sampler": {
"type": "bucket",
"batch_size": 1
}
},
"distributed": {
"cuda_devices": [
0,
1
]
},
"validation_dataset_reader": {
"type": "tbmse_drop",
"answer_field_generators": {
"arithmetic_answer": {
"type": "arithmetic_answer_generator",
"special_numbers": [
100,
1
]
},
"count_answer": {
"type": "count_answer_generator"
},
"passage_span_answer": {
"type": "span_answer_generator",
"text_type": "passage"
},
"question_span_answer": {
"type": "span_answer_generator",
"text_type": "question"
},
"tagged_answer": {
"type": "tagged_answer_generator",
"ignore_question": false,
"labels": {
"I": 1,
"O": 0
}
}
},
"answer_generator_names_per_type": {
"date": [
"arithmetic_answer",
"passage_span_answer",
"question_span_answer",
"tagged_answer"
],
"multiple_span": [
"tagged_answer"
],
"number": [
"arithmetic_answer",
"count_answer",
"passage_span_answer",
"question_span_answer",
"tagged_answer"
],
"single_span": [
"tagged_answer",
"passage_span_answer",
"question_span_answer"
]
},
"is_training": false,
"old_reader_behavior": true,
"pickle": {
"action": "load",
"file_name": "all_heads_IO_roberta-large",
"path": "../pickle/drop"
},
"tokenizer": {
"type": "huggingface_transformers",
"pretrained_model": "roberta-large"
}
}
}
"""
我用allennlp 2.0.1 &2.0.2(两个版本都出现了相同的错误)
是否有可能您的数据集阅读器根本不产生任何实例?或者，它产生的实例中可能没有字段(即完全为空)?在这两种情况下，都会发生此错误。
如果这些事情都没有发生，尝试将batch_sampler的sorting_keys设置为实例中最长的字段。