huggingface/transfer-learning-conv-ai

RuntimeError: shape '[-1, 2, 34]' is invalid for input of size 61710

Open

#12 创建于 2019年6月4日

在 GitHub 查看
 (3 评论) (0 反应) (0 负责人)Python (1,700 star) (429 fork)batch import
good first issue

描述

I'm playing around with this wonderful code but I'm running into a curious issue when I try to train the model with my own data.

I replicated the personachat_self_original.json file structure and added my own data. I deleted dataset_cache_OpenAIGPTTokenizer file but when I try to train, I get this error:

INFO:train.py:Pad inputs and convert to Tensor
Traceback (most recent call last):
  File "train.py", line 252, in <module>
    train()
  File "train.py", line 164, in train
    train_loader, val_loader, train_sampler, valid_sampler = get_data_loaders(args, tokenizer)
  File "train.py", line 97, in get_data_loaders
    tensor = tensor.view((-1, datasets[dataset_name]["n_candidates"]) + tensor.shape[1:])
RuntimeError: shape '[-1, 2, 34]' is invalid for input of size 61710

I have triple checked that my dataset follows the same structure but I can't figure out why the training script doesn't like it.

Any ideas why this is happening?

贡献者指南

技术栈
pythonpytorch
领域
machine learningai
议题类型
bug
难度面向新贡献者的预计实现难度，1 表示很小改动，5 表示专家级工作。
3
预计时间有经验贡献者完成调查、实现、测试并准备 pull request 的粗略时间范围。
half day
活动状态议题当前的可参与程度：新鲜、活跃、陈旧、阻塞或等待维护者输入。
stale
清晰度议题是否清楚说明期望改动、验收标准和下一步。
needs investigation
前置要求
PyTorch basicsData formattingTensor shapes
新手友好度1-100 的估计分数，表示该议题对首次贡献者的友好程度。
25
研究方向
The error occurs in train.py at line 97 during data loading. The tensor shape [ 1, 2, 34] indicates a mismatch between the expected number of candidates (2) and the actual data size. The user should verify that their dataset file has the correct number of candidates per example. Checking the dataset cache generation and the n candidates argument may reveal the issue. The code in get data loaders expects data to be shaped for a fixed number of candidates.