SoftMaskedBert

SoftMaskedBert copied to clipboard

最后使用的优化器中只添加了softMaskedBert的参数，也就是说没有对detector_model的参数进行更新？

yinhong-hu

想问一下如何进行预测？

13

如题，成功跑起来了代码，想问一下怎么进行模型预测，直接打印对应的预测概率吗

travel-go

git-lfs 问题

1

作者你好 ``` Traceback (most recent call last): File "C:\Anaconda3\lib\site-packages\transformers\modeling_utils.py", line 1445, in from_pretrained "You seem to have cloned a repository without having git-lfs installed. Please install " OSError: You seem...

myaijarvis

Greeksilverfir

测试模型是不是错了

1

corrector_correct = corrector_correct + sum( [(output * batch_mask).reshape(-1)[j].equal((batch_out_ids * batch_mask).reshape(-1)[j]) for j in range(len(output.reshape(-1)))]) 纠错和检测模型两个统计方式这里为什么还要reshape(-1)，这岂不是一个个token进行比对？本人放入数据进行训练，把最后的输出数据打印进行比对，发现输出跟正确内容差别很大，不知道题主有没有详细看过

lewispony

想问一下这个报错怎么解决

3

404 Client Error: Not Found for url: https://huggingface.co//model/chinese-bert-wwm-ext/resolve/main/config.json Traceback (most recent call last): File "H:\Anaconda\envs\softmasked\lib\site-packages\transformers\configuration_utils.py", line 512, in get_config_dict resolved_config_file = cached_path( File "H:\Anaconda\envs\softmasked\lib\site-packages\transformers\file_utils.py", line 1370, in cached_path output_path =...

Oldsport-996

`corrector_correct = corrector_correct + sum( [(output*batch_mask).reshape(-1)[j].equal((batch_out_ids*batch_mask).reshape(-1)[j]) for j in range(len(output.reshape(-1)))])` 这里会把pad的0相同都计入正确，明显不合理。 何不改成： `detector_correct += (prob.squeeze().equal(batch_labels) * batch_mask).sum()`

XDxc-cuber