python - 我无法使用 fastai.text 中的 pretrained_model=URLs.WT103

Question

我正在尝试创建一个模型来预测单词作为输入和输出作为段落。当我尝试实现 fastai|text 上给出的相同示例时，出现错误到我自己的数据集。它在下面的步骤中给出了错误。当您查看该网站时，直到您收到下面的代码为止，这并不重要。但这段代码给出了一个错误。导致此错误的原因可能是什么？

代码:

from fastai import *
from fastai.text import * 

path = untar_data(URLs.IMDB_SAMPLE)

df = pd.read_csv(path/'texts.csv')

# Language model data
data_lm = TextLMDataBunch.from_csv(path, 'texts.csv')
# Classifier model data
data_clas = TextClasDataBunch.from_csv(path, 'texts.csv', 
vocab=data_lm.train_ds.vocab, bs=32)

data_lm.save()
data_clas.save()

data_lm = TextLMDataBunch.load(path)
data_clas = TextClasDataBunch.load(path, bs=32)

learn = language_model_learner(data_lm, pretrained_model=URLs.WT103, drop_mult=0.5)
learn.fit_one_cycle(1, 1e-2)

错误代码:

learn = language_model_learner(data_lm, pretrained_model=URLs.WT103, drop_mult=0.5)

输出:

    102     if not ps: return None
    103     if b is None: return ps[0].requires_grad
--> 104     for p in ps: p.requires_grad=b
    105 
    106 def trainable_params(m:nn.Module)->ParamList:

RuntimeError: you can only change requires_grad flags of leaf variables. If you want to use a computed variable in a subgraph that doesn't require differentiation use var_no_grad = var.detach().

Answer 1

使用以下命令将 grad 设置为 false:torch.set_grad_enabled(False)(在创建学习者对象之前使用它)

并用 torch.enable_grad() 包装函数 (learn.fit Cycle()) 的调用: