I am implementing my own notebook using the techniques shared in the lesson 4 video, however, I am getting an error from
data_lm = TextLMDataBunch.load(path, 'tmp_lm')
This is the error stack I got.
NotADirectoryError Traceback (most recent call last) <ipython-input-24-8f395f051e19> in <module>() ----> 1 data_lm = TextLMDataBunch.load(path, 'tmp_lm') /usr/local/lib/python3.6/dist-packages/fastai/text/data.py in load(cls, path, cache_name, processor, **kwargs) 168 Use `load_data` for data saved with v1.0.44 or later.""", DeprecationWarning) 169 cache_path = Path(path)/cache_name --> 170 vocab = Vocab(pickle.load(open(cache_path/'itos.pkl','rb'))) 171 train_ids,train_lbls = np.load(cache_path/f'train_ids.npy'), np.load(cache_path/f'train_lbl.npy') 172 valid_ids,valid_lbls = np.load(cache_path/f'valid_ids.npy'), np.load(cache_path/f'valid_lbl.npy') NotADirectoryError: [Errno 20] Not a directory: '/content/gdrive/My Drive/fastai-v3/tweet-sentiment-extraction/tmp_lm/itos.pkl'
I have tried using the following method as suggested in an earlier post TextLMDataBunch.load raise NotADirectoryError
from fastai import * bs = 32 data_lm = load_data(path, 'tmp_lm', bs=bs)
However, this is not working. I don’t understand where else to look at.