dblock = DataBlock(blocks=TextBlock.from_df('Sequence', is_lm=True, tok=SentencePieceTokenizer(sp_model=sp_model), vocab=vocab),
get_x=ColReader('text'),
splitter=RandomSplitter())
dls = dblock.dataloaders(seqs, bs=64, seq_len=72)
--------------------------------------------------------------------------
TypeError Traceback (most recent call last)
<ipython-input-10-ec664a1ca6de> in <module>
----> 1 dls = dblock.dataloaders(seqs, bs=64, seq_len=72)
/opt/conda/envs/fastai/lib/python3.8/site-packages/fastai/data/block.py in dataloaders(self, source, path, verbose, **kwargs)
113 dsets = self.datasets(source)
114 kwargs = {**self.dls_kwargs, **kwargs, 'verbose': verbose}
--> 115 return dsets.dataloaders(path=path, after_item=self.item_tfms, after_batch=self.batch_tfms, **kwargs)
116
117 _docs = dict(new="Create a new `DataBlock` with other `item_tfms` and `batch_tfms`",
/opt/conda/envs/fastai/lib/python3.8/site-packages/fastai/data/core.py in dataloaders(self, bs, val_bs, shuffle_train, n, path, dl_type, dl_kwargs, device, **kwargs)
211 if dl_type is None: dl_type = self._dl_type
212 drop_last = kwargs.pop('drop_last', shuffle_train)
--> 213 dl = dl_type(self.subset(0), bs=bs, shuffle=shuffle_train, drop_last=drop_last, n=n, device=device,
214 **merge(kwargs, dl_kwargs[0]))
215 dls = [dl] + [dl.new(self.subset(i), bs=(bs if val_bs is None else val_bs), shuffle=False, drop_last=False,
/opt/conda/envs/fastai/lib/python3.8/site-packages/fastai/text/data.py in __init__(self, dataset, lens, cache, bs, seq_len, num_workers, **kwargs)
75 self.seq_len = seq_len
76 if lens is None: lens = _get_lengths(dataset)
---> 77 if lens is None: lens = [len(o) for o in self.items]
78 self.lens = ReindexCollection(lens, idxs=self.items.idxs)
79 # The "-1" is to allow for final label, we throw away the end that's less than bs
/opt/conda/envs/fastai/lib/python3.8/site-packages/fastai/text/data.py in <listcomp>(.0)
75 self.seq_len = seq_len
76 if lens is None: lens = _get_lengths(dataset)
---> 77 if lens is None: lens = [len(o) for o in self.items]
78 self.lens = ReindexCollection(lens, idxs=self.items.idxs)
79 # The "-1" is to allow for final label, we throw away the end that's less than bs
/opt/conda/envs/fastai/lib/python3.8/site-packages/fastcore/xtras.py in <genexpr>(.0)
84 class IterLen:
85 "Base class to add iteration to anything supporting `__len__` and `__getitem__`"
---> 86 def __iter__(self): return (self[i] for i in range_of(self))
87
88 # Cell
/opt/conda/envs/fastai/lib/python3.8/site-packages/fastcore/xtras.py in __getitem__(self, i)
97
98 def _get(self, i): return self.tfm(self.coll[i])
---> 99 def __getitem__(self, i): return self._get(self.idxs[i])
100 def __len__(self): return len(self.coll)
101 def reindex(self, idxs): self.idxs = idxs
/opt/conda/envs/fastai/lib/python3.8/site-packages/fastcore/xtras.py in _get(self, i)
96 if cache is not None: self._get = functools.lru_cache(maxsize=cache)(self._get)
97
---> 98 def _get(self, i): return self.tfm(self.coll[i])
99 def __getitem__(self, i): return self._get(self.idxs[i])
100 def __len__(self): return len(self.coll)
/opt/conda/envs/fastai/lib/python3.8/site-packages/fastai/data/core.py in __getitem__(self, it)
312
313 def __getitem__(self, it):
--> 314 res = tuple([tl[it] for tl in self.tls])
315 return res if is_indexer(it) else list(zip(*res))
316
/opt/conda/envs/fastai/lib/python3.8/site-packages/fastai/data/core.py in <listcomp>(.0)
312
313 def __getitem__(self, it):
--> 314 res = tuple([tl[it] for tl in self.tls])
315 return res if is_indexer(it) else list(zip(*res))
316
/opt/conda/envs/fastai/lib/python3.8/site-packages/fastai/data/core.py in __getitem__(self, idx)
278 res = super().__getitem__(idx)
279 if self._after_item is None: return res
--> 280 return self._after_item(res) if is_indexer(idx) else res.map(self._after_item)
281
282 # Cell
/opt/conda/envs/fastai/lib/python3.8/site-packages/fastai/data/core.py in _after_item(self, o)
240 return super()._new(items, tfms=self.tfms, do_setup=False, types=self.types, split_idx=split_idx, **kwargs)
241 def subset(self, i): return self._new(self._get(self.splits[i]), split_idx=i)
--> 242 def _after_item(self, o): return self.tfms(o)
243 def __repr__(self): return f"{self.__class__.__name__}: {self.items}\ntfms - {self.tfms.fs}"
244 def __iter__(self): return (self[i] for i in range(len(self)))
/opt/conda/envs/fastai/lib/python3.8/site-packages/fastcore/transform.py in __call__(self, o)
196 self.fs.append(t)
197
--> 198 def __call__(self, o): return compose_tfms(o, tfms=self.fs, split_idx=self.split_idx)
199 def __repr__(self): return f"Pipeline: {' -> '.join([f.name for f in self.fs if f.name != 'noop'])}"
200 def __getitem__(self,i): return self.fs[i]
/opt/conda/envs/fastai/lib/python3.8/site-packages/fastcore/transform.py in compose_tfms(x, tfms, is_enc, reverse, **kwargs)
148 for f in tfms:
149 if not is_enc: f = f.decode
--> 150 x = f(x, **kwargs)
151 return x
152
/opt/conda/envs/fastai/lib/python3.8/site-packages/fastcore/transform.py in __call__(self, x, **kwargs)
71 @property
72 def name(self): return getattr(self, '_name', _get_name(self))
---> 73 def __call__(self, x, **kwargs): return self._call('encodes', x, **kwargs)
74 def decode (self, x, **kwargs): return self._call('decodes', x, **kwargs)
75 def __repr__(self): return f'{self.name}:\nencodes: {self.encodes}decodes: {self.decodes}'
/opt/conda/envs/fastai/lib/python3.8/site-packages/fastcore/transform.py in _call(self, fn, x, split_idx, **kwargs)
81 def _call(self, fn, x, split_idx=None, **kwargs):
82 if split_idx!=self.split_idx and self.split_idx is not None: return x
---> 83 return self._do_call(getattr(self, fn), x, **kwargs)
84
85 def _do_call(self, f, x, **kwargs):
/opt/conda/envs/fastai/lib/python3.8/site-packages/fastcore/transform.py in _do_call(self, f, x, **kwargs)
87 if f is None: return x
88 ret = f.returns_none(x) if hasattr(f,'returns_none') else None
---> 89 return retain_type(f(x, **kwargs), x, ret)
90 res = tuple(self._do_call(f, x_, **kwargs) for x_ in x)
91 return retain_type(res, x)
/opt/conda/envs/fastai/lib/python3.8/site-packages/fastcore/dispatch.py in __call__(self, *args, **kwargs)
115 elif self.inst is not None: f = MethodType(f, self.inst)
116 elif self.owner is not None: f = MethodType(f, self.owner)
--> 117 return f(*args, **kwargs)
118
119 def __get__(self, inst, owner):
/opt/conda/envs/fastai/lib/python3.8/site-packages/fastai/text/data.py in encodes(self, o)
46 self.o2i = defaultdict(int, {v:k for k,v in enumerate(self.vocab) if v != 'xxfake'})
47
---> 48 def encodes(self, o): return TensorText(tensor([self.o2i [o_] for o_ in o]))
49 def decodes(self, o): return L(self.vocab[o_] for o_ in o)
50
TypeError: 'float' object is not iterable
1 Like
I’m having the same issue with fastai==2.1.5 in Colab, but using TextDataLoaders.from_df() in my code. I created an issue on GitHub.
UPDATE: This appears to be an issue with I was able to fix the issue in my notebook by pinning earlier versions.fastcore and NOT fastai.
!pip install fastai==2.1.4
!pip install fastcore==1.3.1
—-
UPDATE #2: turns out it was a fastai issue after all. A change to tokenize_df was the culprit. This has been fixed in 2.1.6.
Hi neuradai
Thanks for the reply. I have done
!pip install fastai==2.1.4
!pip install fastcore==1.3.1
from fastai import *
from fastcore import *
from fastai.text.all import *
and rerun my code. now I am getting an error saying
RuntimeError: stack expects each tensor to be equal size, but got [26] at entry 0 and [164] at entry 1
When I run .summary() on my datablock I get
collating items in a batch
Error! It's not possible to collate your items in a batch
Could not collate the 0-th members of your tuples because got the following shapes
torch.Size([26]),torch.Size([164]),torch.Size([59]),torch.Size([21])
Do you know why this might be?
Thanks
Looks like you probably need to apply the padding transform to your datablock. Take a look at the pad_input and pad_input_chunk functions in fastai.text.data
There’s an open issue re: learn.summary() that talks about some sort of incompatibility with an update to pytorch. See below.
I’m still getting the same error both with 2.1.4 and 2.1.6
I had the same error and I fixed with:
!pip install fastai==2.1.8