After pip install in Colab, import blurr.modeling.all and blurr.data.all are throwing errors. Did not encounter errors last week, not sure when they began. Has there been a syntax change for setup?

ValueError Traceback (most recent call last) /usr/local/lib/python3.6/dist-packages/pandas/core/indexes/range.py in get_loc(self, key, method, tolerance) 354 try: --> 355 return self._range.index(new_key) 356 except ValueError as err:

ValueError: 1 is not in range

The above exception was the direct cause of the following exception:

KeyError Traceback (most recent call last) 6 frames in () ----> 1 from blurr.modeling.all import *

/usr/local/lib/python3.6/dist-packages/blurr/modeling/all.py in () ----> 1 from ..utils import * 2 from .core import * 3 from .question_answering import * 4 from .token_classification import * 5 from .text2text.core import *

/usr/local/lib/python3.6/dist-packages/blurr/utils.py in () 182 183 # Cell --> 184 BLURR_MODEL_HELPER = ModelHelper() 185 186 # Cell

/usr/local/lib/python3.6/dist-packages/blurr/utils.py in call(self, *args, **kwargs) 25 26 def call(self, *args, **kwargs): ---> 27 if self._instance == None: self._instance = self._cls(*args, **kwargs) 28 return self._instance 29

/usr/local/lib/python3.6/dist-packages/blurr/utils.py in init(self) 59 model_type_df = self._df[(self._df.functional_area == 'modeling')].class_name.str.split('For', n=1, expand=True) 60 ---> 61 model_type_df[1] = np.where(model_type_df[1].notnull(), 62 'For' + model_type_df[1].astype(str), 63 model_type_df[1])

/usr/local/lib/python3.6/dist-packages/pandas/core/frame.py in getitem(self, key) 2904 if self.columns.nlevels > 1: 2905 return self._getitem_multilevel(key) -> 2906 indexer = self.columns.get_loc(key) 2907 if is_integer(indexer): 2908 indexer = [indexer]

/usr/local/lib/python3.6/dist-packages/pandas/core/indexes/range.py in get_loc(self, key, method, tolerance) 355 return self._range.index(new_key) 356 except ValueError as err: --> 357 raise KeyError(key) from err 358 raise KeyError(key) 359 return super().get_loc(key, method=method, tolerance=tolerance)

KeyError: 1

Hi @ohmeow , this is probably a basic question, but I'm having some issues to do causal language modelling from a set of wikitext-100 style files. My data folder is split as follows:

data/
       - train/
           - file1.txt
           - file2.txt
           - file3.txt
           - ..... 
       - valid/
           - file1.txt
           - file2.txt
           - file3.txt
           - .....

So far I have been following your gpt2 tutorial for LM:

pretrained_model_name = "gpt2"
hf_arch, hf_config, hf_tokenizer, hf_model = BLURR.get_hf_objects(pretrained_model_name, model_cls=AutoModelForCausalLM)
if (hf_tokenizer.pad_token is None): hf_tokenizer.pad_token = '[PAD]'
before_batch_tfm = HF_LMBeforeBatchTransform(hf_arch, hf_config, hf_tokenizer, hf_model, lm_strategy_cls=CausalLMStrategy)
blocks = [HF_TextBlock(before_batch_tfm=before_batch_tfm, input_return_type=HF_CausalLMInput), noop]
path = config["data_path"]
get_items = partial(get_text_files, folders=[train, valid])
dblock = DataBlock(blocks=blocks, get_items=get_items, get_y=None, splitter=config["splitter"])
dls = TextDataLoaders.from_dblock(dblock, path, path=path, seq_len=config["max_seq_len"])

Config is a dict containing various params and a splitter class that's able to get the validation / train sets from a the data folder passed in.

This is however, throwing the following exception:

~/code/tgalery/fastai/fastai/data/core.py in from_dblock(cls, dblock, source, path, bs, val_bs, shuffle, device, **kwargs)
    190     @classmethod
    191     def from_dblock(cls, dblock, source, path='.',  bs=64, val_bs=None, shuffle=True, device=None, **kwargs):
--> 192         return dblock.dataloaders(source, path=path, bs=bs, val_bs=val_bs, shuffle=shuffle, device=device, **kwargs)
    193 
    194     _docs=dict(__getitem__="Retrieve `DataLoader` at `i` (`0` is training, `1` is validation)",

~/code/tgalery/fastai/fastai/data/block.py in dataloaders(self, source, path, verbose, **kwargs)
    113         dsets = self.datasets(source, verbose=verbose)
    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`",

~/code/tgalery/fastai/fastai/data/core.py in dataloaders(self, bs, shuffle_train, shuffle, val_shuffle, n, path, dl_type, dl_kwargs, device, drop_last, val_bs, **kwargs)
    229         val_kwargs={k[4:]:v for k,v in kwargs.items() if k.startswith('val_')}
    230         def_kwargs = {'bs':bs,'shuffle':shuffle,'drop_last':drop_last,'n':n,'device':device}
--> 231         dl = dl_type(self.subset(0), **merge(kwargs,def_kwargs, dl_kwargs[0]))
    232         def_kwargs = {'bs':bs if val_bs is None else val_bs,'shuffle':val_shuffle,'n':None,'drop_last':False}
    233         dls = [dl] + [dl.new(self.subset(i), **merge(kwargs,def_kwargs,val_kwargs,dl_kwargs[i]))

~/code/tgalery/fastai/fastai/text/data.py in __init__(self, dataset, sort_func, res, **kwargs)
    187         self.sort_func = _default_sort if sort_func is None else sort_func
    188         if res is None and self.sort_func == _default_sort: res = _get_lengths(dataset)
--> 189         self.res = [self.sort_func(self.do_item(i)) for i in range_of(self.dataset)] if res is None else res
    190         if len(self.res) > 0: self.idx_max = np.argmax(self.res)
    191 

~/code/tgalery/fastai/fastai/text/data.py in <listcomp>(.0)
    187         self.sort_func = _default_sort if sort_func is None else sort_func
    188         if res is None and self.sort_func == _default_sort: res = _get_lengths(dataset)
--> 189         self.res = [self.sort_func(self.do_item(i)) for i in range_of(self.dataset)] if res is None else res
    190         if len(self.res) > 0: self.idx_max = np.argmax(self.res)
    191 

~/code/tgalery/fastai/fastai/text/data.py in _default_sort(x)
    178 
    179 # Cell
--> 180 def _default_sort(x): return len(x[0])
    181 
    182 @delegates(TfmdDL)

TypeError: object of type 'PosixPath' has no len()

Any pointers on what I might be doing wrong ?

Hi,

I'm currently facing some errors when trying to generate predictions on a batch using fastai functions such as dls.test_dl() to create the test dataloaders and then learn.get_preds() to get all the predictions. I searched through the documentation but couldn't find any examples of batch prediction. Could you show me an example of how to do it.?

Hi there, I'm having a side assert cuda device on self.loss_grad.backward()

https://gist.github.com/tyoc213/1527e3e26f0d037466077949becf0063

It seems that this type of errors are normally about a size mismatch between tensors? but couldn't pinpoint more than that on this issue.

Pegasus has the same parameter groups in Bart so the splitter works for both.

When Pegasus decodes it leaves these <n> symbols in, so I added a line the take them out.

Hi @ohmeow ,

Is it possible to use blurr to do achieve this? I'm trying to do transfer learning on a pretrained NER task model with 39 labels (instead of a LM model like in your example) to a smaller NER dataset with only 5 labels. Unfortunately, I'm getting stuck on how to do so.

I tried 2 different ways but all lead to errors:

1. Fill in config.num_labels

task = HF_TASKS_AUTO.TokenClassification
pretrained_model_name = 'cahya/bert-base-indonesian-NER' 
config = AutoConfig.from_pretrained(pretrained_model_name)
config.num_labels = len(labels) # 5

hf_arch, hf_config, hf_tokenizer, hf_model = BLURR_MODEL_HELPER.get_hf_objects(pretrained_model_name, 
                                                                               task=task, 
                                                                               config=config)

---------------------------------------------------------------------------
RuntimeError                              Traceback (most recent call last)
<ipython-input-24-b2c1babcdb91> in <module>
      4 config.num_labels = len(labels) # 5
      5 
----> 6 hf_arch, hf_config, hf_tokenizer, hf_model = BLURR_MODEL_HELPER.get_hf_objects(pretrained_model_name, 
      7                                                                                task=task,
      8                                                                                config=config)

/opt/conda/envs/fastai/lib/python3.8/site-packages/blurr/utils.py in get_hf_objects(self, pretrained_model_name_or_path, task, config, tokenizer_cls, model_cls, config_kwargs, tokenizer_kwargs, model_kwargs, cache_dir)
    175                 model_cls = self.get_models(arch="auto", task=task.name)[0]
    176 
--> 177             model = model_cls.from_pretrained(pretrained_model_name_or_path,
    178                                               config=config,
    179                                               cache_dir=cache_dir,

/opt/conda/envs/fastai/lib/python3.8/site-packages/transformers/models/auto/modeling_auto.py in from_pretrained(cls, pretrained_model_name_or_path, *model_args, **kwargs)
   1611 
   1612         if type(config) in MODEL_FOR_TOKEN_CLASSIFICATION_MAPPING.keys():
-> 1613             return MODEL_FOR_TOKEN_CLASSIFICATION_MAPPING[type(config)].from_pretrained(
   1614                 pretrained_model_name_or_path, *model_args, config=config, **kwargs
   1615             )

/opt/conda/envs/fastai/lib/python3.8/site-packages/transformers/modeling_utils.py in from_pretrained(cls, pretrained_model_name_or_path, *model_args, **kwargs)
   1155                 )
   1156             if len(error_msgs) > 0:
-> 1157                 raise RuntimeError(
   1158                     "Error(s) in loading state_dict for {}:\n\t{}".format(
   1159                         model.__class__.__name__, "\n\t".join(error_msgs)

RuntimeError: Error(s) in loading state_dict for BertForTokenClassification:
	size mismatch for classifier.weight: copying a param with shape torch.Size([39, 768]) from checkpoint, the shape in current model is torch.Size([5, 768]).
	size mismatch for classifier.bias: copying a param with shape torch.Size([39]) from checkpoint, the shape in current model is torch.Size([5]).

2. Add in an extra Linear(39, 5) layer at the end: model = HF_BaseModelWrapper(nn.Sequential(hf_model, nn.Linear(39, 5))) But when I call learn.fit(), it results in this:

---------------------------------------------------------------------------
TypeError                                 Traceback (most recent call last)
<ipython-input-16-8587f3539821> in <module>
----> 1 learn.fit(1)

/opt/conda/envs/fastai/lib/python3.8/site-packages/fastai/learner.py in fit(self, n_epoch, lr, wd, cbs, reset_opt)
    209             self.opt.set_hypers(lr=self.lr if lr is None else lr)
    210             self.n_epoch = n_epoch
--> 211             self._with_events(self._do_fit, 'fit', CancelFitException, self._end_cleanup)
    212 
    213     def _end_cleanup(self): self.dl,self.xb,self.yb,self.pred,self.loss = None,(None,),(None,),None,None

/opt/conda/envs/fastai/lib/python3.8/site-packages/fastai/learner.py in _with_events(self, f, event_type, ex, final)
    158 
    159     def _with_events(self, f, event_type, ex, final=noop):
--> 160         try: self(f'before_{event_type}');  f()
    161         except ex: self(f'after_cancel_{event_type}')
    162         self(f'after_{event_type}');  final()

/opt/conda/envs/fastai/lib/python3.8/site-packages/fastai/learner.py in _do_fit(self)
    200         for epoch in range(self.n_epoch):
    201             self.epoch=epoch
--> 202             self._with_events(self._do_epoch, 'epoch', CancelEpochException)
    203 
    204     def fit(self, n_epoch, lr=None, wd=None, cbs=None, reset_opt=False):

/opt/conda/envs/fastai/lib/python3.8/site-packages/fastai/learner.py in _with_events(self, f, event_type, ex, final)
    158 
    159     def _with_events(self, f, event_type, ex, final=noop):
--> 160         try: self(f'before_{event_type}');  f()
    161         except ex: self(f'after_cancel_{event_type}')
    162         self(f'after_{event_type}');  final()

/opt/conda/envs/fastai/lib/python3.8/site-packages/fastai/learner.py in _do_epoch(self)
    194 
    195     def _do_epoch(self):
--> 196         self._do_epoch_train()
    197         self._do_epoch_validate()
    198 

/opt/conda/envs/fastai/lib/python3.8/site-packages/fastai/learner.py in _do_epoch_train(self)
    186     def _do_epoch_train(self):
    187         self.dl = self.dls.train
--> 188         self._with_events(self.all_batches, 'train', CancelTrainException)
    189 
    190     def _do_epoch_validate(self, ds_idx=1, dl=None):

/opt/conda/envs/fastai/lib/python3.8/site-packages/fastai/learner.py in _with_events(self, f, event_type, ex, final)
    158 
    159     def _with_events(self, f, event_type, ex, final=noop):
--> 160         try: self(f'before_{event_type}');  f()
    161         except ex: self(f'after_cancel_{event_type}')
    162         self(f'after_{event_type}');  final()

/opt/conda/envs/fastai/lib/python3.8/site-packages/fastai/learner.py in all_batches(self)
    164     def all_batches(self):
    165         self.n_iter = len(self.dl)
--> 166         for o in enumerate(self.dl): self.one_batch(*o)
    167 
    168     def _do_one_batch(self):

/opt/conda/envs/fastai/lib/python3.8/site-packages/fastai/learner.py in one_batch(self, i, b)
    182         self.iter = i
    183         self._split(b)
--> 184         self._with_events(self._do_one_batch, 'batch', CancelBatchException)
    185 
    186     def _do_epoch_train(self):

/opt/conda/envs/fastai/lib/python3.8/site-packages/fastai/learner.py in _with_events(self, f, event_type, ex, final)
    158 
    159     def _with_events(self, f, event_type, ex, final=noop):
--> 160         try: self(f'before_{event_type}');  f()
    161         except ex: self(f'after_cancel_{event_type}')
    162         self(f'after_{event_type}');  final()

/opt/conda/envs/fastai/lib/python3.8/site-packages/fastai/learner.py in _do_one_batch(self)
    167 
    168     def _do_one_batch(self):
--> 169         self.pred = self.model(*self.xb)
    170         self('after_pred')
    171         if len(self.yb):

/opt/conda/envs/fastai/lib/python3.8/site-packages/torch/nn/modules/module.py in _call_impl(self, *input, **kwargs)
    725             result = self._slow_forward(*input, **kwargs)
    726         else:
--> 727             result = self.forward(*input, **kwargs)
    728         for hook in itertools.chain(
    729                 _global_forward_hooks.values(),

/opt/conda/envs/fastai/lib/python3.8/site-packages/blurr/modeling/core.py in forward(self, x)
     41             if k not in self.hf_model_fwd_args: del x[k]
     42 
---> 43         return self.hf_model(**x,
     44                              output_hidden_states=self.output_hidden_states,
     45                              output_attentions=self.output_attentions,

/opt/conda/envs/fastai/lib/python3.8/site-packages/torch/nn/modules/module.py in _call_impl(self, *input, **kwargs)
    725             result = self._slow_forward(*input, **kwargs)
    726         else:
--> 727             result = self.forward(*input, **kwargs)
    728         for hook in itertools.chain(
    729                 _global_forward_hooks.values(),

TypeError: forward() got an unexpected keyword argument 'output_hidden_states'

I'm trying to build a dataloader with data from folders and facing this error:

task = HF_TASKS_AUTO.SequenceClassification
pretrained_model_name = "bert-base-uncased"
hf_arch, hf_config, hf_tokenizer, hf_model = BLURR_MODEL_HELPER.get_hf_objects(pretrained_model_name, task=task)

path = untar_data(URLs.IMDB)

db = DataBlock(blocks=(HF_TextBlock(hf_arch=hf_arch, hf_tokenizer=hf_tokenizer), CategoryBlock), 
               get_items=get_text_files,
               splitter=GrandparentSplitter(train_name='train', valid_name='test'),
               get_y=parent_label)

db.summary(path)

Setting-up type transforms pipelines
Collecting items from /storage/data/imdb
Found 100002 items
2 datasets of sizes 25000,25000
Setting up Pipeline: HF_TokenizerTransform
---------------------------------------------------------------------------
TypeError                                 Traceback (most recent call last)
<ipython-input-34-d2bf6908b967> in <module>
----> 1 db.summary(path)

/opt/conda/envs/fastai/lib/python3.7/site-packages/fastai2/data/block.py in summary(self, source, bs, show_batch, **kwargs)
    152     "Steps through the transform pipeline for one batch, and optionally calls `show_batch(**kwargs)` on the transient `Dataloaders`."
    153     print(f"Setting-up type transforms pipelines")
--> 154     dsets = self.datasets(source, verbose=True)
    155     print("\nBuilding one sample")
    156     for tl in dsets.train.tls:

/opt/conda/envs/fastai/lib/python3.7/site-packages/fastai2/data/block.py in datasets(self, source, verbose)
    102         splits = (self.splitter or RandomSplitter())(items)
    103         pv(f"{len(splits)} datasets of sizes {','.join([str(len(s)) for s in splits])}", verbose)
--> 104         return Datasets(items, tfms=self._combine_type_tfms(), splits=splits, dl_type=self.dl_type, n_inp=self.n_inp, verbose=verbose)
    105 
    106     def dataloaders(self, source, path='.', verbose=False, **kwargs):

/opt/conda/envs/fastai/lib/python3.7/site-packages/fastai2/data/core.py in __init__(self, items, tfms, tls, n_inp, dl_type, **kwargs)
    283     def __init__(self, items=None, tfms=None, tls=None, n_inp=None, dl_type=None, **kwargs):
    284         super().__init__(dl_type=dl_type)
--> 285         self.tls = L(tls if tls else [TfmdLists(items, t, **kwargs) for t in L(ifnone(tfms,[None]))])
    286         self.n_inp = ifnone(n_inp, max(1, len(self.tls)-1))
    287 

/opt/conda/envs/fastai/lib/python3.7/site-packages/fastai2/data/core.py in <listcomp>(.0)
    283     def __init__(self, items=None, tfms=None, tls=None, n_inp=None, dl_type=None, **kwargs):
    284         super().__init__(dl_type=dl_type)
--> 285         self.tls = L(tls if tls else [TfmdLists(items, t, **kwargs) for t in L(ifnone(tfms,[None]))])
    286         self.n_inp = ifnone(n_inp, max(1, len(self.tls)-1))
    287 

/opt/conda/envs/fastai/lib/python3.7/site-packages/fastcore/foundation.py in __call__(cls, x, *args, **kwargs)
     45             return x
     46 
---> 47         res = super().__call__(*((x,) + args), **kwargs)
     48         res._newchk = 0
     49         return res

/opt/conda/envs/fastai/lib/python3.7/site-packages/fastai2/data/core.py in __init__(self, items, tfms, use_list, do_setup, split_idx, train_setup, splits, types, verbose, dl_type)
    221         if do_setup:
    222             pv(f"Setting up {self.tfms}", verbose)
--> 223             self.setup(train_setup=train_setup)
    224 
    225     def _new(self, items, split_idx=None, **kwargs):

/opt/conda/envs/fastai/lib/python3.7/site-packages/fastai2/data/core.py in setup(self, train_setup)
    243             for f in self.tfms.fs:
    244                 self.types.append(getattr(f, 'input_types', type(x)))
--> 245                 x = f(x)
    246             self.types.append(type(x))
    247         types = L(t if is_listy(t) else [t] for t in self.types).concat().unique()

/opt/conda/envs/fastai/lib/python3.7/site-packages/fastcore/transform.py in __call__(self, x, **kwargs)
     70     @property
     71     def name(self): return getattr(self, '_name', _get_name(self))
---> 72     def __call__(self, x, **kwargs): return self._call('encodes', x, **kwargs)
     73     def decode  (self, x, **kwargs): return self._call('decodes', x, **kwargs)
     74     def __repr__(self): return f'{self.name}: {self.encodes} {self.decodes}'

/opt/conda/envs/fastai/lib/python3.7/site-packages/fastcore/transform.py in _call(self, fn, x, split_idx, **kwargs)
     80     def _call(self, fn, x, split_idx=None, **kwargs):
     81         if split_idx!=self.split_idx and self.split_idx is not None: return x
---> 82         return self._do_call(getattr(self, fn), x, **kwargs)
     83 
     84     def _do_call(self, f, x, **kwargs):

/opt/conda/envs/fastai/lib/python3.7/site-packages/fastcore/transform.py in _do_call(self, f, x, **kwargs)
     84     def _do_call(self, f, x, **kwargs):
     85         if not _is_tuple(x):
---> 86             return x if f is None else retain_type(f(x, **kwargs), x, f.returns_none(x))
     87         res = tuple(self._do_call(f, x_, **kwargs) for x_ in x)
     88         return retain_type(res, x)

/opt/conda/envs/fastai/lib/python3.7/site-packages/fastcore/dispatch.py in __call__(self, *args, **kwargs)
     96         if not f: return args[0]
     97         if self.inst is not None: f = MethodType(f, self.inst)
---> 98         return f(*args, **kwargs)
     99 
    100     def __get__(self, inst, owner):

/opt/conda/envs/fastai/lib/python3.7/site-packages/blurr/data/core.py in encodes(self, inp)
     30             toks = self.hf_tokenizer.tokenize(inp, add_prefix_space=self.add_prefix_space)
     31         else:
---> 32             toks = [sub_toks for entity in inp
     33                     for sub_toks in self.hf_tokenizer.tokenize(entity, add_prefix_space=self.add_prefix_space)]
     34 

TypeError: 'PosixPath' object is not iterable

Hey there,

first: Thanks for your awesome tool, that makes everything work so much smoother. I successfully trained a model and want to evaluate its performance. I tried using interp = Interpretation.from_learner(learn), but this fails with an error:

/usr/local/lib/python3.7/dist-packages/fastai/torch_core.py in nested_reorder(t, idxs)
    704     elif is_listy(t): return type(t)(nested_reorder(t_, idxs) for t_ in t)
    705     if t is None: return t
--> 706     raise TypeError(f"Expected tensor, tuple, list or L but got {type(t)}")
    707 
    708 # Cell

TypeError: Expected tensor, tuple, list or L but got <class 'dict'>

Am I missing something or is this an error on my side? Thanks in Advance for your help.

Hi. Is there a way to fix this?

Collecting git+https://github.com/ohmeow/blurr.git
  Cloning https://github.com/ohmeow/blurr.git to c:\users\runner~1\appdata\local\temp\pip-req-build-gaye0t66
    ERROR: Command errored out with exit status 1:
     command: 'C:\Users\RUNNER~1\AppData\Local\R-MINI~1\envs\R-RETI~1\python.exe' -c 'import sys, setuptools, tokenize; sys.argv[0] = '"'"'C:\\Users\\RUNNER~1\\AppData\\Local\\Temp\\pip-req-build-gaye0t66\\setup.py'"'"'; __file__='"'"'C:\\Users\\RUNNER~1\\AppData\\Local\\Temp\\pip-req-build-gaye0t66\\setup.py'"'"';f=getattr(tokenize, '"'"'open'"'"', open)(__file__);code=f.read().replace('"'"'\r\n'"'"', '"'"'\n'"'"');f.close();exec(compile(code, __file__, '"'"'exec'"'"'))' egg_info --egg-base 'C:\Users\RUNNER~1\AppData\Local\Temp\pip-pip-egg-info-mpwpr2p4'
         cwd: C:\Users\RUNNER~1\AppData\Local\Temp\pip-req-build-gaye0t66\
    Complete output (7 lines):
    Traceback (most recent call last):
      File "<string>", line 1, in <module>
      File "C:\Users\RUNNER~1\AppData\Local\Temp\pip-req-build-gaye0t66\setup.py", line 42, in <module>
        long_description = open('README.md').read(),
      File "C:\Users\RUNNER~1\AppData\Local\R-MINI~1\envs\R-RETI~1\lib\encodings\cp1252.py", line 23, in decode
        return codecs.charmap_decode(input,self.errors,decoding_table)[0]
    UnicodeDecodeError: 'charmap' codec can't decode byte 0x9d in position 13891: character maps to <undefined>

Github Actions: https://github.com/henry090/fastai/pull/58/checks?check_run_id=1367643542

I got this when trying to import after installing from master pip install -e ".[dev]" I try to use it on a ipynb and got this:

import torch
from transformers import *
from fastai2.text.all import *

from blurr.data.all import *
from blurr.modeling.all import *

I get

---------------------------------------------------------------------------
ModuleNotFoundError                       Traceback (most recent call last)
<ipython-input-1-906f6e0a84bd> in <module>
      3 from fastai2.text.all import *
      4 
----> 5 from blurr.data.all import *
      6 from blurr.modeling.all import *

~/Documentos/github/blurr/blurr/data/all.py in <module>
      1 from ..utils import *
----> 2 from .core import *
      3 from .language_modeling import *
      4 from .question_answering import *
      5 from .token_classification import *

~/Documentos/github/blurr/blurr/data/core.py in <module>
      6 from functools import reduce
      7 
----> 8 import torch, nlp
      9 from transformers import *
     10 from fastai2.text.all import *

ModuleNotFoundError: No module named 'nlp'

Installing blurr in a Kaggle notebook breaks saving the notebook due incompatible nbconvert requirements. Kaggle requires nbconvert-6.1.0, but blurr installs nbconvert-5.6.1.

This appears to be due to blurr requiring nbverbose as a install requirement. A possible fix on blurr's end could be moving nbverbose to dev_requirements until nbdev has it's dependencies updated.

The dependency tree, from pipdeptree:

- ohmeow-blurr==0.1.0 [requires: nbverbose>=0.0.1] 
   - nbverbose==0.0.9 [requires: nbdev<2.0.0]
      - nbdev==1.1.23 [requires: nbconvert<6]

I tried running the example code in summarization page of doc with 't5-base' model, but it errors out. I have tried using latest release and master of blurr and fastcore but still issue persists. Here's the sample and the error it spits out:

learn = BlearnerForSummarization.from_data(
    cnndm_df,
    "t5-base",
    text_attr="article",
    summary_attr="highlights",
    max_length=256,
    max_target_length=130,
    dblock_splitter=RandomSplitter(),
    dl_kwargs={"bs": 2},
).to_fp16()

The error I get:

---------------------------------------------------------------------------
AttributeError                            Traceback (most recent call last)
Cell In [7], line 1
----> 1 learn = BlearnerForSummarization.from_data(
      2     cnndm_df,
      3     "t5-base",
      4     text_attr="article",
      5     summary_attr="highlights",
      6     max_length=256,
      7     max_target_length=130,
      8     dblock_splitter=RandomSplitter(),
      9     dl_kwargs={"bs": 2},
     10 ).to_fp16()

File ~/mambaforge/envs/aranya/lib/python3.8/site-packages/blurr/text/modeling/seq2seq/summarization.py:146, in BlearnerForSummarization.from_data(cls, data, pretrained_model_name_or_path, text_attr, summary_attr, max_length, max_target_length, dblock_splitter, hf_tok_kwargs, text_gen_kwargs, dl_kwargs, learner_kwargs)
    143 get_y = ItemGetter(summary_attr)
    145 if hf_arch == "t5":
--> 146     get_x.add(cls._add_t5_prefix)
    148 # define our DataBlock and DataLoaders
    149 batch_tokenize_tfm = Seq2SeqBatchTokenizeTransform(
    150     hf_arch,
    151     hf_config,
   (...)
    156     text_gen_kwargs=text_gen_kwargs,
    157 )

File ~/mambaforge/envs/aranya/lib/python3.8/site-packages/fastcore/transform.py:204, in Pipeline.add(self, ts, items, train_setup)
    202 def add(self,ts, items=None, train_setup=False):
    203     if not is_listy(ts): ts=[ts]
--> 204     for t in ts: t.setup(items, train_setup)
    205     self.fs+=ts
    206     self.fs = self.fs.sorted(key='order')

AttributeError: 'function' object has no attribute 'setup'

Hi ,

I am getting issue with below block, my code was running fine a week back, I am getting this issue from last 3 days, I think it is due to fastcore update please check it once : dblock = DataBlock( blocks=blocks, get_x=ColReader("text"), get_y=ColReader("label"), splitter=ColSplitter() )

Below error triggered

AttributeError Traceback (most recent call last) in 8 get_x=ColReader("text"), 9 get_y=ColReader("label"), ---> 10 splitter=ColSplitter() 11 ) 12

2 frames /usr/local/lib/python3.7/dist-packages/fastcore/meta.py in _init(self, *args, **kwargs) 148 if isinstance(arg,MethodType): arg = MethodType(arg.func, self) 149 setattr(self, k, arg) --> 150 old_init(self, *args, **kwargs) 151 functools.update_wrapper(_init, old_init) 152 cls.init = use_kwargs(cls._methods)(_init)

/usr/local/lib/python3.7/dist-packages/fastai/data/block.py in init(self, blocks, dl_type, getters, n_inp, item_tfms, batch_tfms, **kwargs) 97 if getattr(b, 'dl_type', None) is not None: self.dl_type = b.dl_type 98 if dl_type is not None: self.dl_type = dl_type ---> 99 self.dataloaders = delegates(self.dl_type.init)(self.dataloaders) 100 self.dls_kwargs = merge(*blocks.attrgot('dls_kwargs', {})) 101

/usr/local/lib/python3.7/dist-packages/fastcore/meta.py in _f(f) 123 s2 = {k:v.replace(kind=inspect.Parameter.KEYWORD_ONLY) for k,v in inspect.signature(to_f).parameters.items() 124 if v.default != inspect.Parameter.empty and k not in sigd and k not in but} --> 125 anno = {k:v for k,v in to_f.annotations.items() if k not in sigd and k not in but} 126 sigd.update(s2) 127 if keep: sigd['kwargs'] = k

AttributeError: 'method-wrapper' object has no attribute 'annotations'

I am just running the code https://pypi.org/project/ohmeow-blurr/0.0.7/. It is giving the same error: Here is code snip as well:

import os, warnings

import torch from transformers import * from transformers.utils import logging as hf_logging from fastai.text.all import *

from blurr.text.data.all import * from blurr.text.modeling.all import *

path = untar_data(URLs.IMDB_SAMPLE)

model_path = Path("models") imdb_df = pd.read_csv(path / "texts.csv")

n_labels = len(imdb_df["label"].unique())

model_cls = AutoModelForSequenceClassification

pretrained_model_name = "bert-base-uncased"

config = AutoConfig.from_pretrained(pretrained_model_name) config.num_labels = n_labels

hf_arch, hf_config, hf_tokenizer, hf_model = get_hf_objects( pretrained_model_name, model_cls=model_cls, config=config )

single input

blocks = ( TextBlock(hf_arch, hf_config, hf_tokenizer, hf_model), CategoryBlock ) dblock = DataBlock( blocks=blocks, get_x=ColReader("text"), get_y=ColReader("label"), splitter=ColSplitter() )

dls = dblock.dataloaders(imdb_df, bs=4)

Note: dblock is giving error here

I've been trying to do some MLModelling with Blurr and transformers from huggingface. When I come to the datablock creation I get an Error.

It is a problem with the DataBlock class from fastai and fastcore delegate decorator.

From what I understood it is delegating the dataloaders creation, but looks like the delegator is waiting an annotation attribute taht doesn't exist. I am using google colab

Hello, I'm new to DL and have just begun the Fastai course for 2022.

I'm working on a Multi-label classification problem and downloaded the Emotions Dataset from Hugging. As shown below, this Dataset used an Array to show the Multi-label.

I've looked at the example in the repository. You have changed the data to this One-hot encoding value.

and then used the Colreader to get the Y variable.

So, my question is: Do I have to use the same structure for my problem as well, or is there a different one I can use?

Hi, I'm trying to load a keras model saved as h5 by passing model_kwargs={"from_tf": True} to get_hf_objects. This consistently causes CUDA out of memory errors. I've tried reducing batch_size to 1, and downgraded pytorch to 1.9.0. Any ideas what could be going wrong? Thanks in advance.

Traceback (most recent call last): File "/scratch/gh47/dg5608/pretraining-benefits/src/biobart_cnn_tf.py", line 52, in <module> model = BaseModelWrapper(hf_model) File "/scratch/gh47/dg5608/pt109/lib/python3.9/site-packages/fastcore/meta.py", line 39, in __call__ res.__init__(*args,**kwargs) File "/scratch/gh47/dg5608/pt109/lib/python3.9/site-packages/blurr/text/modeling/core.py", line 58, in __init__ self.hf_model = hf_model.cuda() if torch.cuda.is_available() else hf_model File "/apps/pytorch/1.9.0/lib/python3.9/site-packages/torch/nn/modules/module.py", line 637, in cuda return self._apply(lambda t: t.cuda(device)) File "/apps/pytorch/1.9.0/lib/python3.9/site-packages/torch/nn/modules/module.py", line 530, in _apply module._apply(fn) File "/apps/pytorch/1.9.0/lib/python3.9/site-packages/torch/nn/modules/module.py", line 530, in _apply module._apply(fn) File "/apps/pytorch/1.9.0/lib/python3.9/site-packages/torch/nn/modules/module.py", line 530, in _apply module._apply(fn) [Previous line repeated 3 more times] File "/apps/pytorch/1.9.0/lib/python3.9/site-packages/torch/nn/modules/module.py", line 552, in _apply param_applied = fn(param) File "/apps/pytorch/1.9.0/lib/python3.9/site-packages/torch/nn/modules/module.py", line 637, in <lambda> return self._apply(lambda t: t.cuda(device)) RuntimeError: CUDA out of memory. Tried to allocate 20.00 MiB (GPU 0; 31.75 GiB total capacity; 909.13 MiB already allocated; 1.94 MiB free; 920.00 MiB reserved in total by PyTorch)

I'm working on the text summarization task. How to save and load the pretrained model instead of downloading again and again on google colab/local pc?

Below is the code i'm working on

pretrained_model_name = "facebook/bart-large-cnn"
hf_arch, hf_config, hf_tokenizer, hf_model = get_hf_objects(pretrained_model_name, model_cls=BartForConditionalGeneration)

hf_arch, type(hf_config), type(hf_tokenizer), type(hf_model)