AttributeError: train_ds

I have 5 classes arranged in 5 folders for my training set. For my test set, I have image samples in a single folder without any classes at all(not arranged in folders according to class or you can’t extract labels from image name).

NB: Training set is in path and test set is in unlabelled_path

data = DataBlock(
    blocks=(ImageBlock, CategoryBlock), 
    splitter=RandomSplitter(valid_pct=0.2, seed=42),

dls = data.dataloaders(path).test_dl(get_image_files(unlabelled_path))
learner = cnn_learner(dls, resnet34, metrics = [accuracy],n_out=5)

When I run the cell containing the learning, I get the error

   /usr/local/lib/python3.6/dist-packages/fastcore/ in _f(*args, **kwargs)
     50         log_dict = {**func_args.arguments, **{f'{k} (not in signature)':v for k,v in xtra_kwargs.items()}}
     51         log = {f'{f.__qualname__}.{k}':v for k,v in log_dict.items() if k not in but}
---> 52         inst = f(*args, **kwargs) if to_return else args[0]
     53         init_args = getattr(inst, 'init_args', {})
     54         init_args.update(log)

/usr/local/lib/python3.6/dist-packages/fastai/vision/ in cnn_learner(dls, arch, loss_func, pretrained, cut, splitter, y_range, config, n_out, normalize, **kwargs)
    174     if y_range is None and 'y_range' in config: y_range = config.pop('y_range')
    175     model = create_cnn_model(arch, n_out, ifnone(cut, meta['cut']), pretrained, y_range=y_range, **config)
--> 176     learn = Learner(dls, model, loss_func=loss_func, splitter=ifnone(splitter, meta['split']), **kwargs)
    177     if pretrained: learn.freeze()
    178     return learn

/usr/local/lib/python3.6/dist-packages/fastcore/ in _f(*args, **kwargs)
     54         init_args.update(log)
     55         setattr(inst, 'init_args', init_args)
---> 56         return inst if to_return else f(*args, **kwargs)
     57     return _f

/usr/local/lib/python3.6/dist-packages/fastai/ in __init__(self, dls, model, loss_func, opt_func, lr, splitter, cbs, metrics, path, model_dir, wd, wd_bn_bias, train_bn, moms)
     86         path = Path(path) if path is not None else getattr(dls, 'path', Path('.'))
     87         if loss_func is None:
---> 88             loss_func = getattr(dls.train_ds, 'loss_func', None)
     89             assert loss_func is not None, "Could not infer loss function from the data, please pass a loss function."
     90         self.dls,self.model = dls,model

/usr/local/lib/python3.6/dist-packages/fastcore/ in __getattr__(self, k)
    156         if self._component_attr_filter(k):
    157             attr = getattr(self,self._default,None)
--> 158             if attr is not None: return getattr(attr,k)
    159         raise AttributeError(k)
    160     def __dir__(self): return custom_dir(self,self._dir())

/usr/local/lib/python3.6/dist-packages/fastai/data/ in __getattr__(self, k)
    315         return res if is_indexer(it) else list(zip(*res))
--> 317     def __getattr__(self,k): return gather_attrs(self, k, 'tls')
    318     def __dir__(self): return super().__dir__() + gather_attr_names(self, 'tls')
    319     def __len__(self): return len(self.tls[0])

/usr/local/lib/python3.6/dist-packages/fastcore/ in gather_attrs(o, k, nm)
    163     att = getattr(o,nm)
    164     res = [t for t in att.attrgot(k) if t is not None]
--> 165     if not res: raise AttributeError(k)
    166     return res[0] if len(res)==1 else L(res)

AttributeError: train_ds

Fastai version 2.0.15