Dear Fastai Community,
I’ve been playing around with Alan Bertl’s autoencoder with fast.ai tutorial and have by and large been able to replicate it a recent version of fastai: ‘1.0.50.post1’, successfully training the autoencoder.
When I go to use learn.show_results(), however, I’m getting the following error:
---------------------------------------------------------------------------
AttributeError Traceback (most recent call last)
<ipython-input-47-c3b657dcc9ae> in <module>
----> 1 learn.show_results()
/opt/conda/lib/python3.6/site-packages/fastai/basic_train.py in show_results(self, ds_type, rows, **kwargs)
400 xs = [ds.x.reconstruct(grab_idx(x, i)) for i in range(n_items)]
401 if has_arg(ds.y.reconstruct, 'x'):
--> 402 ys = [ds.y.reconstruct(grab_idx(y, i), x=x) for i,x in enumerate(xs)]
403 zs = [ds.y.reconstruct(z, x=x) for z,x in zip(preds,xs)]
404 else :
/opt/conda/lib/python3.6/site-packages/fastai/basic_train.py in <listcomp>(.0)
400 xs = [ds.x.reconstruct(grab_idx(x, i)) for i in range(n_items)]
401 if has_arg(ds.y.reconstruct, 'x'):
--> 402 ys = [ds.y.reconstruct(grab_idx(y, i), x=x) for i,x in enumerate(xs)]
403 zs = [ds.y.reconstruct(z, x=x) for z,x in zip(preds,xs)]
404 else :
/opt/conda/lib/python3.6/site-packages/fastai/data_block.py in reconstruct(self, t, x)
89 def reconstruct(self, t:Tensor, x:Tensor=None):
90 "Reconstruct one of the underlying item for its data `t`."
---> 91 return self[0].reconstruct(t,x) if has_arg(self[0].reconstruct, 'x') else self[0].reconstruct(t)
92
93 def new(self, items:Iterator, processor:PreProcessors=None, **kwargs)->'ItemList':
AttributeError: 'Tensor' object has no attribute 'reconstruct'
I imagine this might be a versioning issue, but I’m not sure. Has anyone seen something like this before?