Type issue when using get_tabular_learner for regression problem

[harvitronix]

I'm trying to run a regression on a dataframe with categorical and continuous columns using the get_tabular_learner() helper. My code is as follows:

df = pd.read_csv(DATA_PATH)
dep_var = 'actual'

train_df, valid_df = df[:10000].copy(), df[10000:].copy()

data = tabular_data_from_df('.', train_df, valid_df, dep_var, tfms=[Categorify], cat_names=CAT_NAMES, cont_names=CONT_NAMES)

learn = get_tabular_learner(data, layers=[200,100])
learn.loss_fn = F.mse_loss
learn.fit(1)

Running this gives me an error with the loss function:

File "/home/harvitronix/.local/lib/python3.6/site-packages/fastai/basic_train.py", line 25, in loss_batch
    loss = loss_fn(out, *yb)
  File "/home/harvitronix/.local/lib/python3.6/site-packages/torch/nn/functional.py", line 1808, in mse_loss
    return _pointwise_loss(lambda a, b: (a - b) ** 2, torch._C._nn.mse_loss, input, target, reduction)
  File "/home/harvitronix/.local/lib/python3.6/site-packages/torch/nn/functional.py", line 1770, in _pointwise_loss
    return lambd_optimized(input, target, _Reduction.get_enum(reduction))
RuntimeError: Expected object of scalar type Float but got scalar type Double for argument #2 'target'

I'm unclear if this is a bug or implementation error. Guidance is appreciated.

[jandremarais]

What happens if you add log_output=True to tabular_data_from_df and change layers argument to [200, 1]?

Edit:

Or if you don't want log_output=True, you can hack at it this way:

def myloss(input, target): return F.mse_loss(input, target.float())
learn.loss_fn = myloss

Not sure where to tell the learner that it is a regression model.

[jph00]

Can you please ask this question on the forums?