The size of tensor a (983040) must match the size of tensor b (491520) at non-singleton dimension 0

dls = SegmentationDataLoaders.from_label_func(data_path, fnames, get_mask_path, valid_pct=0.2, seed=42, codes=codes, bs=bs, item_tfms=Resize(src_size // 2, method=ResizeMethod.Squish))
learn = unet_learner(dls, resnet34, loss_func=loss_func, metrics=Dice, wd=wd, y_range=(0,1), path=save_path)
learn.lr_find()

/usr/local/lib/python3.6/dist-packages/torch/tensor.py:995: UserWarning: Using a target size (torch.Size([491520])) that is different to the input size (torch.Size([983040])). This will likely lead to incorrect results due to broadcasting. Please ensure they have the same size.
ret = func(*args, **kwargs)
RuntimeError: The size of tensor a (983040) must match the size of tensor b (491520) at non-singleton dimension 0

Any help with this is much appreciated