imbalanced data set not reading in correctly to torch

[jbh1128d1]

Hello,

I'm getting the following error trying to use the Imbalanced data sampler.

---

ValueError Traceback (most recent call last)
in
----> 1 train_loader = DataLoader(roof, batch_size=10, sampler = ImbalancedDatasetSampler)

C:\ProgramData\Anaconda3\lib\site-packages\torch\utils\data\dataloader.py in init(self, dataset, batch_size, shuffle, sampler, batch_sampler, num_workers, collate_fn, pin_memory, drop_last, timeout, worker_init_fn, multiprocessing_context)
217 if batch_size is not None and batch_sampler is None:
218 # auto_collation without custom batch_sampler
--> 219 batch_sampler = BatchSampler(sampler, batch_size, drop_last)
220
221 self.batch_size = batch_size

C:\ProgramData\Anaconda3\lib\site-packages\torch\utils\data\sampler.py in init(self, sampler, batch_size, drop_last)
184 raise ValueError("sampler should be an instance of "
185 "torch.utils.data.Sampler, but got sampler={}"
--> 186 .format(sampler))
187 if not isinstance(batch_size, _int_classes) or isinstance(batch_size, bool) or
188 batch_size <= 0:

ValueError: sampler should be an instance of torch.utils.data.Sampler, but got sampler=<class 'sampler.ImbalancedDatasetSampler'>

Was I supposed to save the sampler.py file in a special location? I saved it in my directory and it imports.