I've been trying to use the following package and just when I tried to instantiate it, NotImplementedError:
showed up in Google Colab.
Complete traceback of the issue
<ipython-input-51-9980be5d7f5b> in <module>()
4 test_dataset = MyData(input_tensor_test, target_tensor_test)
5
----> 6 train_dataset = DataLoader(train_dataset, sampler=ImbalancedDatasetSampler(train_dataset),batch_size = BATCH_SIZE,
7 drop_last=True
8 )
1 frames
/content/drive/My Drive/torchsampler/imbalanced.py in __init__(self, dataset, indices, num_samples, callback_get_label)
30 label_to_count = {}
31 for idx in self.indices:
---> 32 label = self._get_label(dataset, idx)
33 if label in label_to_count:
34 label_to_count[label] += 1
/content/drive/My Drive/torchsampler/imbalanced.py in _get_label(self, dataset, idx)
51 return self.callback_get_label(dataset, idx)
52 else:
---> 53 raise NotImplementedError
54
55 def __iter__(self):
NotImplementedError:
I've seen similar solution to tackle this but it was in jupyter notebook where proposed solution consisted of upgrading the notebook.
How can I do it in Colab or is there any other alternate way to fix this issue on Colab?