# Random batch sampling from DataLoader **URL:** \ **Category:** Uncategorized\ **Created:** [March 2, 2021, 10:59am UTC](https://discuss.pytorch.org/t/random-batch-sampling-from-dataloader/113457 "2021-03-02T10:59:28Z")\ **Posts on this page:** 9\ **Page:** 1
**Author:** ![razvanc92](https://discuss.pytorch.org/user_avatar/discuss.pytorch.org/razvanc92/32/25610_2.png) [@razvanc92](https://discuss.pytorch.org/u/razvanc92)\ **Post date:** [March 2, 2021, 10:59am UTC](https://discuss.pytorch.org/t/random-batch-sampling-from-dataloader/113457/1 "2021-03-02T10:59:28Z")
Hello, I’m interesting if it’s possible to randomly sample X batches of data from a DataLoader object for each epoch. Is there any way of accessing the batches by indexes? Or something similar to achieve such behavior? Thank you for the help. ---
**Author:** ![Laura\_Montalvo](https://discuss.pytorch.org/user_avatar/discuss.pytorch.org/laura_montalvo/32/34770_2.png) [@Laura\_Montalvo](https://discuss.pytorch.org/u/Laura_Montalvo)\ **Post date:** [March 2, 2021, 11:02am UTC](https://discuss.pytorch.org/t/random-batch-sampling-from-dataloader/113457/2 "2021-03-02T11:02:25Z")
I guess what you’re asking the following: - If you set the dataloader class shuffle=True you can get random samples into your batches. I mean the batches will be created with random samples of the dataset insead of sequential ones. - For accesing the batches with indexes try with for batch, (data, target) in enumerate(loader) so the batch variable will store the value of the batch (I think it works that way) ---
**Author:** ![razvanc92](https://discuss.pytorch.org/user_avatar/discuss.pytorch.org/razvanc92/32/25610_2.png) [@razvanc92](https://discuss.pytorch.org/u/razvanc92)\ **Post date:** [March 2, 2021, 11:10am UTC](https://discuss.pytorch.org/t/random-batch-sampling-from-dataloader/113457/4 "2021-03-02T11:10:51Z")
Thank you for your replay. I already tried this solution, the problem is that for each epoch (training loop) I want to select a small subset of batches (lets say 5 batches). If i simply enumerate though the loader (enumerate(loader)) I will get the same order (the shuffled version from the data loader) since. I am interested if something like this is possible (or some other way to achieve the same behaviour): ```auto data_loader = torch.utils.data.DataLoader(data, shuffle=True) for epoch in range(100): random_ids = np.random.randint(len(data_loader), size=5) batches = data_loader[random_ids] ``` ---
**Author:** ![Laura\_Montalvo](https://discuss.pytorch.org/user_avatar/discuss.pytorch.org/laura_montalvo/32/34770_2.png) [@Laura\_Montalvo](https://discuss.pytorch.org/u/Laura_Montalvo)\ **Post date:** [March 2, 2021, 11:12am UTC](https://discuss.pytorch.org/t/random-batch-sampling-from-dataloader/113457/5 "2021-03-02T11:12:32Z")
Sorry then! I dont know how to help you with that 😬 ---
**Author:** ![razvanc92](https://discuss.pytorch.org/user_avatar/discuss.pytorch.org/razvanc92/32/25610_2.png) [@razvanc92](https://discuss.pytorch.org/u/razvanc92)\ **Post date:** [March 2, 2021, 11:13am UTC](https://discuss.pytorch.org/t/random-batch-sampling-from-dataloader/113457/6 "2021-03-02T11:13:34Z")
No worries, I’ve been struggling with this for a while. ---
**Author:** ![ptrblck](https://discuss.pytorch.org/user_avatar/discuss.pytorch.org/ptrblck/32/1823_2.png) [@ptrblck](https://discuss.pytorch.org/u/ptrblck)\ **Post date:** [March 2, 2021, 7:29pm UTC](https://discuss.pytorch.org/t/random-batch-sampling-from-dataloader/113457/7 "2021-03-02T19:29:32Z")
If you want to sample only a specific subset using predefined indices, you could create a new `DataLoader` with a `SubsetRandomSampler` or wrap the `Dataset` into a `Subset`. ---
**Author:** ![Flock1](https://discuss.pytorch.org/user_avatar/discuss.pytorch.org/flock1/32/12220_2.png) [@Flock1](https://discuss.pytorch.org/u/Flock1)\ **Post date:** [December 3, 2022, 12:33am UTC](https://discuss.pytorch.org/t/random-batch-sampling-from-dataloader/113457/8 "2022-12-03T00:33:16Z")
Hi, I did this ```auto num_test_examples = len(test_dl) indices = torch.randperm(num_test_examples)[:100] random_test_dataset = SubsetRandomSampler(test_dl, indices) random_test_dataloader = DataLoader(random_test_dataset, batch_size=1, shuffle=False) for i,data in random_test_dataloader: print(i) ``` Then I get this error: ```auto TypeError Traceback (most recent call last) /tmp/ipykernel_84972/1562982579.py in ----> 1 for i,data in random_test_dataloader: 2 print(i) ~/anaconda3/envs/torch/lib/python3.8/site-packages/torch/utils/data/dataloader.py in __next__ (self) 626 # TODO(https://github.com/pytorch/pytorch/issues/76750) 627 self._reset() # type: ignore[call-arg] --> 628 data = self._next_data() 629 self._num_yielded += 1 630 if self._dataset_kind == _DatasetKind.Iterable and \ ~/anaconda3/envs/torch/lib/python3.8/site-packages/torch/utils/data/dataloader.py in _next_data(self) 669 def _next_data(self): 670 index = self._next_index() # may raise StopIteration --> 671 data = self._dataset_fetcher.fetch(index) # may raise StopIteration 672 if self._pin_memory: 673 data = _utils.pin_memory.pin_memory(data, self._pin_memory_device) ~/anaconda3/envs/torch/lib/python3.8/site-packages/torch/utils/data/_utils/fetch.py in fetch(self, possibly_batched_index) 56 data = self.dataset. __getitems__ (possibly_batched_index) 57 else: ---> 58 data = [self.dataset[idx] for idx in possibly_batched_index] 59 else: ... ---> 58 data = [self.dataset[idx] for idx in possibly_batched_index] 59 else: 60 data = self.dataset[possibly_batched_index] TypeError: 'SubsetRandomSampler' object is not subscriptable ``` What should I do here? ---
**Author:** ![ptrblck](https://discuss.pytorch.org/user_avatar/discuss.pytorch.org/ptrblck/32/1823_2.png) [@ptrblck](https://discuss.pytorch.org/u/ptrblck)\ **Post date:** [December 3, 2022, 12:35am UTC](https://discuss.pytorch.org/t/random-batch-sampling-from-dataloader/113457/9 "2022-12-03T00:35:42Z")
You have to pass the `SubsetRandomSampler` as the `sampler` argument, not as the `dataset`. ---
**Author:** ![Flock1](https://discuss.pytorch.org/user_avatar/discuss.pytorch.org/flock1/32/12220_2.png) [@Flock1](https://discuss.pytorch.org/u/Flock1)\ **Post date:** [December 3, 2022, 12:58am UTC](https://discuss.pytorch.org/t/random-batch-sampling-from-dataloader/113457/10 "2022-12-03T00:58:43Z")
Like this? ```auto random_test_dataloader = DataLoader(test_dl, batch_size=1, shuffle=False, sampler=random_test_dataset) ```