# TypeError: 'DataLoader' object is not callable **URL:** \ **Category:** Uncategorized\ **Created:** [April 1, 2020, 7:29am UTC](https://discuss.pytorch.org/t/typeerror-dataloader-object-is-not-callable/74979 "2020-04-01T07:29:11Z")\ **Posts on this page:** 11\ **Page:** 1
**Author:** ![Sreekar](https://discuss.pytorch.org/user_avatar/discuss.pytorch.org/sreekar/32/22221_2.png) [@Sreekar](https://discuss.pytorch.org/u/Sreekar)\ **Post date:** [April 1, 2020, 7:29am UTC](https://discuss.pytorch.org/t/typeerror-dataloader-object-is-not-callable/74979/1 "2020-04-01T07:29:11Z")
train\_loader = DataLoader(dataset=dataset, batch\_size=40, shuffle=False) " This is my train loader variable." for epoch in range(num\_epochs): for i in enumerate(train\_loader): t = train\_loader(-1,1).to(device) outputs = model(t) loss = criterion(outputs) optimizer.zero\_grad() loss.backward() optimizer.step() ``` if (i + 1) % 100 == 0: print('Epoch [{}/{}], Step [{}/{}], Loss: {:.4f}'.format(epoch + 1, num_epochs, i + 1, total_step, loss.item())) ``` ![Screenshot 2020-04-01 at 12.57.59 PM](https://discuss.pytorch.org/uploads/default/original/3X/7/5/759e9d80551a842d2cd10d427140c292e50afdc8.png) I’m getting this error whatever I change. Can anyone help me with this? Thanks in advance ---
**Author:** ![damicoedoardo](https://discuss.pytorch.org/user_avatar/discuss.pytorch.org/damicoedoardo/32/21571_2.png) [@damicoedoardo](https://discuss.pytorch.org/u/damicoedoardo)\ **Post date:** [April 1, 2020, 7:41am UTC](https://discuss.pytorch.org/t/typeerror-dataloader-object-is-not-callable/74979/2 "2020-04-01T07:41:59Z")
I don’t get what you want to do doing: ```auto t = train_loader(-1,1) ``` you are trying to call the `DataLoader` class which is not callable as suggested by the error. What do you want achieve with (-1,1)? ---
**Author:** ![Sreekar](https://discuss.pytorch.org/user_avatar/discuss.pytorch.org/sreekar/32/22221_2.png) [@Sreekar](https://discuss.pytorch.org/u/Sreekar)\ **Post date:** [April 1, 2020, 7:58am UTC](https://discuss.pytorch.org/t/typeerror-dataloader-object-is-not-callable/74979/3 "2020-04-01T07:58:06Z")
i want to load my data into the model ---
**Author:** ![Sreekar](https://discuss.pytorch.org/user_avatar/discuss.pytorch.org/sreekar/32/22221_2.png) [@Sreekar](https://discuss.pytorch.org/u/Sreekar)\ **Post date:** [April 1, 2020, 8:03am UTC](https://discuss.pytorch.org/t/typeerror-dataloader-object-is-not-callable/74979/4 "2020-04-01T08:03:59Z")
This is sample data 13 0 -1 13 0 -1 13 0 -1 16 0 -1 12 0 -1 I converted them to tensor and i want train the data by passing them to model and i’m unable to load the data into model. ---
**Author:** ![damicoedoardo](https://discuss.pytorch.org/user_avatar/discuss.pytorch.org/damicoedoardo/32/21571_2.png) [@damicoedoardo](https://discuss.pytorch.org/u/damicoedoardo)\ **Post date:** [April 1, 2020, 8:55am UTC](https://discuss.pytorch.org/t/typeerror-dataloader-object-is-not-callable/74979/5 "2020-04-01T08:55:53Z")
You have to iterate on the data loader, Check the tutorial: [data loader tutorial](https://pytorch.org/tutorials/beginner/data_loading_tutorial.html#iterating-through-the-dataset) Basically: `for i_batch, sample_batched in enumerate(dataloader): ` Hope I have been useful 😁 ---
**Author:** ![braindotai](https://discuss.pytorch.org/user_avatar/discuss.pytorch.org/braindotai/32/61373_2.png) [@braindotai](https://discuss.pytorch.org/u/braindotai)\ **Post date:** [April 1, 2020, 9:07am UTC](https://discuss.pytorch.org/t/typeerror-dataloader-object-is-not-callable/74979/6 "2020-04-01T09:07:45Z")
Few things I found- - As @damicoedoardo mentioned you should iterate for dataloader as- ```python for i, batch in enumerate(train_loader): ``` - You should pass only the features of the batch, not the whole batch. In a normal supervised scenario, you will have `len(batch)` = 2, which means `features = batch[0]` and `labels = batch[1]`. And you will calculate predictions as `outputs = model(features)` > [@Sreekar](#): > > loss = criterion(outputs) - I don’t get how you are minimizing the loss functions here without passing labels? Something like `loss = criterion(outputs, labels)`. Can you tell what criterion you are using? - And by calling `.(-1, 1)` I think you are trying to reshape the labels or maybe features to (-1, 1). If your cirterion is `torch.nn.CrossEntropyLoss()` then shape of the labels should be (-1), that’s it, no reshaping is required for labels there. Also features shape should be (-1, n) where n is number of unique features in your single training example. If you want to reshape either you can do as- - So your final traning loop should like - ```python for epoch in range(num_epochs): for i, batch in enumerate(train_loader): features = batch[0] labels = batch[1] features = features.reshape(-1, n) # only if features's shape is not this already, put the value of n here!! labels = labels.reshape(-1, 1) # only if labels's shape is not this already outputs = model(features) loss = criterion(outputs, labels) optimizer.zero_grad() loss.backward() optimizer.step() ``` ---
**Author:** ![Sreekar](https://discuss.pytorch.org/user_avatar/discuss.pytorch.org/sreekar/32/22221_2.png) [@Sreekar](https://discuss.pytorch.org/u/Sreekar)\ **Post date:** [April 1, 2020, 9:37am UTC](https://discuss.pytorch.org/t/typeerror-dataloader-object-is-not-callable/74979/7 "2020-04-01T09:37:19Z")
I tried your solution and I’m getting this error ![Screenshot 2020-04-01 at 3.06.11 PM](https://discuss.pytorch.org/uploads/default/original/3X/4/e/4e8efea2dc390fa410092521330ee3162019af63.png) ---
**Author:** ![Sreekar](https://discuss.pytorch.org/user_avatar/discuss.pytorch.org/sreekar/32/22221_2.png) [@Sreekar](https://discuss.pytorch.org/u/Sreekar)\ **Post date:** [April 1, 2020, 9:43am UTC](https://discuss.pytorch.org/t/typeerror-dataloader-object-is-not-callable/74979/8 "2020-04-01T09:43:25Z")
I tried it previously and it did not work. ---
**Author:** ![braindotai](https://discuss.pytorch.org/user_avatar/discuss.pytorch.org/braindotai/32/61373_2.png) [@braindotai](https://discuss.pytorch.org/u/braindotai)\ **Post date:** [April 1, 2020, 10:09am UTC](https://discuss.pytorch.org/t/typeerror-dataloader-object-is-not-callable/74979/9 "2020-04-01T10:09:10Z")
Show me your complete model definition. And print shapes for features and labels. Also what is your criterion??? ---
**Author:** ![Sreekar](https://discuss.pytorch.org/user_avatar/discuss.pytorch.org/sreekar/32/22221_2.png) [@Sreekar](https://discuss.pytorch.org/u/Sreekar)\ **Post date:** [April 1, 2020, 11:59am UTC](https://discuss.pytorch.org/t/typeerror-dataloader-object-is-not-callable/74979/10 "2020-04-01T11:59:51Z")
![Screenshot 2020-04-01 at 5.28.52 PM](https://discuss.pytorch.org/uploads/default/original/3X/a/2/a20878a5c60bd67831b71f58686e7b2ba85b0854.png) ! ---
**Author:** ![Sreekar](https://discuss.pytorch.org/user_avatar/discuss.pytorch.org/sreekar/32/22221_2.png) [@Sreekar](https://discuss.pytorch.org/u/Sreekar)\ **Post date:** [April 1, 2020, 12:00pm UTC](https://discuss.pytorch.org/t/typeerror-dataloader-object-is-not-callable/74979/11 "2020-04-01T12:00:33Z")
![Screenshot 2020-04-01 at 5.30.29 PM](https://discuss.pytorch.org/uploads/default/original/3X/7/4/748a2bc64142124df444885bf476ec9fb4b8c734.png)