PyTorch Tutorials and Examples for Beginners

PyTorch torch.nn.functional.normalize() function can allow us to compute \(L_p\) normalization of a tensor over specified dimension.

In this tutorial, we will use an example to show you how to use transformers.get_linear_schedule_with_warmup(). You can see the effect of it.

In this tutorial, we will use some example to show you the effect of pytorch scheduler last_epoch parameter.

In this tutorial, we will create an example to show the effect of transformers.get_cosine_schedule_with_warmup(), you can understand how to use this function easily.

In this tutorial, we will create a warm-up scheduler without without package dependency in pytorch. This scheduler is very easy to use.

In this tutorial, we will introduce you how to fix pytorch error: RuntimeError: one of the variables needed for gradient computation has been modified by an inplace operation.

It is easy to use torch.sum() function. In this tutorial, we will use some examples to show you how to use it.

There does not exist a function like tf.sequence_mask() in pytorch. It is not easy to process variable length sequence. In this tutorial, we will introduce you how to create a function like tf.sequence_mask().

When we are creating pytorch tensor, we may use scalar, tuple and list. In this tutorial, we will introduce the difference when using them.