PyTorch Tutorials and Examples for Beginners

Here 1D matrix is: [batch_size, channel, width] or [batch_size, channel, height]. We will implement a SE block on it in pytorch.

As to 2D matrix, it means the shape is [batch, channel, height, width]. In this tutorial, we will introduce how to implement a squeeze-and-excitation (SE) block for this kind of data.

Parameter inplace appears in many pytorch functions. In this tutorial, we will use some example to help you understand it.

In this tutorial, we will introduce how to implement ranger optimizer in pytorch. There are two ways to implement, we will introduce one by one.

torch.optim.lr_scheduler.StepLR() allows us to change the learning rate when training a model. In this tutorial, we will use some examples to show you how to use it.

In this tutorial, we will use some examples to show you how to use torch.optim.lr_scheduler.CosineAnnealingLR() in pytorch.

When we are using torch.nn.Conv2d() function, we may also use torch.nn.AdaptiveAvgPool2d(). In this tutorial, we will use some examples to show you how to use it.

When we are reading papers, we may see: All models are trained using Adam with a learning rate of 0.001 and gradient clipping at 2.0. In this tutorial, we will introduce gradient clipping in pytorch.

When we are using torch.nn.Conv1d(), we may want the input and output have the same shape. In this tutorial, we will introduce you how to do.

Focal loss is one of method to process imbalance dataset in deep learning. In this tutorial, we will introduce how to implement focal loss for multi label classification in pytorch.