conv(weight)+BN+ReLU is the basic operation when building convolutional networks. How about conv(weight)+ReLU+BN? In this tutorial, we will discuss this topic.
In this tutorial, we will introduce what is mixed precision training, how about the effect of it and how to use it.
In this tutorial, we will discuss the different effect of layer normalization in RNN, CNN and Feed-Forward Networks.
In this tutorial, we will introduce the structure of Resnet V1 and Resnet V2, we also discuss the performance of them.
In this tutorial, we introduce what is causal padding, and discuss the difference SAME or VALID padding. It will be very useful to you.
In this tutorial, we will introduce you how to use python to generate hash audio fingerprinting for audio retrieval and detection. It contains three parts, we will introduce you one by one.
In this tutorial, we will use an example code to show you how to split musan dataset to musan_split dataset, which cotains many small wav files from musan dataset.
Channel attention is the core of Squeeze-and-Excitation (SE) block. In this tutorial, we will analysis how to implement it for beginners.
In speaker verification task, we often use EER to measure the performance of a deep learning model. However, if you also need to compute Recall, we will tell you how to do in this tutorial.
We have known that random seed value can affect the performance of a deep learning model. In this tutorial, we will discuss what random seed we should use when building an AI model.