DBScan Density-Based Scan is a clustering method recommended when clusters are nested. You first specify 2 parameters. 1. Radius 2. Number of points to be considered as “core” points. Algorithm The algorithm takes the following steps. 1. Within the radius,…
Pruning “Pruning” means sparsing the network for faster inference. Most of the weights inside networks are quite useless, so this can help when you have limited resources such as running inference on the edge. Methods There are mainly 2 methods…
Here is a simple diagram of understanding the meaning of each error rate gaps.
There are 2 ways to consider “depth” for models.
Here is a simple guide to consider what you need to do next to improve your model’s performance.
Selective Search Selective search is a region proposal method for object detection. It hierarchically groups similar regions based on color, texture, size, and shape. Selective Search uses over-segmented images as input. Then takes the following steps. 1. Add all bounding…
Here is one way to combine losses using PyTorch. Let’s say we want to train a binary semantic segmentation model using Binary Cross Entropy Loss. When you look at your data, you’ve noticed that the data is quite imbalanced. So…
Why Do we Normalize Inputs? When the input is not normalized, the shape of the cost function can become distorted like the diagram on the left. This leads to instability when optimizing the model. The training speed decreases depending on…
Why are residual blocks called “residual” blocks? The reason why I was confused was that the equation in the diagram explaining the residual blocks on the research paper was f(x) + x. So I thought, “Where is the residual..?” When…
Highway Networks Training models with DEEP networks becomes difficult, even when using variance-preserving initialization. By adding an information highway (Learning how to route information through the network), it makes it easier to train models even when it is really DEEP.…