Binary Cross Entropy Explained

Posted 2021-02-22 • Last updated 2021-10-21

A simple NumPy implementation of the binary cross entropy loss function and some intuition about why it works.

numpy meshgrid loss surface

NumPy Meshgrid: Understanding np.meshgrid()

Posted 2021-02-09 • Last updated 2021-10-21

You can create multi-dimensional coordinate arrays using the np.meshgrid() function, which is also available in PyTorch and TensorFlow. But watch out! PyTorch uses different indexing by default so the results might not be the same.

sagemaker studio launcher

SageMaker Studio Quick Start

Posted 2021-02-08 • Last updated 2021-10-21

A step-by-step quick start guide for SageMaker Studio. Start a Studio session, launch a notebook on a GPU instance and run object detection inference with a detectron2 pre-trained model.

PyTorch One Hot Encoding

Posted 2021-02-02 • Last updated 2021-10-14

PyTorch has a one_hot() function for converting class indices to one-hot encoded targets.

numpy pad reflection

Numpy Pad: Understanding np.pad()

Posted 2021-01-30 • Last updated 2021-10-21

The np.pad() function has a complex, powerful API. But basic usage is very simple and complex usage is achievable! This post shows you how to use NumPy pad and gives a couple examples.

The PyTorch Softmax Function

Posted 2021-01-29 • Last updated 2021-10-14

You can use the top-level torch.softmax() function from PyTorch for your softmax activation needs.



ben [at] sparrow [dot] dev

Email List