In our recent post about receptive field computation, we examined the concept of receptive fields using PyTorch. We learned receptive field is the proper tool to understand what the network 'sees' ...
Latest From the Blog
CNN Fully Convolutional Image Classification (FCN CNN) with TensorFlow –
In a previous post, we covered the concept of fully convolutional neural networks (FCN) in PyTorch, where we showed how we could solve the classification task using the input image of arbitrary ...
Build and Install OpenCV 4 for Raspberry Pi
Raspberry Pi is a small ARM computer with a camera, a network controller, and Linux on board. That makes it a good choice for DIY computer vision projects. In this post, we will learn how to build ...
How to Convert a Model from PyTorch to TensorRT and Speed Up Inference
The life of a machine learning engineer consists of long stretches of frustration and a few moments of joy! First, struggle to get your model to produce good results on your training data. You ...
Efficient image loading
When it comes to writing optimized code, image loading plays an important role in computer vision. This process can be a bottleneck in many CV tasks and it can often be the culprit behind bad ...
Zero-shot Learning : An Introduction
Deep learning based models have achieved the state of the art performance for image recognition and object detection tasks in the recent past. Many of these models are able to achieve human level ...
