Object-Detection: 40 FPS on Jetson Nano with TensorRT.
The Jetson Nano is low powered but equipped with an NVIDIA GPU. NVIDIA TensorRT can be used to optimize neural networks for the GPU achieving enough performa...
Posts
2021
CNN Saliency with Grad-CAM
Gradient-weighted Class Activation Mapping (Grad-CAM) is a technique for making Convolutional Neural Network (CNN)-based models explainable by visualizing th...
Cancer CNN Validation and Analysis
In this post we compare the performance of the CNN cancer detection models that we trained previously. The results show that the performance of our custom mo...
Cancer CNN Training Walkthrough
In previous posts we have reviewed the development of CNN architectures over the last decade and even defined our own custom architecture. In this post we tr...
Custom Cancer Detection CNN
Medical Imaging is one of the major applications of ML and the clinically-relevant task of metastatic breast cancer detection can be framed as a straight-for...
Data Augmentation with Keras
In Medical Imaging large datasets are typically not available due to low incidence of conditions and performance of deep learning based algorithms is comprom...
CNN Architectures: An Overview
Convolutional Neural Networks (CNN) are now ubiquitous in computer vision. After foundational work in the late 1990’s the last decade saw an explosion in the...
ROS2: Convert sensor data to rosbag
In a previous post we learned what rosbags are and how to use them to playback KITTI data. In this prequel-post we will show how to create the rosbag. The so...
ROS2: Playback sensor data with rosbag
The KITTI Vision Suite benchmark was introduced in the previous post. In this post we are going to convert to “rosbags”, a format that is designed for develo...
Introducing the KITTI dataset
The KITTI Vision Suite benchmark is a dataset for autonomous vehicle research consisting of 6 hours of multi-modal data recorded at 10-100 Hz. It is widely u...