We need "Agile" in machine learning

It’s time for a non-linear, iterative approach that builds highly performant vision AI applications.

Attribute Prediction

Sample inference script for torchscript exported image-tagger. The following sample code should be run from the export directory: import torch import …

Challenges of Deployment

A few of the challenges most teams usually run into during the deployment stage: 1. Differences in programming languages The machine learning model …

Classification

Sample inference script for exported torchscript image classifier The following sample code should be run from the export directory: import torch …

Commonly used web frameworks

Flask is an open-source lightweight web framework built in Python to deploy web applications. To begin using Flask, we must first install it on our …

Containerized Deployment

Previously explained frameworks should be running well on your machine, but you might run into issues when you try to deploy to another environment …

Deploy

Deploy dashboard The Deploy option in the Deploy & export page allows you to choose a model from the available experiments to choose as the …

Image-Tagging

Sample inference script for torchscript exported image-tagger. The following script should be run from the model export directory: import torch …

Instance Segmentation

Sample inference script for torchscript exported instance segmentation model Mask RCNN code example import torch import numpy as np from PIL import …

Machine learning IRL

Everyone is talking about applying ML to real-world use cases, but there’s very little sharing between teams actually doing the implementation. We …

Object Detection

Inference sample for exported torchscript object detector model. Mask RCNN code example import torch import numpy as np from PIL import Image import …

Orchestrated Deployment

If you want to run multiple models with different logics at once, it makes sense to use an orchestrated container platform like Kubernetes. It allows …