Build models that recognize objects in images.
What it does
Guides implementation of vision models for classifying images, detecting objects, segmenting images, and estimating poses.
When to use it
Use for image classification, object detection, segmentation, pose estimation, face recognition, or medical imaging analysis.
How to use it
Give it a computer vision task in your project; it produces a model, inference pipeline, evaluation, visualizations, and deployment guidance.
What you provide
- An existing project
Uses
What you need · 8
The implementation is written in Python; no runtime version is specified.
The implementation imports torch and uses its neural-network layers to define vision models.
The implementation imports torchvision for image transforms, pretrained models, and datasets.
Access · 1
This skill
ResNet18
Loads pretrained ResNet18 weights