• 5 min read
How to Try CLIP: OpenAI's Zero-Shot Image Classifier
Earlier this week, OpenAI dropped a bomb on the computer vision world.
• 9 min read
How to Detect, Track, and Identify Basketball Players with Computer Vision
Build a computer vision pipeline that detects, tracks, and identifies NBA players during a game. Using models like RF-DETR, SAM2, SigLIP, SmolVLM2, and ResNet, the system handles motion blur, occlusion, and uniform similarity to reliably map jersey numbers to player identities.
• 6 min read
How to Train a ResNet-34 Model on a Custom Dataset
Learn how to train a ResNet-34 model for image classification using a custom dataset.
• 5 min read
How to Train a ResNet-18 Model with a Custom Dataset
Learn how to train a ResNet-18 classification model with a custom dataset.
• 6 min read
How to Train and Deploy a ResNet-50 Model
Learn how to train a ResNet-50 model for image classification.
• 6 min read
How to Train and Deploy a Vision Transformer (ViT) Classification Model
Learn how to train a Vision Transformer (ViT) classification model using Roboflow.
• 4 min read
How to use MobileNetV4 for Classification
Learn how to use the MobileNetV4 architecture to classify images using pre-trained model weights.
• 8 min read
What is Scene Classification? An Introduction.
In this guide, learn what scene classification is and how to classify scenes with computer vision.
• 4 min read
Use an Image Classification API to Classify Images
Learn how to use the CLIP-powered Roboflow image classification API to assign labels to images.
• 6 min read
What is Zero-Shot Classification?
Learn what zero-shot classification is, what zero-shot classification is used for, and how to use zero-shot classification to solve computer vision problems.
• 4 min read
Distilling GPT-4 for Classification with an API
In this guide, learn how to distill GPT-4V to train an image classification model.
• 5 min read
How CLIP and GPT-4V Compare for Classification
In this post, we analyze how CLIP and GPT-4V compare for classification.
• 5 min read
How to Classify Images with DINOv2
In this guide, we walk through how to classify images using DINOv2 and a dataset from Roboflow Universe.
• 7 min read
Use Resnet34 for Image Classification
SUMMARY
This tutorial walks through training a custom image classification model on the ResNet34 backbone using the fastai library and PyTorch, starting from an ImageNet pretrained checkpoint and fine-tuning it on a new dataset via transfer learning. The post uses a public flower classification dataset as a worked example,
Stay Connected