Try the Model

Use the widget below to experiment with ResNet 34. You can detect COCO classes such as people, vehicles, animals, household items.

Overview

What is Resnet34?

Resnet34 is a state-of-the-art image classification model, structured as a 34 layer convolutional neural network and defined in "Deep Residual Learning for Image Recognition". Restnet34 is pre-trained on the ImageNet dataset which contains 100,000+ images across 200 different classes.

However, RestNet is different from traditional neural networks in the sense that it takes residuals from each layer and uses them in the subsequent connected layers (similar to residual neural networks used for text prediction).

Restnet34 Architecture

Below. on the right-hand side, is Resnet34's architecture where the 34 layers and the residuals from one layer to another are visualized.

Learn More

Learn how to use Resnet34 Custom Resnet34 Model for Image Classification using fastai and PyTorch: https://blog.roboflow.com/custom-resnet34-classification-model/

‍

ResNet 34 License

ResNet 34

is licensed under a

license.

Performance

Deploy a ResNet 34 API

You can use Roboflow Inference to deploy a

ResNet 34

API on your hardware. You can deploy the model on CPU (i.e. Raspberry Pi, AI PCs) and GPU devices (i.e. NVIDIA Jetson, NVIDIA T4).

Below are instructions on how to deploy your own model API.

Label Data Automatically with ResNet 34

You can automatically label a dataset using ResNet 34 with help from Autodistill, an open source package for training computer vision models. You can label a folder of images automatically with only a few lines of code. Below, see our tutorials that demonstrate how to use ResNet 34 to train a computer vision model.

No items found.