Image Classification with W&B Tables

This is a walkthrough of Tables for visualization and Artifacts for versioning deep learning models in Weights & Biases. As an example, I finetune a convnet in Keras on photos from iNaturalist 2017 to identify 10 classes of living things (plants, insects, birds, etc).

Explore more examples in this W&B Report

Sign up or login

Sign up or login to W&B to see and interact with your experiments in the browser.

In this example we're using Google Colab as a convenient hosted environment, but you can run your own training scripts from anywhere and visualize metrics with W&B's experiment tracking tool.

Download sample data: Choose 1 of 4 sizes

Choose one of the three dataset size options below to run the rest of the demo. With fewer images, you'll run through the demo much faster and use less storage space. With more images, you'll get more realistic model training and more interesting results and examples to explore.

Note: for the largest dataset, this stage might take a few minutes. If you end up needing to rerun a cell, comment out the first capture line (change %%capture to #%%capture ) so you can respond to the prompt about re-downloading the dataset (and see the progress bar).

Each zipped directory contains randomly sampled images from the iNaturalist dataset, evenly distributed across 10 classes of living things like birds, insects, plants, and mammals (names given in Latin—so Aves, Insecta, Plantae, etc :).

Step 0: Setup

Start out by installing the experiment tracking library and setting up your free W&B account:

• pip install wandb – Install the W&B library
• import wandb – Import the wandb library
• wandb login – Login to your W&B account so you can log all your metrics in one place

Step 1: Upload raw data

Step 2: Split raw data to prepare for training

Step 3: Train with artifacts and save model

Step 4: Load model for inference

More about Weights & Biases

We're always free for academics and open source projects. Email carey@wandb.com with any questions or feature suggestions. Here are some more resources:

1. Documentation - Python docs
2. Gallery - example reports in W&B
3. Articles - blog posts and tutorials
4. Community - join our Slack community forum