> For AI agents: guidance on navigating Viam documentation is available at https://docs.viam.com/llms.txt. # Phase 3: Train a starter and capture more Start a built-in training job on the starter dataset, then capture about 70 more images into the training dataset while it runs. > Source: https://docs.viam.com/tutorials/dice-vision/train-a-starter-model/ At the end of this phase, a starter model is training in the cloud and a dataset named `dice-train` holds about 70 new, unlabeled images. The starter model won't be very good, since it learns from only 30 images. That's fine, because its only job is to give you a head start on labeling. In [Phase 4](/tutorials/dice-vision/auto-label-the-training-set/) it draws a first guess at every box in the 70 new images, and you fix its mistakes, which is much faster than drawing all of those boxes by hand. ## Start the starter training job {#start-the-starter-training-job} 1. On the **DATASETS** page, open `dice-starter`. 1. Click **Train model**. 1. Select **TFLite** as the framework. 1. Name the model `dice-starter-model`. 1. Select **Object Detection** as the task type. 1. Select all six labels, `1` through `6`. 1. Click **Train model**. > **Checkpoint:** > > On the **DATA** tab, click **MODELS** and expand **Active Training**. > The `dice-starter-model` job shows **Preparing**, **Waiting for GPU** or **Training**. > If the job fails to start with a message about too few annotations, a label has fewer than 10 boxes; add and label more images for it, as in [Phase 2](/tutorials/dice-vision/label-the-starter-set/#check-the-label-counts). The job runs in the cloud, so you don't need to wait for it. A small job like this one usually finishes within 20 minutes, but it can take longer when cloud compute is busy. Keep going with the next section. ## Capture the rest of the training set {#capture-the-rest-of-the-training-set} Thirty images are enough for a rough starter model, but not for a model you can rely on. The models you train in Phases 5 and 6 learn from a training set of about 100 images: the 30 starter images plus about 70 new ones. You capture the new images now, while the starter model trains, and leave them unlabeled; in [Phase 4](/tutorials/dice-vision/auto-label-the-training-set/) the starter model labels them for you, and then you add the 30 starter images. They go in a new dataset, `dice-train`, so `dice-starter` stays fully labeled. 1. On the **DATA** tab, click **DATASETS**, then click **Create dataset**. 1. Name it `dice-train`, leave **Data type** set to **Binary Data**, and click **Create dataset**. 1. On the **CONFIGURE** tab, open the **Test** section of the `camera` card. 1. Roll, click **Add to dataset**, select `dice-train`, and confirm. 1. Repeat until you've added about 70 images. Vary the rolls as you did in [Phase 1](/tutorials/dice-vision/capture-a-starter-set/): one to five dice, different positions, some touching. Keep the camera at the same height and angle. Other conditions, such as a different height or dim light, are for the hard test dataset in [Phase 7](/tutorials/dice-vision/build-the-test-datasets/), where they show how well each model handles scenes it hasn't seen. > **Checkpoint:** > > `dice-train` on the **DATASETS** page shows about 70 images. > If the count is lower, check that you selected `dice-train`, not `dice-starter`, each time. > If an image shows no dice or a blurry roll, remove it from the dataset. ## Troubleshooting {#troubleshooting} **The training job shows Failed** On the **DATA** tab, click **MODELS**, expand **Active Training**, click the job, and read its logs. The most common cause is a label with fewer than 10 boxes. See [Train a model](/train/train-a-model/#troubleshooting) for other causes. In the next phase, once the starter model finishes training, you use it to label the 70 new images.