Starting your first bounding box object detection project on Roboflow.

Dataset Upload --> Dataset Generation & Model Training with Roboflow Train. Plus: Quick insight into Dataset Health Check, selecting preprocessing & augmentation steps, and exporting in different annotation formats.

Timestamps:

0:00 - Creating Your Project

0:40 - What are annotation batches? Uploading images (working with annotation batches, and our annotation workflow) https://blog.roboflow.com/annotation-workflow/

1:00 - Getting Images from Roboflow Universe to add to a project

1:58 - Uploading images to your annotation batch (fresh unannotated images, already annotated images, video files)

5:00 - Using the annotation tool

7:00 - Completing an annotation batch, and generating versions of your dataset for model training

8:10 - Uploading the images from Roboflow Universe to the project

10:35 - More on navigating annotation batches, and uploading new images

12:05 - Generating versions: quick primer on preprocessing and augmentation -- for more: https://roboflow.slab.com/posts/roboflow-preprocessing-and-augmentation-v57xsmv5

14:22 - Primer on Dataset Health Check -- insights into your dataset like: total number of annotations, heatmap of annotations, average image sizes, number of labels for each class (class balance)

15:55 - Training your model

16:20 - Using Label Assist

18:51 - Training a custom model (https://models.roboflow.com)

21:00 - Roboflow Train results: model inference/deployment options and running tests https://docs.roboflow.com/inference