✅ Subscribe: https://bit.ly/rf-yt-sub
We train an EfficientDet model in TensorFlow 2 to detect custom objects (blood cells), including setting up a TensorFlow 2 training environment, loading and converting our dataset to create TFRecord files, and configuring our EffecientDet-b0 training job. Finally, we use our newly minted custom detector to infer on test images that it has never seen.

Tools:
Roboflow – https://roboflow.com
Public datasets – https://public.roboflow.com
Colab notebook – https://colab.research.google.com/drive/1sLqFKVV94wm-lglFq_0kGo2ciM0kecWD
Blog post – https://blog.roboflow.com/train-a-tensorflow2-object-detection-model/

Create Labeled Data
CVAT – https://blog.roboflow.com/getting-started-with-cvat/

Follow us on Twitter: https://twitter.com/roboflowAI

source