✅ Subscribe: [ Ссылка ]
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 - [ Ссылка ]
Public datasets - [ Ссылка ]
Colab notebook - [ Ссылка ]
Blog post - [ Ссылка ]
Create Labeled Data
CVAT - [ Ссылка ]
Follow us on Twitter: [ Ссылка ]
Ещё видео!