3

TensorFlow Hub is a repository for pre-trained models. Model Garden (Model Zoo) also keeps SOTA models and provides facilities for downloading and leveraging its models like TfHub, and both of them are created by TensorFlow.

Why did Tensorflow make two concepts for a model repository?

When should we use TfHub for retrieving a well-known model, and when should we use Model Garden to download a model? What is the difference between them?

Kaveh
  • 4,618
  • 2
  • 20
  • 33
  • 5
    We mostly expect users of TF Hub to treat models as blackboxes with clearly defined inputs and outputs. If a model meets your needs (eg. accuracy, speed, size, pre-training category), then use it! If you instead want to dig into the internal details of a model's structure, then you may be more interested in code-first resources, such as Model Garden or Keras applications. These often come with pre-trained checkpoints that can be loaded with the provided code. –  Jun 04 '21 at 04:18

1 Answers1

4

TF Hub provides trained models in SavedModel, TFLite, or TF.js format. These artifacts can be used for inference and some can be used in code for fine-tuning. TF Hub does not provide modeling library code to train your own models from scratch.

Model Garden is a modeling library for training BERT, image classification models, and more. Model Garden provides code for training your own models from scratch as well as some checkpoints to start from.

kempy
  • 606
  • 3
  • 8