TensorFlow 对象检测 API 微调检查点

Question

我正在尝试从头开始训练模型，在这种情况下，我应该在 Protobuf 文件中放入 Fine_tune_checkpoint 值。

Answer 1

Nothing. It should initialize your entire model.

If for some reason that doesn't work for you, you can give it a checkpoint of something else entirely. The API builds the graph of the model, and compares between its variables to the variables in the checkpoint (both names and shapes), and every variable it doesn't find - it initializes.