Evaluator

tflearn.helpers.evaluator.Evaluator (tensors, model=None, session=None)

A class used for performing predictions and evaluate a model performance.

Arguments

  • tensors: list of Tensor. A list of tensors to perform predictions.
  • model: str. The model weights path (Optional).
  • session: Session. The session to run the prediction (Optional).

Methods

evaluate (feed_dict, ops, batch_size=128)

Evaluate a list of tensors over a whole dataset. Generally, 'ops' argument are average performance metrics (such as average mean, top-3, etc...)

Arguments
  • feed_dict: dict. The feed dictionary of data.
  • ops: list of Tensors. The tensors to evaluate.
  • batch_size: int. A batch size.
Returns

The mean average result per tensor over all batches.

predict (feed_dict)

Run data through the provided network and return the result value.

Arguments
  • feed_dict: dict. Feed data dictionary, with placeholders as keys, and data as values.
Returns

An array. In case of multiple tensors to predict, each tensor's prediction result is concatenated.