tflearn.helpers.evaluator.Evaluator (tensors, model=None, session=None)
A class used for performing predictions and evaluate a model performance.
- tensors: list of
Tensor. A list of tensors to perform predictions.
str. The model weights path (Optional).
Session. The session to run the prediction (Optional).
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...)
dict. The feed dictionary of data.
- ops: list of
Tensors. The tensors to evaluate.
int. A batch size.
The mean average result per tensor over all batches.
Run data through the provided network and return the result value.
dict. Feed data dictionary, with placeholders as keys, and data as values.
array. In case of multiple tensors to predict, each tensor's
prediction result is concatenated.