通过如下几个操作，可以大概看出tflearn.models.dnn.DNN与tflearn.DNN的关系：
print(help(tflearn.models.dnn.DNN))
print(help(tflearn.DNN))
从返回可以看出，tflearn.models.dnn.DNN与tflearn.DNN是一样的：
class DNN(builtins.object)
| Deep Neural Network Model.深度神经网络模型
|
| Arguments:
| network: `Tensor`. Neural network to be used.
| tensorboard_verbose: `int`. Summary verbose（冗余的） level, it accepts different levels of tensorboard logs
| tensorboard_dir: `str`. Directory to store tensorboard logs.
| checkpoint_path: `str`. Path to store model checkpoints. If None, no model checkpoint will be saved. Default: None.
| best_checkpoint_path: `str`. Path to store the model when the validation rate reaches its
| highest point of the current training session and also is above best_val_accuracy. Default: None.
| max_checkpoints: `int` or None. Maximum amount of checkpoints. If None, no limit. Default: None.
| session: `Session`. A session for running ops. If None, a new one will
| be created. Note: When providing a session, variables must have been
| initialized already, otherwise an error will be raised.
| best_val_accuracy: `float` The minimum validation accuracy that needs to be
| achieved before a model weight's are saved to the best_checkpoint_path. This
| allows the user to skip early saves and also set a minimum save point when continuing
| to train a reloaded model. Default: 0.0.
|
| Attributes:
| trainer: `Trainer`. Handle model training.
| predictor: `Predictor`. Handle model prediction.
| session: `Session`. The current model session.
|
| Methods defined here:
|
| __init__(self, network, clip_gradients=5.0, tensorboard_verbose=0, tensorboard_dir='/tmp/tflearn_logs/', checkpoint_path=None, best_checkpoint_path=None, max_checkpoints=None, session=None, best_val_accuracy=0.0)
| Initialize self. See help(type(self)) for accurate signature.
|
| evaluate(self, X, Y, batch_size=128)
| Evaluate.
|
| Evaluate model metric(s) on given samples.
|
| Arguments:
| X: array, `list` of array (if multiple inputs) or `dict`
| (with inputs layer name as keys). Data to feed to train
| model.
| Y: array, `list` of array (if multiple inputs) or `dict`
| (with estimators layer name as keys). Targets (Labels) to
| feed to train model. Usually set as the next element of a
| sequence, i.e. for x[0] => y[0] = x[1].
| batch_size: `int`. The batch size. Default: 128.
|
| Returns:
| The metric(s) score.
|
| fit(self, X_inputs, Y_targets, n_epoch=10, validation_set=None, show_metric=False, batch_size=None, shuffle=None, snapshot_epoch=True, snapshot_step=None, excl_trainops=None, validation_batch_size=None, run_id=None, callbacks=[])
| Fit.
|
| Train model, feeding X_inputs and Y_targets to the network.
|
| NOTE: When not feeding dicts, data assignations is made by
| input/estimator layers creation order (For example, the second
| input layer created will be feeded by the second value of
| X_inputs list).
|
| Examples:
| ```python
| model.fit(X, Y) # Single input and output
| model.fit({'input1': X}, {'output1': Y}) # Single input and output
| model.fit([X1, X2], Y) # Mutliple inputs, Single output
|
| # validate with X_val and [Y1_val, Y2_val]
| model.fit(X, [Y1, Y2], validation_set=(X_val, [Y1_val, Y2_val]))
| # 10% of training data used for validation
| model.fit(X, Y, validation_set=0.1)
| ```
|
| Arguments:
| X_inputs: array, `list` of array (if multiple inputs) or `dict`
| (with inputs layer name as keys). Data to feed to train
| model.
| Y_targets: array, `list` of array (if multiple inputs) or `dict`
| (with estimators layer name as keys). Targets (Labels) to
| feed to train model.
| n_epoch: `int`. Number of epoch to run. Default: None.
| validation_set: `tuple`. Represents data used for validation.
| `tuple` holds data and targets (provided as same type as
| X_inputs and Y_targets). Additionally, it also accepts
| `float` (<1) to performs a data split over training data.
| show_metric: `bool`. Display or not accuracy at every step.
| batch_size: `int` or None. If `int`, overrides all network
| estimators 'batch_size' by this value. Also overrides
| `validation_batch_size` if `int`, and if `validation_batch_size`
| is None.
| validation_batch_size: `int` or None. If `int`, overrides all network
| estimators 'validation_batch_size' by this value.
| shuffle: `bool` or None. If `bool`, overrides all network
| estimators 'shuffle' by this value.
| snapshot_epoch: `bool`. If True, it will snapshot model at the end
| of every epoch. (Snapshot a model will evaluate this model
| on validation set, as well as create a checkpoint if
| 'checkpoint_path' specified).
| snapshot_step: `int` or None. If `int`, it will snapshot model
| every 'snapshot_step' steps.
| excl_trainops: `list` of `TrainOp`. A list of train ops to
| exclude from training process (TrainOps can be retrieve
| through `tf.get_collection_ref(tf.GraphKeys.TRAIN_OPS)`).
| run_id: `str`. Give a name for this run. (Useful for Tensorboard).
| callbacks: `Callback` or `list`. Custom callbacks to use in the
| training life cycle
|
| fit_batch(self, X_inputs, Y_targets)
|
| get_train_vars(self)
|
| get_weights(self, weight_tensor)
| Get Weights.
|
| Get a variable weights.
|
| Examples:
| ```
| dnn = DNNTrainer(...)
| w = dnn.get_weights(denselayer.W) # get a dense layer weights
| w = dnn.get_weights(convlayer.b) # get a conv layer biases
| ```
|
| Arguments:
| weight_tensor: `Tensor`. A Variable.
|
| Returns:
| `np.array`. The provided variable weights.
|
| load(self, model_file, weights_only=False, **optargs)
| Load.
|
| Restore model weights.
|
| Arguments:
| model_file: `str`. Model path.
| weights_only: `bool`. If True, only weights will be restored (
| and not intermediate variable, such as step counter, moving
| averages...). Note that if you are using batch normalization,
| averages will not be restored as well.
| optargs: optional extra arguments for trainer.restore (see helpers/trainer.py)
| These optional arguments may be used to limit the scope of
| variables restored, and to control whether a new session is
| created for the restored variables.
|
| predict(self, X)
| Predict.
|
| Model prediction for given input data.
|
| Arguments:
| X: array, `list` of array (if multiple inputs) or `dict`
| (with inputs layer name as keys). Data to feed for prediction.
|
| Returns:
| array or `list` of array. The predicted probabilities.
|
| predict_label(self, X)
| Predict Label.
|
| Predict class labels for input X.
|
| Arguments:
| X: array, `list` of array (if multiple inputs) or `dict`
| (with inputs layer name as keys). Data to feed for prediction.
|
| Returns:
| array or `list` of array. The predicted classes index array, sorted
| by descendant probability value.
|
| save(self, model_file)
| Save.
|
| Save model weights.
|
| Arguments:
| model_file: `str`. Model path.
|
| set_weights(self, tensor, weights)
| Set Weights.
|
| Assign a tensor variable a given value.
|
| Arguments:
| tensor: `Tensor`. The tensor variable to assign value.
| weights: The value to be assigned.
|
| ----------------------------------------------------------------------
| Data descriptors defined here:
|
| __dict__
| dictionary for instance variables (if defined)
|
| __weakref__
| list of weak references to the object (if defined)
NAME
tflearn.models
PACKAGE CONTENTS
dnn
generator
DATA
absolute_import = _Feature((2, 5, 0, 'alpha', 1), (3, 0, 0, 'alpha', 0...
有点困惑，既然两种方法最后得到的类是同样的，为什么还要有两种表述？
