skflow.TensorFlowDNNRegressor parameters

Question

I am new to skflow. With the following example code, I am able to initialize a neural network estimator.

regressor = skflow.TensorFlowDNNRegressor(
     hidden_units=[10, 10],
     steps=5000,
     learning_rate=0.1,
     batch_size=1)

I would like to know if these are the only input parameters for TensorFlowDNNRegressor or are there more parameters, which I can change? Could anyone please let me know where I can find this list of parameters? I am not able to find any documentation for it.

@YuanTang Thanks for the update. Looking forward for the documentation. — Sundaravelpandian Singaravel, May 19 '16 at 22:04

score 3 · Accepted Answer · answered May 19 '16 at 10:14

I found the documentation of this function here. (not very clean format yet).

Here are the different parameters of the class:

skflow.TensorFlowDNNRegressor.__init__(
     hidden_units,
     n_classes=0,
     tf_master='',
     batch_size=32,
     steps=200,
     optimizer='SGD',
     learning_rate=0.1,
     tf_random_seed=42,
     continue_training=False,
     config_addon=None,
     verbose=1,
     max_to_keep=5,
     keep_checkpoint_every_n_hours=10000)

@Oliver Moindrot: Thanks for this link. – Sundaravelpandian Singaravel May 19 '16 at 13:40 — Sundaravelpandian Singaravel, May 19 '16 at 13:40

skflow.TensorFlowDNNRegressor parameters

1 Answers1