官术网_书友最值得收藏!

TFLearn estimator layers

TFLearn offers only one layer in the tflearn.layers.estimator module:

While creating the regression layer, you can specify the optimizer and the loss and metric functions.

TFLearn offers the following optimizer functions as classes in the tflearn.optimizers module:

  • SGD
  • RMSprop
  • Adam
  • Momentum
  • AdaGrad
  • Ftrl
  • AdaDelta
  • ProximalAdaGrad
  • Nesterov

You can create custom optimizers by extending the tflearn.optimizers.Optimizer base class.

TFLearn offers the following metric functions as classes or ops in the tflearn.metrics module:

  • Accuracy or  accuracy_op
  • Top_k or top_k_op
  • R2 or r2_op
  • WeightedR2  or weighted_r2_op
  • binary_accuracy_op

You can create custom metrics by extending the tflearn.metrics.Metric base class.

TFLearn provides the following loss functions, known as objectives, in the tflearn.objectives module:

  • softymax_categorical_crossentropy
  • categorical_crossentropy
  • binary_crossentropy
  • weighted_crossentropy
  • mean_square
  • hinge_loss
  • roc_auc_score
  • weak_cross_entropy_2d

While specifying the input, hidden, and output layers, you can specify the activation functions to be applied to the output. TFLearn provides the following activation functions in the tflearn.activations module:

  • linear
  • tanh
  • sigmoid
  • softmax
  • softplus
  • softsign
  • relu
  • relu6
  • leaky_relu
  • prelu
  • elu
  • crelu
  • selu
主站蜘蛛池模板: 百色市| 天门市| 延津县| 镇雄县| 灵寿县| 郑州市| 库车县| 昌图县| 永吉县| 开平市| 合江县| 拉萨市| 合作市| 陇川县| 中江县| 左云县| 佛冈县| 金平| 宁城县| 古交市| 吉首市| 江达县| 桃园县| 高雄县| 滨海县| 青田县| 鄂尔多斯市| 筠连县| 镇远县| 全南县| 三门县| 渭南市| 绿春县| 丁青县| 浠水县| 凤山县| 卢湾区| 紫金县| 道真| 斗六市| 永修县|