import { Pool2DLayer } from "https://deno.land/x/netsaur@0.4.2/mod.ts";
Creates a pooling layer. Pooling layers are used for downsampling. See https://en.wikipedia.org/wiki/Convolutional_neural_network#Pooling_layer
Module
Powerful Powerful Machine Learning library with GPU, CPU and WASM backends
Latest
benchcratesexamplespackagesSequentialTensorAdamOptimizerConfigBackendDataSetDecaySchedulerConfigNetworkConfigNeuralNetworkOneCycleSchedulerConfigRMSPropOptimizerConfigTensorLikeArray1DArray2DArray3DArray4DArray5DArray6DArrayMapOptimizerPaddingSchedulerShapeShape1DShape2DShape3DShape4DShape5DShape6DAUTOCPUGPUWASMAdamOptimizerAveragePool2DLayerBatchNorm1DLayerBatchNorm2DLayerConv1DLayerConv2DLayerConvTranspose1DLayerConvTranspose2DLayerDenseLayerDropout1DLayerDropout2DLayerEluLayerEmbeddingLayerExponentialDecayFlattenLayerGeluLayerLeakyReluLayerLinearDecayLSTMLayerMaxPool2DLayerNadamOptimizerNoSchedulerOneCycleOPTIONPool2DLayerRelu6LayerReluLayerRMSPropOptimizerSeluLayersetupBackendSGDOptimizerSigmoidLayerSoftmaxLayerTanhLayertensortensor1Dtensor2Dtensor3Dtensor4Dtensor5Dtensor6DActivationBackendTypeCostInitLayerTypeOptimizerTypeRankSchedulerTypeSequentialTensorAdamOptimizerConfigBackendDataSetNetworkConfigNeuralNetworkRMSPropOptimizerConfigTensorLikeArray1DArray2DArray3DArray4DArray5DArray6DArrayMapOptimizerPaddingShapeShape1DShape2DShape3DShape4DShape5DShape6DWASMAdamOptimizerAveragePool2DLayerBatchNorm1DLayerBatchNorm2DLayerConv1DLayerConv2DLayerConvTranspose1DLayerConvTranspose2DLayerDenseLayerDropout1DLayerDropout2DLayerEluLayerEmbeddingLayerFlattenLayerGeluLayerLeakyReluLayerLSTMLayerMaxPool2DLayerNadamOptimizerPool2DLayerRelu6LayerReluLayerRMSPropOptimizerSeluLayersetupBackendSGDOptimizerSigmoidLayerSoftmaxLayerTanhLayertensortensor1Dtensor2Dtensor3Dtensor4Dtensor5Dtensor6DActivationBackendTypeCostInitLayerTypeOptimizerTypeRankSchedulerType
mod.ts (default module)
c
c
I
I
I
I
I
I
I
I
I
T
T
T
T
T
T
T
T
T
T
T
T
T
T
T
T
T
v
v
v
v
f
f
f
f
f
f
f
f
f
f
f
f
f
f
f
f
f
f
f
f
f
f
f
f
f
f
f
f
f
f
f
f
f
f
f
f
f
f
f
f
f
E
E
E
E
E
E
E
E
web.ts
c
c
I
I
I
I
I
I
I
T
T
T
T
T
T
T
T
T
T
T
T
T
T
T
T
v
f
f
f
f
f
f
f
f
f
f
f
f
f
f
f
f
f
f
f
f
f
f
f
f
f
f
f
f
f
f
f
f
f
f
f
f
E
E
E
E
E
E
E
E