摘要:
目录 Outline Auto-Encoder 创建编解码器 训练 Outline Auto-Encoder Variational Auto-Encoders Auto-Encoder 创建编解码器 import os import tensorflow as tf import numpy as 阅读全文
摘要:
目录AE v.s. VAEGenerative modelVAE v.s. GAN AE v.s. VAE Generative model VAE v.s. GAN 阅读全文
摘要:
目录Sample() is not differentiableReparameterization trickToo Complex Sample() is not differentiable 现在我们得到的不是一个向量,得到的是一个分布,而分布是无法使用梯度下降的 Reparameteriza 阅读全文
摘要:
目录Another Approach: q(z)->p(z)Intuitively comprehend KL(p|q)Minimize KL DivergenceHow to compute KL between q(z) and p(z) Distribution of hidden code 阅读全文
摘要:
目录PCA V.S. Auto-EncodersDenoising AutoEncodersDropout AutoEncoders PCA V.S. Auto-Encoders deep autoencoder由深度神经网络构成,因此降维效果丢失数据少 左pca;右auto-encoder Den 阅读全文
摘要:
目录Auto-EncodersHow to Train? Auto-Encoders How to Train? 阅读全文
摘要:
目录Supervised LearningMassive Unlabeled dataUnsupervised LearningWhy needed Supervised Learning Massive Unlabeled data Unsupervised Learning Why needed 阅读全文
摘要:
目录 Sentiment Analysis Two approaches Single layer Multi-layers Sentiment Analysis Two approaches SimpleRNNCell single layer multi-layers RNNCell Singl 阅读全文
摘要:
目录Recapinput dim, hidden dimSimpleRNNCellSingle layer RNN CellMulti-Layers RNNRNN Layer Recap input dim, hidden dim from tensorflow.keras import layer 阅读全文
摘要:
目录RecapSentiment AnalysisProposalS1.Weight sharingNaive versionWeight shareS2.Consistent memoryUnfolded modelFormulationOverall DiagramOne more thingH 阅读全文
摘要:
目录 Res Block ResNet18 Out of memory # Resnet.py #!/usr/bin/env python # -*- coding:utf-8 -*- import tensorflow as tf from tensorflow import keras from 阅读全文
摘要:
目录 Res Block ResNet18 Out of memory # Resnet.py #!/usr/bin/env python # -*- coding:utf-8 -*- import tensorflow as tf from tensorflow import keras from 阅读全文
摘要:
目录ResNetBOOMWhy call Residual?发展史Basic BlockRes BlockResNet-18DenseNet ResNet 确保20层能训练好的前提下,增加8层;然后确保28层能训练好的前提下,继续堆叠8层…… BOOM Why call Residual? 发展史 阅读全文
摘要:
目录ImageNetLeNet-5LeNet-5 DemoAlexNetVGG1*1 ConvolutionGoogLeNetStack more layers? ImageNet LeNet-5 LeNet-5 Demo AlexNet VGG 1*1 Convolution GoogLeNet 阅读全文
摘要:
目录CIFAR10013 Layerscafar100_train CIFAR100 13 Layers cafar100_train import tensorflow as tf from tensorflow.keras import layers, optimizers, datasets, 阅读全文
摘要:
目录OutlineReduce DimsubsampleMax/Avg poolingStridesFor instanceupsampleUpSampling2DReLu Outline Pooling upsample ReLU Reduce Dim subsample Max/Avg pool 阅读全文
摘要:
目录2D ConvolutionKernel sizePadding & StrideChannelsFor instanceLeNet-5Pyramid Architecturelayers.Conv2Dweight & biasnn.conv2dGradient?For instance 2D 阅读全文
摘要:
目录Feature mapsWhy not Linear335k or 1.3MBem...Receptive FieldFully connnectedPartial connectedLocally connectedRethink Linear layerFully VS LovallyWei 阅读全文
摘要:
详情查看:https://www.zhihu.com/question/32246256 阅读全文
摘要:
目录 CIFAR10 MyDenseLayer CIFAR10 MyDenseLayer import os import tensorflow as tf from tensorflow.keras import datasets, layers, optimizers, Sequential, 阅读全文