autoencoder

问题 I build a CNN 1d Autoencoder in Keras, following the advice in this SO question, where Encoder and Decoder are separated. My goal is to re-use the decoder, once the Autoencoder has been trained. The central layer of my Autoencoder is a Dense layer, because I would like to learn it afterwards. My problem is that if I compile and fit the whole Autoencoder, written as Decoder()Encoder()(x) where x is the input, I get a different prediction when I do autoencoder.predict(training_set) w.r.t. if I

问题 Look at this strange load/save model situation. I saved variational autoencoder model and its encoder and decoder: autoencoder.save("autoencoder_save", overwrite=True) encoder.save("encoder_save", overwrite=True) decoder.save("decoder_save", overwrite=T) After that I loaded all of it from the disk: autoencoder_disk = load_model("autoencoder_save", custom_objects={'KLDivergenceLayer': KLDivergenceLayer, 'nll': nll}) encoder_disk = load_model("encoder_save", custom_objects={'KLDivergenceLayer':

问题 I am doing an image captioning task using vectors for representing both images and captions. The caption vectors have a legth/dimension of size 128. The image vectors have a length/dimension of size 2048. What I want to do is to train an autoencoder, to get an encoder which is able to convert text vector into a image vector. And a decoder which is able to convert an image vector into a text vector. Encoder: 128 -> 2048. Decoder: 2048 -> 128. I followed this tutorial to implement a shallow

问题 I wrote a vanilla autoencoder using only Dense layer. Below is my code: iLayer = Input ((784,)) layer1 = Dense(128, activation='relu' ) (iLayer) layer2 = Dense(64, activation='relu') (layer1) layer3 = Dense(28, activation ='relu') (layer2) layer4 = Dense(64, activation='relu') (layer3) layer5 = Dense(128, activation='relu' ) (layer4) layer6 = Dense(784, activation='softmax' ) (layer5) model = Model (iLayer, layer6) model.compile(loss='binary_crossentropy', optimizer='adam') (trainX, trainY),

问题 I have a seq2seq model which is working fine. I want to add an embedding layer in this network which I faced with an error. this is my architecture using pretrained word embedding which is working fine(Actually the code is almost the same code available here, but I want to include the Embedding layer in the model rather than using the pretrained embedding vectors): LATENT_SIZE = 20 inputs = Input(shape=(SEQUENCE_LEN, EMBED_SIZE), name="input") encoded = Bidirectional(LSTM(LATENT_SIZE), merge

问题 I am playing with a toy example to understand PCA vs keras autoencoder I have the following code for understanding PCA: import numpy as np import matplotlib.pyplot as plt from mpl_toolkits.mplot3d import Axes3D from sklearn import decomposition from sklearn import datasets iris = datasets.load_iris() X = iris.data pca = decomposition.PCA(n_components=3) pca.fit(X) pca.explained_variance_ratio_ array([ 0.92461621, 0.05301557, 0.01718514]) pca.components_ array([[ 0.36158968, -0.08226889, 0

问题 I am playing with a toy example to understand PCA vs keras autoencoder I have the following code for understanding PCA: import numpy as np import matplotlib.pyplot as plt from mpl_toolkits.mplot3d import Axes3D from sklearn import decomposition from sklearn import datasets iris = datasets.load_iris() X = iris.data pca = decomposition.PCA(n_components=3) pca.fit(X) pca.explained_variance_ratio_ array([ 0.92461621, 0.05301557, 0.01718514]) pca.components_ array([[ 0.36158968, -0.08226889, 0

问题 I'm trying to follow the Deep Autoencoder Keras example. I'm getting a dimension mismatch exception, but for the life of me, I can't figure out why. It works when I use only one encoded dimension, but not when I stack them. Exception: Input 0 is incompatible with layer dense_18: expected shape=(None, 128), found shape=(None, 32)* The error is on the line decoder = Model(input=encoded_input, output=decoder_layer(encoded_input)) from keras.layers import Dense,Input from keras.models import

问题 what is the main difference between autoencoder networks and fully convolutional network ? Please help me understand the difference between architecture of these two networks? 回答1: 1] AutoEncoder : Autoencodder is a dimensionality reduction technique It has two parts an encoder and decoder Enocder maps the raw data to a hidden representation (Latent Space Representation) Decoder maps the hidden representation back to raw data The network automatically learns this hidden representation and it

问题 I am currently developing a CNN model with Keras (an autoencoder). This type my inputs are of shape (47,47,3) , that is a 47x47 image with 3 (RGB) layers. I have worked with some CNN's in the past, but this time my input dimensions are prime numbers (47 pixels). This I think is causing issues with my implementation, specifically when using MaxPooling2D and UpSampling2D in my model. I noticed that some dimensions are lost when max pooling and then up sampling . Using model.summary() I can see