This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
def generator(): | |
""" Declare generator """ | |
model = Sequential() | |
model.add(Dense(256, input_shape=(10,))) | |
model.add(LeakyReLU(alpha=0.2)) # 使用 LeakyReLU 激活函數 | |
model.add(BatchNormalization(momentum=0.8)) # 使用 BatchNormalization 優化 | |
model.add(Dense(512)) | |
model.add(LeakyReLU(alpha=0.2)) | |
model.add(BatchNormalization(momentum=0.8)) |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import numpy as np | |
import os | |
from keras.datasets import mnist | |
from keras.layers import Dense, Reshape, Flatten | |
from keras.layers import BatchNormalization | |
from keras.layers.advanced_activations import LeakyReLU | |
from keras.models import Sequential | |
from keras.optimizers import Adam |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
# Eval. | |
q = model.predict(x, verbose=0) | |
p = target_distribution(q) # update the auxiliary target distribution p | |
# evaluate the clustering performance | |
y_pred = q.argmax(1) | |
if y is not None: | |
acc = np.round(accu(y, y_pred), 5) | |
nmi = np.round(nmis(y, y_pred), 5) | |
ari = np.round(aris(y, y_pred), 5) |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
model.compile(optimizer=SGD(0.01, 0.9), loss='kld') | |
#%% | |
kmeans = KMeans(n_clusters=n_clusters, n_init=20) | |
y_pred = kmeans.fit_predict(encoder.predict(x)) | |
#%% | |
y_pred_last = np.copy(y_pred) | |
model.get_layer(name='clustering').set_weights([kmeans.cluster_centers_]) | |
#%% | |
# computing an auxiliary target distribution | |
def target_distribution(q): |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
class ClusteringLayer(Layer): | |
""" | |
Clustering layer converts input sample (feature) to soft label, i.e. a vector that represents the probability of the | |
sample belonging to each cluster. The probability is calculated with student's t-distribution. | |
# Example | |
``` | |
model.add(ClusteringLayer(n_clusters=10)) | |
``` | |
# Arguments | |
n_clusters: number of clusters. |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import os | |
import keras.backend as K | |
from keras.engine.topology import Layer, InputSpec | |
from keras.layers import Dense, Input | |
from keras.models import Model | |
from keras.optimizers import SGD | |
from keras import callbacks | |
from keras.initializers import VarianceScaling | |
def autoencoder(dims, act='relu', init='glorot_uniform'): |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
from sklearn.cluster import KMeans | |
from keras.datasets import mnist | |
import numpy as np | |
def accu(y_true, y_pred): | |
""" | |
Calculate clustering accuracy. Require scikit-learn installed | |
# Arguments | |
y: true labels, numpy.array with shape `(n_samples,)` | |
y_pred: predicted labels, numpy.array with shape `(n_samples,)` |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
# -*- coding: utf-8 -*- | |
""" | |
Created on Mon Apr 22 10:47:52 2019 | |
@author: Mortis | |
""" | |
#%% | |
import os | |
import numpy as np | |
import keras.backend as K |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
# -*- coding: utf-8 -*- | |
""" | |
Created on Thu Feb 21 12:53:15 2019 | |
@author: Mortis | |
""" | |
import umap | |
import pandas as pd | |
import numpy as np | |
from sklearn.datasets import load_digits |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
from bokeh.plotting import figure, output_file, show | |
# prepare some data | |
x = [1, 2, 3, 4, 5] | |
y = [6, 7, 2, 4, 5] | |
# output to static HTML file | |
output_file("lines.html", title="line plot example") | |
# create a new plot with a title and axis labels |