def setup(self, X, num_centers, alpha, save_to='dec_model'):
sep = X.shape[0]*9/10
X_train = X[:sep]
X_val = X[sep:]
ae_model = AutoEncoderModel(self.xpu, [X.shape[1],500,500,2000,10], pt_dropout=0.2)
if not os.path.exists(save_to+'_pt.arg'):
ae_model.layerwise_pretrain(X_train, 256, 50000, 'sgd', l_rate=0.1, decay=0.0,
lr_scheduler=mx.misc.FactorScheduler(20000,0.1))
ae_model.finetune(X_train, 256, 100000, 'sgd', l_rate=0.1, decay=0.0,
lr_scheduler=mx.misc.FactorScheduler(20000,0.1))
ae_model.save(save_to+'_pt.arg')
logging.log(logging.INFO, "Autoencoder Training error: %f"%ae_model.eval(X_train))
logging.log(logging.INFO, "Autoencoder Validation error: %f"%ae_model.eval(X_val))
else:
ae_model.load(save_to+'_pt.arg')
self.ae_model = ae_model
self.dec_op = DECModel.DECLoss(num_centers, alpha)
label = mx.sym.Variable('label')
self.feature = self.ae_model.encoder
self.loss = self.dec_op(data=self.ae_model.encoder, label=label, name='dec')
self.args.update({k:v for k,v in self.ae_model.args.items() if k in self.ae_model.encoder.list_arguments()})
self.args['dec_mu'] = mx.nd.empty((num_centers, self.ae_model.dims[-1]), ctx=self.xpu)
self.args_grad.update({k: mx.nd.empty(v.shape, ctx=self.xpu) for k,v in self.args.items()})
self.args_mult.update({k: k.endswith('bias') and 2.0 or 1.0 for k in self.args})
self.num_centers = num_centers
def setup(self, X, num_centers, alpha, save_to='dec_model'):
sep = X.shape[0] * 9 / 10
X_train = X[:sep]
X_val = X[sep:]
ae_model = AutoEncoderModel(self.xpu, [X.shape[1], 500, 500, 2000, 10], pt_dropout=0.2)
if not os.path.exists(save_to + '_pt.arg'):
ae_model.layerwise_pretrain(X_train, 256, 50000, 'sgd', l_rate=0.1, decay=0.0,
lr_scheduler=mx.misc.FactorScheduler(20000, 0.1))
ae_model.finetune(X_train, 256, 100000, 'sgd', l_rate=0.1, decay=0.0,
lr_scheduler=mx.misc.FactorScheduler(20000, 0.1))
ae_model.save(save_to + '_pt.arg')
logging.log(logging.INFO, "Autoencoder Training error: %f" % ae_model.eval(X_train))
logging.log(logging.INFO, "Autoencoder Validation error: %f" % ae_model.eval(X_val))
else:
ae_model.load(save_to + '_pt.arg')
self.ae_model = ae_model
self.dec_op = DECModel.DECLoss(num_centers, alpha)
label = mx.sym.Variable('label')
self.feature = self.ae_model.encoder
self.loss = self.dec_op(data=self.ae_model.encoder, label=label, name='dec')
self.args.update({k: v for k, v in self.ae_model.args.items() if k in self.ae_model.encoder.list_arguments()})
self.args['dec_mu'] = mx.nd.empty((num_centers, self.ae_model.dims[-1]), ctx=self.xpu)
self.args_grad.update({k: mx.nd.empty(v.shape, ctx=self.xpu) for k, v in self.args.items()})
self.args_mult.update({k: k.endswith('bias') and 2.0 or 1.0 for k in self.args})
self.num_centers = num_centers
def setup(self, X, num_centers, alpha, znum, save_to='dec_model'):
# Read previously trained _SAE
ae_model = AutoEncoderModel(self.xpu,
[X.shape[1], 500, 500, 2000, znum],
pt_dropout=0.2)
ae_model.load(
os.path.join(
save_to,
'SAE_zsize{}_wimgfeatures_descStats_zeromean.arg'.format(
str(znum)))) #_Nbatch_wimgfeatures
logging.log(
logging.INFO,
"Reading Autoencoder from file..: %s" % (os.path.join(
save_to, 'SAE_zsize{}_wimgfeatures_descStats_zeromean.arg'.
format(znum))))
self.ae_model = ae_model
logging.log(logging.INFO, "finished reading Autoencoder from file..: ")
self.dec_op = DECModel.DECLoss(num_centers, alpha)
label = mx.sym.Variable('label')
self.feature = self.ae_model.encoder
self.loss = self.dec_op(data=self.ae_model.encoder,
label=label,
name='dec')
self.args.update({
k: v
for k, v in self.ae_model.args.items()
if k in self.ae_model.encoder.list_arguments()
})
self.args['dec_mu'] = mx.nd.empty(
(num_centers, self.ae_model.dims[-1]), ctx=self.xpu)
self.args_grad.update({
k: mx.nd.empty(v.shape, ctx=self.xpu)
for k, v in self.args.items()
})
self.args_mult.update(
{k: k.endswith('bias') and 2.0 or 1.0
for k in self.args})
self.num_centers = num_centers
self.best_args = {}
self.best_args['num_centers'] = num_centers
self.best_args['znum'] = znum
decay=0.0,
lr_scheduler=mx.lr_scheduler.FactorScheduler(
20000, 0.7),
print_every=print_every)
ae_model.finetune(train_X,
batch_size,
finetune_num_iter,
'sgd',
l_rate=0.1,
decay=0.0,
lr_scheduler=mx.lr_scheduler.FactorScheduler(20000, 0.1),
print_every=print_every)
ae_model.save('autoencoder.arg')
ae_model.load('autoencoder.arg')
print("Training error:", ae_model.eval(train_X))
print("Validation error:", ae_model.eval(val_X))
if visualize:
try:
from matplotlib import pyplot as plt
from model import extract_feature
# sample a random image
#index = np.random.choice(len(X))
index = 0
original_image = X[index]
#print(json.dumps(original_image))
data_iter = mx.io.NDArrayIter({'data': [original_image]},
batch_size=1,
save_to = r'Z:\Cristina\Section3\paper_notes_section3_MODIFIED\save_to\SAEmodels'
input_size = combX_allNME.shape[1]
latent_size = [input_size / rxf for rxf in [15, 10, 5, 2]]
############ BEST PERFORMIGN of Step 1 nzum = 2x
znum = 261
X = combX_allNME
y = roi_labels
xpu = mx.cpu()
ae_model = AutoEncoderModel(xpu, [X.shape[1], 500, 500, 2000, znum],
pt_dropout=0.2)
print('Loading autoencoder of znum = {}, post training'.format(znum))
ae_model.load(
os.path.join(
save_to,
'SAE_zsize{}_wimgfeatures_descStats_zeromean.arg'.format(str(znum))))
data_iter = mx.io.NDArrayIter({'data': X},
batch_size=X.shape[0],
shuffle=False,
last_batch_handle='pad')
# extract only the encoder part of the SAE
feature = ae_model.encoder
zspace = model.extract_feature(feature, ae_model.args, None, data_iter,
X.shape[0], xpu).values()[0]
# pool Z-space variables
datalabels = np.asarray(y)
dataZspace = zspace
# pylint: skip-file
import mxnet as mx
import numpy as np
import logging
import data
from autoencoder import AutoEncoderModel
if __name__ == '__main__':
# set to INFO to see less information during training
logging.basicConfig(level=logging.DEBUG)
ae_model = AutoEncoderModel(mx.gpu(0), [784,500,500,2000,10], pt_dropout=0.2,
internal_act='relu', output_act='relu')
X, _ = data.get_mnist()
train_X = X[:60000]
val_X = X[60000:]
ae_model.layerwise_pretrain(train_X, 256, 50000, 'sgd', l_rate=0.1, decay=0.0,
lr_scheduler=mx.misc.FactorScheduler(20000,0.1))
ae_model.finetune(train_X, 256, 100000, 'sgd', l_rate=0.1, decay=0.0,
lr_scheduler=mx.misc.FactorScheduler(20000,0.1))
ae_model.save('mnist_pt.arg')
ae_model.load('mnist_pt.arg')
print "Training error:", ae_model.eval(train_X)
print "Validation error:", ae_model.eval(val_X)
import logging
import mnist_data as data
from math import sqrt
from autoencoder import AutoEncoderModel
if __name__ == '__main__':
lv = 1e-2# lv/ln in CDL
# set to INFO to see less information during training
logging.basicConfig(level=logging.DEBUG)
#ae_model = AutoEncoderModel(mx.gpu(0), [784,500,500,2000,10], pt_dropout=0.2,
# internal_act='relu', output_act='relu')
ae_model = AutoEncoderModel(mx.cpu(2), [784,500,500,2000,10], pt_dropout=0.2,
internal_act='relu', output_act='relu')
X, _ = data.get_mnist()
train_X = X[:60000]
val_X = X[60000:]
#ae_model.layerwise_pretrain(train_X, 256, 50000, 'sgd', l_rate=0.1, decay=0.0,
# lr_scheduler=mx.misc.FactorScheduler(20000,0.1))
#V = np.zeros((train_X.shape[0],10))
V = np.random.rand(train_X.shape[0],10)/10
lambda_v_rt = np.ones((train_X.shape[0],10))*sqrt(lv)
ae_model.finetune(train_X, V, lambda_v_rt, 256,
20, 'sgd', l_rate=0.1, decay=0.0,
lr_scheduler=mx.misc.FactorScheduler(20000,0.1))
ae_model.save('mnist_pt.arg')
ae_model.load('mnist_pt.arg')
print "Training error:", ae_model.eval(train_X,V,lambda_v_rt)
#print "Validation error:", ae_model.eval(val_X)
import mxnet as mx
import sys
sys.path.append("../")
sys.path.append("../../autoencoder")
import logging
import numpy as np
from autoencoder import AutoEncoderModel
#from visualize import visualize
from data_all import news_iterator
#ae_model = AutoEncoderModel(mx.gpu(0), [5000,100], pt_dropout=0.5)
ae_model = AutoEncoderModel(mx.gpu(3),[5000,100],internal_act='sigmoid', output_act='sigmoid', sparseness_penalty=1e-4, pt_dropout=0)
logging.basicConfig(level=logging.DEBUG)
#ae_model.load('../../autoencoder/news_20classes_small.arg')#classes_small.arg') #news_20_ltest.arg
ae_model.load('news_20classes_small_1e-4_non-neg.arg')
batch_size = 100
fea_sym = ae_model.loss.get_internals()#[3]
logging.info(fea_sym.list_outputs())
output=fea_sym['sparse_encoder_0_output']
fc3 = mx.symbol.FullyConnected(data=output, num_hidden=20)
softmax = mx.symbol.SoftmaxOutput(data=fc3, name='softmax')
#logging.info(softmax.list_arguments())
args=ae_model.args
datashape=(100,5000)
train, val, _ = news_iterator(input_size = 5000,batchsize=100)
#fc = softmax.get_internals()
#logging.info(fc.list_arguments())
args_shape,ow,aw = softmax.get_internals().infer_shape(data=datashape)
#logging.info(args_shape)
def setup(self, X, num_centers, alpha, znum, save_to='dec_model'):
self.sep = int(X.shape[0] * 0.75)
X_train = X[:self.sep]
X_val = X[self.sep:]
batch_size = 32 # 160 32*5 = update_interval*5
# Train or Read autoencoder: note is not dependent on number of clusters just on z latent size
ae_model = AutoEncoderModel(self.xpu,
[X.shape[1], 500, 500, 2000, znum],
pt_dropout=0.2)
if not os.path.exists(save_to + '_pt.arg'):
ae_model.layerwise_pretrain(X_train,
batch_size,
50000,
'sgd',
l_rate=0.1,
decay=0.0,
lr_scheduler=mx.misc.FactorScheduler(
20000, 0.1))
ae_model.finetune(X_train,
batch_size,
100000,
'sgd',
l_rate=0.1,
decay=0.0,
lr_scheduler=mx.misc.FactorScheduler(20000, 0.1))
ae_model.save(save_to + '_pt.arg')
logging.log(
logging.INFO,
"Autoencoder Training error: %f" % ae_model.eval(X_train))
logging.log(
logging.INFO,
"Autoencoder Validation error: %f" % ae_model.eval(X_val))
else:
ae_model.load(save_to + '_pt.arg')
logging.log(
logging.INFO,
"Reading Autoencoder from file..: %s" % (save_to + '_pt.arg'))
logging.log(
logging.INFO,
"Autoencoder Training error: %f" % ae_model.eval(X_train))
logging.log(
logging.INFO,
"Autoencoder Validation error: %f" % ae_model.eval(X_val))
self.ae_model = ae_model
logging.log(logging.INFO, "finished reading Autoencoder from file..: ")
# prep model for clustering
self.dec_op = DECModel.DECLoss(num_centers, alpha)
label = mx.sym.Variable('label')
self.feature = self.ae_model.encoder
self.loss = self.dec_op(data=self.ae_model.encoder,
label=label,
name='dec')
self.args.update({
k: v
for k, v in self.ae_model.args.items()
if k in self.ae_model.encoder.list_arguments()
})
self.args['dec_mu'] = mx.nd.empty(
(num_centers, self.ae_model.dims[-1]), ctx=self.xpu)
self.args_grad.update({
k: mx.nd.empty(v.shape, ctx=self.xpu)
for k, v in self.args.items()
})
self.args_mult.update(
{k: k.endswith('bias') and 2.0 or 1.0
for k in self.args})
self.num_centers = num_centers
self.znum = znum
self.batch_size = batch_size
self.G = self.ae_model.eval(X_train) / self.ae_model.eval(X_val)
dev=mx.gpu()
# train, val, voc = news_iterator(voc_count, 100)
vocfile = "/home/tingyubi/20w/data/tfidf_extraction-1_26.voc"
with open(vocfile,'r') as f:
voc = f.read().decode('utf-8').split(" ")
"""
data = mx.symbol.Variable('data')
fc1 = mx.symbol.FullyConnected(name='encoder_%d'%istack, data=data, num_hidden=20)
sig1 = mx.symbol.Activation(data=fc1, act_type='sigmoid')
sparse1 = mx.symbol.SparseReg(data=sig1, penalty=1e-3, sparseness_target=0.1)
fc2 = mx.symbol.FullyConnected(name='decoder_%d'%istack, data=sparse1, num_hidden=5000)
loss = mx.symbol.LinearRegressionOutput(data=fc2, name='softmax')
"""
aem = AutoEncoderModel(mx.gpu(3),[voc_count,1000,200],internal_act='sigmoid', output_act='sigmoid', sparseness_penalty=1e-4, pt_dropout=0)
aem.load('/home/tingyubi/20w/autoencoder/20w_1000_200_1e-4_non-neg.arg')
#print aem.loss.get_internals().list_outputs()
fc2 = aem.encoder
print aem.loss.get_internals().list_outputs()
#print aem.loss.get_internals().list_arguments()
model = aem
#print model.arg_params['encoder_0_weight'].shape
"""
for k in range(2):
words_index=np.argsort(model.args['encoder_0_weight'].asnumpy()[k,:])
logging.info('Topic %d' % k)
logging.info([voc[i] for i in words_index[-20:]])
"""
for k in range(200):
