from GAN.utils import vis_grid
from GAN.utils.data import transform_skeleton, inverse_transform_skeleton
from GAN.utils.init import InitNormal
from keras.optimizers import Adam, SGD, RMSprop
if __name__ == '__main__':
nbatch = 128
nmax = nbatch * 100
npxw, npxh = 64, 128
from load import people, load_all
va_data, tr_stream, _ = people(pathfile='protocol/PPPS.txt', size=(npxw, npxh), batch_size=nbatch)
g = Generator(g_size=(8, npxh, npxw), g_nb_filters=128, g_nb_coding=500, g_scales=4, g_init=InitNormal(scale=0.002))#, g_FC=[5000])
d = Discriminator(d_size=g.g_size, d_nb_filters=128, d_scales=4, d_init=InitNormal(scale=0.002))#, d_FC=[5000])
gan = GAN(g, d)
from keras.optimizers import Adam, SGD, RMSprop
gan.fit(tr_stream,
save_dir='./samples/parsing_skeleton/',
k=1,
nbatch=nbatch,
nmax=nmax,
opt=Adam(lr=0.0002, beta_1=0.5, decay=1e-5),
transform=transform_skeleton, #opt=RMSprop(lr=0.01))
inverse_transform=inverse_transform_skeleton)
if __name__ == '__main__':
nbatch = 128
x, y, stream = get_mnist(nbatch)
g = InfoGenerator(g_size=(1, 28, 28),
g_nb_filters=64,
g_nb_noise=100, # not coding but noise
g_scales=2,
g_FC=[1024],
g_info=[
CategoryDist(n=10, lmbd=1e-3),
# UniformDist(min=-1.0,max=+1.0,lmbd=1e-3,stddev_fix=True),
# UniformDist(min=-1.0,max=+1.0,lmbd=1e-3,stddev_fix=True),
# UniformDist(min=-1.0,max=+1.0,lmbd=1e-3,stddev_fix=True),
],
g_init=InitNormal(scale=0.02),
)
d = Discriminator(d_size=g.g_size, d_nb_filters=64, d_scales=2, d_FC=[1024], d_init=InitNormal(scale=0.02))
Q = Sequential([ Dense(200, batch_input_shape=d.layers[-2].output_shape) ,
BN(),
Activation('relu'),
Dense(g.g_info.Qdim),
])
gan = InfoGAN(generator=g, discriminator=d, Qdist=Q)
from keras.optimizers import Adam, SGD, RMSprop
gan.fit(stream, save_dir='./samples/mnist_info', k=2,
nmax=nbatch*100,
nbatch=nbatch,
# opt=RMSprop(lr=0.0005))
opt=Adam(lr=0.0001))
if __name__ == '__main__':
nbatch = 128
nmax = nbatch * 100
npxw, npxh = 64, 128
from load import people
va_data, tr_stream, _ = people(pathfile='protocol/cuhk01-train.txt',
size=(npxw, npxh),
batch_size=nbatch)
g = Generator(g_size=(3, npxh, npxw),
g_nb_filters=128,
g_nb_coding=200,
g_scales=4,
g_init=InitNormal(scale=0.002))
d = Discriminator(d_size=g.g_size,
d_nb_filters=128,
d_scales=4,
d_init=InitNormal(scale=0.002))
gan = GAN(g, d)
from keras.optimizers import Adam, SGD, RMSprop
gan.fit(tr_stream,
save_dir='/home/shaofan/Projects/JSTL/transfer/gan/',
k=1,
nbatch=nbatch,
nmax=nmax,
opt=Adam(lr=0.0003, beta_1=0.5, decay=1e-5))
#opt=RMSprop(lr=0.01))
size=nbatch)].transpose(0, 2, 3, 1)
return x, y, random_stream
if __name__ == '__main__':
# init with ae and then run gan
nbatch = 128
x, y, stream = get_mnist(nbatch)
g = Generator(g_size=(1, 28, 28),
g_nb_filters=64,
g_nb_coding=200,
g_scales=2,
g_FC=[1024],
g_init=InitNormal(scale=0.05))
d = Discriminator(d_size=g.g_size,
d_nb_filters=64,
d_scales=2,
d_FC=[1024],
d_init=InitNormal(scale=0.05))
g.load_weights('models/mnist_ae_g.h5')
print g.get_weights()[0].sum()
d.load_weights('models/mnist_ae_d.h5')
print d.get_weights()[0].sum()
# gan = GAN(g, d)
gan = AEGAN(g, d)
from keras.optimizers import Adam, SGD, RMSprop
gan.fit(stream,
if __name__ == '__main__':
nbatch = 128
nmax = nbatch * 100
npxw, npxh = 64, 128
from load import people, load_all
va_data, tr_stream, _ = people(pathfile='protocol/cuhk01-train.txt',
size=(npxw, npxh),
batch_size=nbatch)
allx = transform(load_all('protocol/cuhk01-train.txt', (npxw, npxh)))
g = Generator(g_size=(3, npxh, npxw),
g_nb_filters=128,
g_nb_coding=5000,
g_scales=4,
g_init=InitNormal(scale=0.002)) #, g_FC=[5000])
d = Discriminator(d_size=g.g_size,
d_nb_filters=128,
d_scales=4,
d_init=InitNormal(scale=0.002)) #, d_FC=[5000])
# init with autoencoder
ae = Autoencoder(g, d)
# ae.fit(tr_stream,
# save_dir='./samples/reid_aegan_5000/ae/',
# nbatch=nbatch,
# opt=Adam(lr=0.002),
# niter=1001)
ae.autoencoder.load_weights(
'./samples/reid_aegan_5000/ae/1000_ae_params.h5')
def random_stream():
while 1:
yield x[np.random.choice(x.shape[0], replace=False,
size=nbatch)].transpose(0, 2, 3, 1)
return x, y, random_stream
from models_WGAN import generator_upsampling, generator_deconv
from models_WGAN import discriminator
if __name__ == '__main__':
nbatch = 64
x, y, stream = get_mnist(nbatch)
init = InitNormal(scale=0.02)
# g = MLP(g_size=(1, 28, 28),
# g_nb_filters=128,
# g_nb_coding=50,
# g_init=init)
g = Generator(g_size=(1, 28, 28),
g_nb_filters=32,
g_FC=[1024],
g_nb_coding=100,
g_scales=2,
g_init=init)
# d = Sequential([
# Flatten(input_shape=g.output_shape[1:]),
# Dense(128, init=init),
# Activation('relu'),
import numpy as np
from sklearn.datasets import fetch_mldata
from GAN.models import Generator, Critic, WGAN, MLP
from GAN.utils import vis_grid
from GAN.utils.data import transform, inverse_transform
from GAN.utils.init import InitNormal
from keras.models import Sequential
from keras.layers import Flatten, Dense, Activation
if __name__ == '__main__':
nbatch = 64
npxw, npxh = 64, 128
from load import people
va_data, stream, _ = people(pathfile='protocol/cuhk01-train.txt', size=(npxw, npxh), batch_size=nbatch)
g = Generator(g_size=(3, npxh, npxw), g_nb_filters=128, g_nb_coding=50, g_scales=4, g_init=InitNormal(scale=0.001))
d = Critic(d_size=g.g_size, d_nb_filters=128, d_scales=4, d_init=InitNormal(scale=0.001))
gan = WGAN(g, d)
from keras.optimizers import Adam, SGD, RMSprop
gan.fit(stream, save_dir='./labs/WGAN_reid',
opts = [RMSprop(lr=0.00005, clipvalue=0.01),
RMSprop(lr=0.00005)],
niter=100000,
)