def test_MaskSoftmax():
X_ph = tf.placeholder('float32', [None, 20])
seq_ph = tf.placeholder('int32', [None])
X_sn = tg.StartNode(input_vars=[X_ph])
seq_sn = tg.StartNode(input_vars=[seq_ph])
merge_hn = tg.HiddenNode(prev=[X_sn, seq_sn], input_merge_mode=MaskSoftmax())
y_en = tg.EndNode(prev=[merge_hn])
graph = tg.Graph(start=[X_sn, seq_sn], end=[y_en])
y_sb, = graph.train_fprop()
with tf.Session() as sess:
sess.run(tf.global_variables_initializer())
feed_dict = {X_ph:np.random.rand(3, 20),
seq_ph:[5, 8, 0]}
out = sess.run(y_sb, feed_dict=feed_dict)
assert (out[0][5:].sum() - 0)**2 < 1e-6
assert (out[0][:5].sum() - 1)**2 < 1e-6
assert (out[1][8:].sum() - 0)**2 < 1e-6
assert (out[1][:8].sum() - 1)**2 < 1e-6
assert (out[2].sum() - 0)**2 < 1e-6
print('test passed!')
def test_SequenceMask():
X_ph = tf.placeholder('float32', [None, 5, 6, 7])
seq_ph = tf.placeholder('int32', [None])
X_sn = tg.StartNode(input_vars=[X_ph])
seq_sn = tg.StartNode(input_vars=[seq_ph])
merge_hn = tg.HiddenNode(prev=[X_sn, seq_sn], input_merge_mode=SequenceMask(maxlen=5))
out_en = tg.EndNode(prev=[merge_hn])
graph = tg.Graph(start=[X_sn, seq_sn], end=[out_en])
y_train_sb = graph.train_fprop()
y_test_sb = graph.test_fprop()
with tf.Session() as sess:
init = tf.global_variables_initializer()
sess.run(init)
feed_dict = {X_ph:np.random.rand(3,5,6,7), seq_ph:[2,3,4]}
y_train = sess.run(y_train_sb, feed_dict=feed_dict)[0]
y_test = sess.run(y_test_sb, feed_dict=feed_dict)[0]
assert y_train.sum() == y_test.sum()
assert y_train[0, :2].sum() > 0 and y_train[0, 2:].sum() == 0
assert y_train[1, :3].sum() > 0 and y_train[1, 3:].sum() == 0
assert y_train[2, :4].sum() > 0 and y_train[2, 4:].sum() == 0
print('test passed!')
def test_SelectedMaskSoftmax():
X_ph = tf.placeholder('float32', [None, 20])
mask_ph = tf.placeholder('float32', [20])
X_sn = tg.StartNode(input_vars=[X_ph])
mask_sn = tg.StartNode(input_vars=[mask_ph])
merge_hn = tg.HiddenNode(prev=[X_sn, mask_sn], input_merge_mode=SelectedMaskSoftmax())
y_en = tg.EndNode(prev=[merge_hn])
graph = tg.Graph(start=[X_sn, mask_sn], end=[y_en])
y_sb, = graph.train_fprop()
with tf.Session() as sess:
sess.run(tf.global_variables_initializer())
mask_arr = np.zeros(20)
mask_arr[[2,3,4]] = 1
# import pdb; pdb.set_trace()
feed_dict = {X_ph:np.random.rand(3, 20),
mask_ph:mask_arr}
out = sess.run(y_sb, feed_dict=feed_dict)
assert (out.sum(1) == 1).any()
print(out)
print('test passed!')
def discriminator(self, X):
X_sn = tg.StartNode(input_vars=[X])
hn1 = tg.HiddenNode(prev=[X_sn], layers=self.d1_layers)
hn2 = tg.HiddenNode(prev=[hn1], layers=self.d2_layers)
hn3 = tg.HiddenNode(prev=[hn2], layers=self.d3_layers)
hn4 = tg.HiddenNode(prev=[hn3], layers=self.d4_layers)
hn5 = tg.HiddenNode(prev=[hn4], layers=self.d5_layers)
en1 = tg.EndNode(prev=[hn1])
en2 = tg.EndNode(prev=[hn2])
en3 = tg.EndNode(prev=[hn3])
en4 = tg.EndNode(prev=[hn4])
en5 = tg.EndNode(prev=[hn5])
graph = tg.Graph(start=[X_sn], end=[en1, en2, en3, en4, en5])
y1, y2, y3, y4, y5 = graph.train_fprop()
y1_test, y2_test, y3_test, y4_test, y5_test = graph.test_fprop()
return y1, y2, y3, y4, y5, y1_test, y2_test, y3_test, y4_test, y5_test
def __init__(self, h, w, c):
layers1 = []
layers1.append(Conv2D(input_channels=c, num_filters=1, kernel_size=(2,2), stride=(1,1), padding='SAME'))
layers1.append(BatchNormalization(input_shape=[h,w,1]))
layers1.append(RELU())
layers2 = []
layers2.append(Conv2D(input_channels=c, num_filters=1, kernel_size=(2,2), stride=(1,1), padding='SAME'))
layers2.append(BatchNormalization(input_shape=[h,w,1]))
layers2.append(RELU())
self.startnode = tg.StartNode(input_vars=[None])
hn1 = tg.HiddenNode(prev=[self.startnode], layers=layers1)
hn2 = tg.HiddenNode(prev=[self.startnode], layers=layers2)
hn3 = tg.HiddenNode(prev=[hn1, hn2], input_merge_mode=Sum())
self.endnode = tg.EndNode(prev=[hn3])
def classfication(self, X):
X_sn = tg.StartNode(input_vars=[X])
hn = tg.HiddenNode(prev=[X_sn], layers=[])
en = tg.EndNode(prev=[hn])
graph = tg.Graph(start=[X_sn], end=[en])
y_train, = graph.train_fprop()
y_test, = graph.test_fprop()
return y_train, y_test
def __init__(self, nclass, h, w, c):
layers = []
layers.append(AllCNN(nclass, h, w, c))
layers.append(Linear(nclass, nclass))
layers.append(Softmax())
self.startnode = tg.StartNode(input_vars=[None])
model_hn = tg.HiddenNode(prev=[self.startnode], layers=layers)
self.endnode = tg.EndNode(prev=[model_hn])
def generator(self, z_fake):
z_fake_sn = tg.StartNode(input_vars=[z_fake])
hn = tg.HiddenNode(prev=[z_fake_sn], layers=self.g_layers)
en = tg.EndNode(prev=[hn])
graph = tg.Graph(start=[z_fake_sn], end=[en])
X_fake_train_sb, = graph.train_fprop()
X_fake_test_sb, = graph.test_fprop()
return X_fake_train_sb, X_fake_test_sb
def __init__(self, h, w, c, nclass):
layers = []
layers.append(CBR(h,w,c))
layers.append(Flatten())
layers.append(Linear(1*h*w, nclass))
self.startnode = tg.StartNode(input_vars=[None])
hn = tg.HiddenNode(prev=[self.startnode], layers=layers)
self.endnode = tg.EndNode(prev=[hn])
def __init__(self):
self.startnode = tg.StartNode(input_vars=[None])
layers1 = []
layers1.append(Linear(5))
hn1 = tg.HiddenNode(prev=[self.startnode], input_merge_mode=Select(0), layers=layers1)
layers2 = []
layers2.append(Linear(8))
hn2 = tg.HiddenNode(prev=[self.startnode], input_merge_mode=Select(1), layers=layers2)
merge = tg.HiddenNode(prev=[hn1, hn2], input_merge_mode=Concat(axis=1))
layers1a = []
layers1a.append(Linear(20))
hn1a = tg.HiddenNode(prev=[merge], layers=layers1a)
layers2a = []
layers2a.append(Linear(30))
hn2a = tg.HiddenNode(prev=[merge], layers=layers2a)
self.endnode = tg.EndNode(prev=[hn1a, hn2a])
def model(word_len, sent_len, nclass):
unicode_size = 1000
ch_embed_dim = 20
h, w = valid(ch_embed_dim,
word_len,
stride=(1, 1),
kernel_size=(ch_embed_dim, 5))
h, w = valid(h, w, stride=(1, 1), kernel_size=(1, 5))
h, w = valid(h, w, stride=(1, 2), kernel_size=(1, 5))
conv_out_dim = int(h * w * 60)
X_ph = tf.placeholder('int32', [None, sent_len, word_len])
input_sn = tg.StartNode(input_vars=[X_ph])
charcnn_hn = tg.HiddenNode(prev=[input_sn],
layers=[
Reshape(shape=(-1, word_len)),
Embedding(cat_dim=unicode_size,
encode_dim=ch_embed_dim,
zero_pad=True),
Reshape(shape=(-1, ch_embed_dim, word_len,
1)),
Conv2D(input_channels=1,
num_filters=20,
padding='VALID',
kernel_size=(ch_embed_dim, 5),
stride=(1, 1)),
RELU(),
Conv2D(input_channels=20,
num_filters=40,
padding='VALID',
kernel_size=(1, 5),
stride=(1, 1)),
RELU(),
Conv2D(input_channels=40,
num_filters=60,
padding='VALID',
kernel_size=(1, 5),
stride=(1, 2)),
RELU(),
Flatten(),
Linear(conv_out_dim, nclass),
Reshape((-1, sent_len, nclass)),
ReduceSum(1),
Softmax()
])
output_en = tg.EndNode(prev=[charcnn_hn])
graph = tg.Graph(start=[input_sn], end=[output_en])
y_train_sb = graph.train_fprop()[0]
y_test_sb = graph.test_fprop()[0]
return X_ph, y_train_sb, y_test_sb
def resnet_crf_rnn(x_ph):
s_n = tg.StartNode(input_vars=[x_ph])
h1_n = tg.HiddenNode(prev=[s_n],
layers=[
ResNet(num_blocks=5),
Conv2D(input_channels=3,
num_filters=1,
kernel_size=(5, 5),
stride=(1, 1),
padding='SAME'),
Sigmoid()
])
h2_n = tg.HiddenNode(prev=[s_n, h1_n],
input_merge_mode=NoChange(),
layers=[CRF_RNN(num_iter=2)])
end_n = tg.EndNode(prev=[h2_n])
graph = tg.Graph(start=[s_n], end=[end_n])
# import pdb; pdb.set_trace()
train_out = graph.train_fprop()
test_out = graph.test_fprop()
return train_out, test_out
def __init__(self, nclass, h, w, c):
layers = []
template = TemplateModel(nclass, h, w, c)
layers.append(template)
layers.append(Flatten())
layers.append(Linear(template.output_dim, 200))
layers.append(RELU())
layers.append(Linear(200, nclass))
layers.append(Softmax())
self.startnode = tg.StartNode(input_vars=[None])
model_hn = tg.HiddenNode(prev=[self.startnode], layers=layers)
self.endnode = tg.EndNode(prev=[model_hn])
def __init__(self, nclass, h, w, c):
layers = []
identityblk = IdentityBlock(input_channels=c,
input_shape=[h, w],
nlayers=10)
layers.append(identityblk)
layers.append(
Conv2D(input_channels=c,
num_filters=16,
kernel_size=(3, 3),
stride=(1, 1),
padding='SAME'))
layers.append(RELU())
h, w = same(in_height=h, in_width=w, stride=(1, 1), kernel_size=(3, 3))
layers.append(BatchNormalization(input_shape=[h, w, 16]))
denseblk = DenseBlock(input_channels=16,
input_shape=[h, w],
growth_rate=4,
nlayers=4)
layers.append(denseblk)
layers.append(
Conv2D(input_channels=denseblk.output_channels,
num_filters=32,
kernel_size=(3, 3),
stride=(2, 2),
padding='SAME'))
layers.append(RELU())
h, w = same(in_height=h, in_width=w, stride=(2, 2), kernel_size=(3, 3))
layers.append(Dropout(0.5))
layers.append(
Conv2D(input_channels=32,
num_filters=nclass,
kernel_size=(1, 1),
stride=(1, 1),
padding='SAME'))
layers.append(RELU())
h, w = same(in_height=h, in_width=w, stride=(1, 1), kernel_size=(1, 1))
layers.append(BatchNormalization(input_shape=[h, w, nclass]))
layers.append(
AvgPooling(poolsize=(h, w), stride=(1, 1), padding='VALID'))
layers.append(Flatten())
layers.append(Softmax())
self.startnode = tg.StartNode(input_vars=[None])
model_hn = tg.HiddenNode(prev=[self.startnode], layers=layers)
self.endnode = tg.EndNode(prev=[model_hn])
def __init__(self, nclass, h, w, c):
layers = []
model = UNet(input_channels=c, input_shape=(h, w))
layers.append(model)
layers.append(
MaxPooling(poolsize=tuple(model.output_shape),
stride=(1, 1),
padding='VALID'))
layers.append(Flatten())
layers.append(Linear(model.output_channels, nclass))
layers.append(Softmax())
self.startnode = tg.StartNode(input_vars=[None])
model_hn = tg.HiddenNode(prev=[self.startnode], layers=layers)
self.endnode = tg.EndNode(prev=[model_hn])
def __init__(self, nclass, h, w, c):
layers = []
# model = DenseNet(input_channels=c, input_shape=(h, w), ndense=1, growth_rate=1, nlayer1blk=1)
model = DenseNet(input_channels=c,
input_shape=(h, w),
ndense=3,
growth_rate=4,
nlayer1blk=4)
layers.append(model)
self.output_dim = np.prod(model.output_shape) * model.output_channels
# import pdb; pdb.set_trace()
self.startnode = tg.StartNode(input_vars=[None])
model_hn = tg.HiddenNode(prev=[self.startnode], layers=layers)
self.endnode = tg.EndNode(prev=[model_hn])
def discriminator(self):
if not self.generator_called:
raise Exception(
'self.generator() has to be called first before self.discriminator()'
)
scope = 'Discriminator'
with self.tf_graph.as_default():
with tf.name_scope(scope):
h1, w1 = valid(self.h,
self.w,
kernel_size=(5, 5),
stride=(1, 1))
h2, w2 = valid(h1, w1, kernel_size=(5, 5), stride=(2, 2))
h3, w3 = valid(h2, w2, kernel_size=(5, 5), stride=(2, 2))
flat_dim = int(h3 * w3 * 32)
h1, w1 = valid(self.char_embed_dim,
self.word_len,
kernel_size=(self.char_embed_dim, 3),
stride=(1, 1))
print('h1:{}, w1:{}'.format(h1, w1))
h2, w2 = valid(h1, w1, kernel_size=(1, 3), stride=(1, 1))
print('h2:{}, w2:{}'.format(h2, w2))
h3, w3 = valid(h2, w2, kernel_size=(1, 3), stride=(1, 1))
print('h3:{}, w3:{}'.format(h3, w3))
# h4, w4 = valid(h3, w3, kernel_size=(1,6), stride=(1,1))
# print('h4:{}, w4:{}'.format(h4, w4))
# hf, wf = h4, w4
hf, wf = h3, w3
n_filters = 100
real_sn = tg.StartNode(input_vars=[self.real_ph])
real_hn = tg.HiddenNode(prev=[real_sn],
layers=[
OneHot(self.char_embed_dim),
Transpose(perm=[0, 3, 2, 1])
])
disc_hn = tg.HiddenNode(
prev=[real_hn, self.gen_hn],
layers=[
Conv2D(input_channels=self.sent_len,
num_filters=100,
kernel_size=(self.char_embed_dim, 3),
stride=(1, 1),
padding='VALID'),
TFBatchNormalization(name=scope + '/d1'),
LeakyRELU(),
Conv2D(input_channels=100,
num_filters=100,
kernel_size=(1, 3),
stride=(1, 1),
padding='VALID'),
TFBatchNormalization(name=scope + '/d2'),
LeakyRELU(),
Conv2D(input_channels=100,
num_filters=100,
kernel_size=(1, 3),
stride=(1, 1),
padding='VALID'),
TFBatchNormalization(name=scope + '/d3'),
LeakyRELU(),
# Conv2D(input_channels=32, num_filters=128, kernel_size=(1,6), stride=(1,1), padding='VALID'),
# RELU(),
Flatten(),
Linear(int(hf * wf * n_filters), self.bottleneck_dim),
TFBatchNormalization(name=scope + '/d4'),
LeakyRELU(),
])
class_hn = tg.HiddenNode(prev=[disc_hn],
layers=[
Linear(self.bottleneck_dim,
self.nclass),
Softmax()
])
judge_hn = tg.HiddenNode(
prev=[disc_hn],
layers=[
Linear(self.bottleneck_dim, 1),
# Sigmoid()
])
real_class_en = tg.EndNode(prev=[class_hn])
real_judge_en = tg.EndNode(prev=[judge_hn])
fake_class_en = tg.EndNode(prev=[class_hn])
fake_judge_en = tg.EndNode(prev=[judge_hn])
graph = tg.Graph(start=[real_sn],
end=[real_class_en, real_judge_en])
real_train = graph.train_fprop()
real_valid = graph.test_fprop()
graph = tg.Graph(start=[self.noise_sn],
end=[fake_class_en, fake_judge_en])
fake_train = graph.train_fprop()
fake_valid = graph.test_fprop()
dis_var_list = tf.get_collection(tf.GraphKeys.GLOBAL_VARIABLES,
scope=scope)
return self.real_ph, real_train, real_valid, fake_train, fake_valid, dis_var_list
def discriminator(self):
if not self.generator_called:
raise Exception(
'self.generator() has to be called first before self.discriminator()'
)
scope = 'Discriminator'
with self.tf_graph.as_default():
with tf.name_scope(scope):
h1, w1 = valid(self.h,
self.w,
kernel_size=(5, 5),
stride=(1, 1))
h2, w2 = valid(h1, w1, kernel_size=(5, 5), stride=(2, 2))
h3, w3 = valid(h2, w2, kernel_size=(5, 5), stride=(2, 2))
flat_dim = int(h3 * w3 * 32)
dis_real_sn = tg.StartNode(input_vars=[self.real_ph])
# fake_ph = tf.placeholder('float32', [None, self.h, self.w, 1], name='fake')
# fake_sn = tg.StartNode(input_vars=[fake_ph])
disc_hn = tg.HiddenNode(
prev=[dis_real_sn, self.gen_hn],
layers=[
Conv2D(input_channels=self.c,
num_filters=32,
kernel_size=(5, 5),
stride=(1, 1),
padding='VALID'),
TFBatchNormalization(name=scope + '/d1'),
# BatchNormalization(layer_type='conv', dim=32, short_memory=0.01),
LeakyRELU(),
Conv2D(input_channels=32,
num_filters=32,
kernel_size=(5, 5),
stride=(2, 2),
padding='VALID'),
TFBatchNormalization(name=scope + '/d2'),
# BatchNormalization(layer_type='conv', dim=32, short_memory=0.01),
LeakyRELU(),
Conv2D(input_channels=32,
num_filters=32,
kernel_size=(5, 5),
stride=(2, 2),
padding='VALID'),
TFBatchNormalization(name=scope + '/d3'),
# BatchNormalization(layer_type='conv', dim=32, short_memory=0.01),
LeakyRELU(),
# Conv2D(input_channels=32, num_filters=32, kernel_size=(5,5), stride=(2,2), padding='VALID'),
# RELU(),
Flatten(),
Linear(flat_dim, self.bottleneck_dim),
# BatchNormalization(layer_type='fc', dim=self.bottleneck_dim, short_memory=0.01),
TFBatchNormalization(name=scope + '/d4'),
LeakyRELU(),
# Dropout(0.5),
])
class_hn = tg.HiddenNode(prev=[disc_hn],
layers=[
Linear(self.bottleneck_dim,
self.nclass),
Softmax()
])
judge_hn = tg.HiddenNode(
prev=[disc_hn],
layers=[Linear(self.bottleneck_dim, 1),
Sigmoid()])
real_class_en = tg.EndNode(prev=[class_hn])
real_judge_en = tg.EndNode(prev=[judge_hn])
fake_class_en = tg.EndNode(prev=[class_hn])
fake_judge_en = tg.EndNode(prev=[judge_hn])
graph = tg.Graph(start=[dis_real_sn],
end=[real_class_en, real_judge_en])
real_train = graph.train_fprop()
real_valid = graph.test_fprop()
graph = tg.Graph(start=[self.noise_sn, self.gen_real_sn],
end=[fake_class_en, fake_judge_en])
fake_train = graph.train_fprop()
fake_valid = graph.test_fprop()
dis_var_list = tf.get_collection(tf.GraphKeys.GLOBAL_VARIABLES,
scope=scope)
return self.real_ph, real_train, real_valid, fake_train, fake_valid, dis_var_list
def Vanilla_Classifier(X_train, y_train, X_valid, y_valid, restore):
batchsize = 100
learning_rate = 0.001
_, h, w, c = X_train.shape
_, nclass = y_train.shape
g = tf.Graph()
with g.as_default():
data_train = tg.SequentialIterator(X_train, y_train, batchsize=batchsize)
data_valid = tg.SequentialIterator(X_valid, y_valid, batchsize=batchsize)
X_ph = tf.placeholder('float32', [None, h, w, c])
# y_ph = tf.placeholder('float32', [None, nclass])
y_phs = []
for comp in [nclass]:
y_phs.append(tf.placeholder('float32', [None, comp]))
dim = int(h*w*c)
scope = 'encoder'
start = tg.StartNode(input_vars=[X_ph])
h1_Node = tg.HiddenNode(prev=[start],
layers=[Sigmoid(),
TFBatchNormalization(name= scope + '/vanilla1'),
RELU(),
Flatten(),
Sigmoid(),
TFBatchNormalization(name=scope + '/vanilla2')])
h2_Node = tg.HiddenNode(prev=[h1_Node],
layers=[Linear(prev_dim=dim, this_dim=nclass),
Softmax()])
end_nodes = [tg.EndNode(prev=[h2_Node])]
graph = Graph(start=[start], end=end_nodes)
train_outs_sb = graph.train_fprop()
test_outs = graph.test_fprop()
ttl_mse = []
# import pdb; pdb.set_trace()
for y_ph, out in zip(y_phs, train_outs_sb):
#ttl_mse.append(tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(y_ph, out)))
ttl_mse.append(tf.reduce_mean((y_ph-out)**2))
mse = sum(ttl_mse)
#optimizer = tf.train.GradientDescentOptimizer(learning_rate).minimize(mse)
optimizer = tf.train.AdamOptimizer(learning_rate).minimize(mse)
saver = tf.train.Saver()
vardir = './var/2'
if not os.path.exists(vardir):
os.makedirs(vardir)
gpu_options=tf.GPUOptions(per_process_gpu_memory_fraction=0.9)
tf.set_random_seed(1)
init = tf.global_variables_initializer()
with tf.Session(config = tf.ConfigProto(gpu_options = gpu_options)) as sess:
# print '=======session start'
sess.run(init)
if restore == 1:
re_saver = tf.train.Saver()
re_saver.restore(sess, vardir + "/model.ckpt")
print("Model restored.")
max_epoch = 100
temp_acc = []
for epoch in range(max_epoch):
train_error = 0
train_accuracy = 0
ttl_examples = 0
for X_batch, ys in data_train:
feed_dict = {X_ph:X_batch}
for y_ph, y_batch in zip(y_phs, [ys]):
feed_dict[y_ph] = y_batch
sess.run(optimizer, feed_dict=feed_dict)
train_outs = sess.run(train_outs_sb, feed_dict=feed_dict)
train_error += total_mse(train_outs, [ys])[0]
train_accuracy += total_accuracy(train_outs, [ys])[0]
ttl_examples += len(X_batch)
valid_error = 0
valid_accuracy = 0
ttl_examples = 0
for X_batch, ys in data_valid:
feed_dict = {X_ph:X_batch}
for y_ph, y_batch in zip(y_phs, [ys]):
feed_dict[y_ph] = y_batch
valid_outs = sess.run(test_outs, feed_dict=feed_dict)
valid_error += total_mse(valid_outs, [ys])[0]
valid_accuracy += total_accuracy(valid_outs, [ys])[0]
ttl_examples += len(X_batch)
save_path = saver.save(sess, vardir + "/model.ckpt")
# print("Model saved in file: %s" % save_path)
temp_acc.append(valid_accuracy/float(ttl_examples))
print 'max accuracy is:\t', max(temp_acc)
def Encoder_Classifier(X_train, y_train, X_valid, y_valid, restore):
batchsize = 100
learning_rate = 0.001
_, h, w, c = X_train.shape
_, nclass = y_train.shape
g = tf.Graph()
with g.as_default():
data_train = tg.SequentialIterator(X_train, y_train, batchsize=batchsize)
data_valid = tg.SequentialIterator(X_valid, y_valid, batchsize=batchsize)
X_ph = tf.placeholder('float32', [None, h, w, c])
y_phs = []
for comp in [nclass]:
y_phs.append(tf.placeholder('float32', [None, comp]))
start = tg.StartNode(input_vars=[X_ph])
h1, w1 = valid(h, w, filters=(5,5), strides=(1,1))
h2, w2 = valid(h1, w1, filters=(5,5), strides=(2,2))
h3, w3 = valid(h2, w2, filters=(5,5), strides=(2,2))
flat_dim = int(h3*w3*32)
scope = 'encoder'
bottleneck_dim = 300
enc_hn = tg.HiddenNode(prev=[start],
layers=[Conv2D(input_channels=c, num_filters=32, kernel_size=(5,5), stride=(1,1), padding='VALID'),
TFBatchNormalization(name=scope + '/genc1'),
RELU(),
Conv2D(input_channels=32, num_filters=32, kernel_size=(5,5), stride=(2,2), padding='VALID'),
TFBatchNormalization(name=scope + '/genc2'),
RELU(),
Conv2D(input_channels=32, num_filters=32, kernel_size=(5,5), stride=(2,2), padding='VALID'),
TFBatchNormalization(name=scope + '/genc3'),
RELU(),
Flatten(),
Linear(flat_dim, 300),
TFBatchNormalization(name=scope + '/genc4'),
RELU(),
Linear(300, bottleneck_dim),
Tanh()
])
h2_Node = tg.HiddenNode(prev=[enc_hn],
layers=[Linear(prev_dim=bottleneck_dim, this_dim=nclass),
Softmax()])
end_nodes = [tg.EndNode(prev=[h2_Node])]
graph = Graph(start=[start], end=end_nodes)
train_outs_sb = graph.train_fprop()
test_outs = graph.test_fprop()
ttl_mse = []
# import pdb; pdb.set_trace()
for y_ph, out in zip(y_phs, train_outs_sb):
#ttl_mse.append(tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(y_ph, out)))
ttl_mse.append(tf.reduce_mean((y_ph-out)**2))
mse = sum(ttl_mse)
#optimizer = tf.train.GradientDescentOptimizer(learning_rate).minimize(mse)
optimizer = tf.train.AdamOptimizer(learning_rate).minimize(mse)
gpu_options=tf.GPUOptions(per_process_gpu_memory_fraction=0.9)
# saver_init = tf.train.Saver()
saver = tf.train.Saver()
vardir = './var/1'
if not os.path.exists(vardir):
os.makedirs(vardir)
tf.set_random_seed(1)
init = tf.global_variables_initializer()
with tf.Session(config = tf.ConfigProto(gpu_options = gpu_options)) as sess:
sess.run(init)
if restore == 1:
re_saver = tf.train.Saver()
re_saver.restore(sess, vardir + "/model.ckpt")
print("Model restored.")
# save_path = saver_init.save(sess, vardir + "/init.ckpt")
# print("Model saved in file: %s" % save_path)
max_epoch = 2
temp_acc = []
for epoch in range(max_epoch):
# print 'epoch:', epoch
train_error = 0
train_accuracy = 0
ttl_examples = 0
for X_batch, ys in data_train:
feed_dict = {X_ph:X_batch}
for y_ph, y_batch in zip(y_phs, [ys]):
feed_dict[y_ph] = y_batch
# import pdb; pdb.set_trace()
sess.run(optimizer, feed_dict=feed_dict)
train_outs = sess.run(train_outs_sb, feed_dict=feed_dict)
train_error += total_mse(train_outs, [ys])[0]
train_accuracy += total_accuracy(train_outs, [ys])[0]
ttl_examples += len(X_batch)
valid_error = 0
valid_accuracy = 0
ttl_examples = 0
for X_batch, ys in data_valid:
feed_dict = {X_ph:X_batch}
for y_ph, y_batch in zip(y_phs, [ys]):
feed_dict[y_ph] = y_batch
valid_outs = sess.run(test_outs, feed_dict=feed_dict)
valid_error += total_mse(valid_outs, [ys])[0]
valid_accuracy += total_accuracy(valid_outs, [ys])[0]
ttl_examples += len(X_batch)
temp_acc.append(valid_accuracy/float(ttl_examples))
save_path = saver.save(sess, vardir + "/model.ckpt")
print("Model saved in file: %s" % save_path)
print 'max accuracy is:\t', max(temp_acc)
def CNN_Classifier(X_train, y_train, X_valid, y_valid):
batchsize = 64
learning_rate = 0.001
_, h, w, c = X_train.shape
_, nclass = y_train.shape
data_train = tg.SequentialIterator(X_train, y_train, batchsize=batchsize)
data_valid = tg.SequentialIterator(X_valid, y_valid, batchsize=batchsize)
X_ph = tf.placeholder('float32', [None, h, w, c])
y_phs = []
for comp in [nclass]:
y_phs.append(tf.placeholder('float32', [None, comp]))
start = tg.StartNode(input_vars=[X_ph])
h, w = same(in_height=h, in_width=w, strides=(1,1), filters=(2,2))
h, w = same(in_height=h, in_width=w, strides=(2,2), filters=(2,2))
#h1, w1 = valid(ch_embed_dim, word_len, strides=(1,1), filters=(ch_embed_dim,4))
dim = int(h * w * c * 10)
h1_Node = tg.HiddenNode(prev=[start],
layers=[Conv2D(input_channels=c, num_filters=10, padding='SAME', kernel_size=(2,2), stride=(1,1)),
MaxPooling(poolsize=(2,2), stride=(2,2), padding='SAME'),
Reshape(shape=(-1, dim))] )
h2_Node = tg.HiddenNode(prev=[h1_Node],
layers=[Linear(prev_dim=dim, this_dim=nclass),
Softmax()])
end_nodes = [tg.EndNode(prev=[h2_Node])]
graph = Graph(start=[start], end=end_nodes)
train_outs_sb = graph.train_fprop()
test_outs = graph.test_fprop()
ttl_mse = []
# import pdb; pdb.set_trace()
for y_ph, out in zip(y_phs, train_outs_sb):
#ttl_mse.append(tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(y_ph, out)))
ttl_mse.append(tf.reduce_mean((y_ph-out)**2))
mse = sum(ttl_mse)
#optimizer = tf.train.GradientDescentOptimizer(learning_rate).minimize(mse)
optimizer = tf.train.AdamOptimizer(learning_rate).minimize(mse)
gpu_options=tf.GPUOptions(per_process_gpu_memory_fraction=0.9)
saver = tf.train.Saver()
vardir = './var/1'
if not os.path.exists(vardir):
os.makedirs(vardir)
with tf.Session(config = tf.ConfigProto(gpu_options = gpu_options)) as sess:
init = tf.global_variables_initializer()
sess.run(init)
max_epoch = 100
temp_acc = []
for epoch in range(max_epoch):
# print 'epoch:', epoch
train_error = 0
train_accuracy = 0
ttl_examples = 0
for X_batch, ys in data_train:
feed_dict = {X_ph:X_batch}
for y_ph, y_batch in zip(y_phs, [ys]):
feed_dict[y_ph] = y_batch
# import pdb; pdb.set_trace()
sess.run(optimizer, feed_dict=feed_dict)
train_outs = sess.run(train_outs_sb, feed_dict=feed_dict)
train_error += total_mse(train_outs, [ys])[0]
train_accuracy += total_accuracy(train_outs, [ys])[0]
ttl_examples += len(X_batch)
# print 'train mse', train_error/float(ttl_examples)
# print 'train accuracy', train_accuracy/float(ttl_examples)
valid_error = 0
valid_accuracy = 0
ttl_examples = 0
for X_batch, ys in data_valid:
feed_dict = {X_ph:X_batch}
for y_ph, y_batch in zip(y_phs, [ys]):
feed_dict[y_ph] = y_batch
valid_outs = sess.run(test_outs, feed_dict=feed_dict)
valid_error += total_mse(valid_outs, [ys])[0]
valid_accuracy += total_accuracy(valid_outs, [ys])[0]
ttl_examples += len(X_batch)
# print 'valid mse', valid_error/float(ttl_examples)
# print 'valid accuracy', valid_accuracy/float(ttl_examples)
temp_acc.append(valid_accuracy/float(ttl_examples))
save_path = saver.save(sess, vardir + "/model.ckpt")
print("Model saved in file: %s" % save_path)
print 'max accuracy is:\t', max(temp_acc)
def __init__(self, nclass, h, w, c):
layers = []
layers.append(
Conv2D(input_channels=c,
num_filters=96,
kernel_size=(3, 3),
stride=(1, 1),
padding='SAME'))
layers.append(RELU())
h, w = same(in_height=h, in_width=w, stride=(1, 1), kernel_size=(3, 3))
layers.append(BatchNormalization(input_shape=[h, w, 96]))
layers.append(
Conv2D(input_channels=96,
num_filters=96,
kernel_size=(3, 3),
stride=(1, 1),
padding='SAME'))
layers.append(RELU())
h, w = same(in_height=h, in_width=w, stride=(1, 1), kernel_size=(3, 3))
layers.append(Dropout(0.5))
layers.append(
Conv2D(input_channels=96,
num_filters=96,
kernel_size=(3, 3),
stride=(2, 2),
padding='SAME'))
layers.append(RELU())
h, w = same(in_height=h, in_width=w, stride=(2, 2), kernel_size=(3, 3))
layers.append(BatchNormalization(input_shape=[h, w, 96]))
layers.append(
Conv2D(input_channels=96,
num_filters=192,
kernel_size=(3, 3),
stride=(1, 1),
padding='SAME'))
layers.append(RELU())
h, w = same(in_height=h, in_width=w, stride=(1, 1), kernel_size=(3, 3))
layers.append(Dropout(0.5))
layers.append(
Conv2D(input_channels=192,
num_filters=192,
kernel_size=(3, 3),
stride=(1, 1),
padding='SAME'))
layers.append(RELU())
h, w = same(in_height=h, in_width=w, stride=(1, 1), kernel_size=(3, 3))
layers.append(BatchNormalization(input_shape=[h, w, 192]))
layers.append(
Conv2D(input_channels=192,
num_filters=192,
kernel_size=(3, 3),
stride=(2, 2),
padding='SAME'))
layers.append(RELU())
h, w = same(in_height=h, in_width=w, stride=(2, 2), kernel_size=(3, 3))
layers.append(Dropout(0.5))
layers.append(
Conv2D(input_channels=192,
num_filters=192,
kernel_size=(3, 3),
stride=(1, 1),
padding='SAME'))
layers.append(RELU())
h, w = same(in_height=h, in_width=w, stride=(1, 1), kernel_size=(3, 3))
layers.append(BatchNormalization(input_shape=[h, w, 192]))
layers.append(
Conv2D(input_channels=192,
num_filters=192,
kernel_size=(1, 1),
stride=(1, 1),
padding='SAME'))
layers.append(RELU())
h, w = same(in_height=h, in_width=w, stride=(1, 1), kernel_size=(1, 1))
layers.append(Dropout(0.5))
layers.append(
Conv2D(input_channels=192,
num_filters=nclass,
kernel_size=(1, 1),
stride=(1, 1),
padding='SAME'))
layers.append(RELU())
h, w = same(in_height=h, in_width=w, stride=(1, 1), kernel_size=(1, 1))
layers.append(BatchNormalization(input_shape=[h, w, nclass]))
layers.append(
AvgPooling(poolsize=(h, w), stride=(1, 1), padding='VALID'))
layers.append(Flatten())
layers.append(Softmax())
self.startnode = tg.StartNode(input_vars=[None])
model_hn = tg.HiddenNode(prev=[self.startnode], layers=layers)
self.endnode = tg.EndNode(prev=[model_hn])
def discriminator_allconv(self):
if not self.generator_called:
raise Exception(
'self.generator() has to be called first before self.discriminator()'
)
scope = 'Discriminator'
with self.tf_graph.as_default():
with tf.name_scope(scope):
# h1, w1 = valid(self.h, self.w, kernel_size=(5,5), stride=(1,1))
# h2, w2 = valid(h1, w1, kernel_size=(5,5), stride=(2,2))
# h3, w3 = valid(h2, w2, kernel_size=(5,5), stride=(2,2))
# flat_dim = int(h3*w3*32)
dis_real_sn = tg.StartNode(input_vars=[self.real_ph])
# fake_ph = tf.placeholder('float32', [None, self.h, self.w, 1], name='fake')
# fake_sn = tg.StartNode(input_vars=[fake_ph])
h, w = same(in_height=self.h,
in_width=self.w,
stride=(1, 1),
kernel_size=(3, 3))
h, w = same(in_height=h,
in_width=w,
stride=(1, 1),
kernel_size=(3, 3))
h, w = same(in_height=h,
in_width=w,
stride=(2, 2),
kernel_size=(3, 3))
h, w = same(in_height=h,
in_width=w,
stride=(1, 1),
kernel_size=(3, 3))
h, w = same(in_height=h,
in_width=w,
stride=(1, 1),
kernel_size=(3, 3))
h, w = same(in_height=h,
in_width=w,
stride=(2, 2),
kernel_size=(3, 3))
h, w = same(in_height=h,
in_width=w,
stride=(1, 1),
kernel_size=(1, 1))
h, w = same(in_height=h,
in_width=w,
stride=(1, 1),
kernel_size=(3, 3))
h, w = same(in_height=h,
in_width=w,
stride=(1, 1),
kernel_size=(1, 1))
print('h, w', h, w)
print('===============')
# h, w = valid(in_height=h, in_width=w, stride=(1,1), kernel_size=(h,w))
disc_hn = tg.HiddenNode(
prev=[dis_real_sn, self.gen_hn],
layers=[
Dropout(0.2),
# TFBatchNormalization(name='b0'),
Conv2D(input_channels=self.c,
num_filters=96,
kernel_size=(3, 3),
stride=(1, 1),
padding='SAME'),
LeakyRELU(),
TFBatchNormalization(name='b1'),
# Dropout(0.5),
Conv2D(input_channels=96,
num_filters=96,
kernel_size=(3, 3),
stride=(1, 1),
padding='SAME'),
LeakyRELU(),
# TFBatchNormalization(name='b2'),
Dropout(0.5),
Conv2D(input_channels=96,
num_filters=96,
kernel_size=(3, 3),
stride=(2, 2),
padding='SAME'),
LeakyRELU(),
TFBatchNormalization(name='b3'),
# Dropout(0.5),
Conv2D(input_channels=96,
num_filters=192,
kernel_size=(3, 3),
stride=(1, 1),
padding='SAME'),
LeakyRELU(),
# TFBatchNormalization(name='b4'),
Dropout(0.5),
Conv2D(input_channels=192,
num_filters=192,
kernel_size=(3, 3),
stride=(1, 1),
padding='SAME'),
LeakyRELU(),
TFBatchNormalization(name='b5'),
# Dropout(0.5),
Conv2D(input_channels=192,
num_filters=192,
kernel_size=(3, 3),
stride=(2, 2),
padding='SAME'),
LeakyRELU(),
# TFBatchNormalization(name='b6'),
Dropout(0.5),
Conv2D(input_channels=192,
num_filters=192,
kernel_size=(3, 3),
stride=(1, 1),
padding='SAME'),
LeakyRELU(),
TFBatchNormalization(name='b7'),
# Dropout(0.5),
Conv2D(input_channels=192,
num_filters=192,
kernel_size=(1, 1),
stride=(1, 1),
padding='SAME'),
LeakyRELU(),
# TFBatchNormalization(name='b8'),
Dropout(0.5),
Conv2D(input_channels=192,
num_filters=self.nclass,
kernel_size=(1, 1),
stride=(1, 1),
padding='SAME'),
LeakyRELU(),
TFBatchNormalization(name='b9'),
# Dropout(0.5),
AvgPooling(poolsize=(h, w),
stride=(1, 1),
padding='VALID'),
Flatten(),
])
print('h,w', h, w)
print('==============')
class_hn = tg.HiddenNode(
prev=[disc_hn],
layers=[
Linear(self.nclass, self.nclass),
# Softmax()
])
judge_hn = tg.HiddenNode(
prev=[disc_hn],
layers=[
Linear(self.nclass, 1),
# Sigmoid()
])
real_class_en = tg.EndNode(prev=[class_hn])
real_judge_en = tg.EndNode(prev=[judge_hn])
fake_class_en = tg.EndNode(prev=[class_hn])
fake_judge_en = tg.EndNode(prev=[judge_hn])
graph = tg.Graph(start=[dis_real_sn],
end=[real_class_en, real_judge_en])
real_train = graph.train_fprop()
real_valid = graph.test_fprop()
graph = tg.Graph(start=[self.noise_sn, self.gen_real_sn],
end=[fake_class_en, fake_judge_en])
fake_train = graph.train_fprop()
fake_valid = graph.test_fprop()
dis_var_list = tf.get_collection(tf.GraphKeys.GLOBAL_VARIABLES,
scope=scope)
return self.real_ph, real_train, real_valid, fake_train, fake_valid, dis_var_list
def generator(self):
self.generator_called = True
with self.tf_graph.as_default():
scope = 'Generator'
with tf.name_scope(scope):
h1, w1 = valid(self.h,
self.w,
kernel_size=(5, 5),
stride=(1, 1))
h2, w2 = valid(h1, w1, kernel_size=(5, 5), stride=(2, 2))
h3, w3 = valid(h2, w2, kernel_size=(5, 5), stride=(2, 2))
flat_dim = int(h3 * w3 * 32)
print('h1:{}, w1:{}'.format(h1, w1))
print('h2:{}, w2:{}'.format(h2, w2))
print('h3:{}, w3:{}'.format(h3, w3))
print('flat dim:{}'.format(flat_dim))
self.gen_real_sn = tg.StartNode(input_vars=[self.real_ph])
enc_hn = tg.HiddenNode(
prev=[self.gen_real_sn],
layers=[
Conv2D(input_channels=self.c,
num_filters=32,
kernel_size=(5, 5),
stride=(1, 1),
padding='VALID'),
TFBatchNormalization(name=scope + '/genc1'),
RELU(),
Conv2D(input_channels=32,
num_filters=32,
kernel_size=(5, 5),
stride=(2, 2),
padding='VALID'),
TFBatchNormalization(name=scope + '/genc2'),
RELU(),
Conv2D(input_channels=32,
num_filters=32,
kernel_size=(5, 5),
stride=(2, 2),
padding='VALID'),
TFBatchNormalization(name=scope + '/genc3'),
RELU(),
# Conv2D(input_channels=32, num_filters=32, kernel_size=(5,5), stride=(2,2), padding='VALID'),
# RELU(),
Flatten(),
Linear(flat_dim, 300),
TFBatchNormalization(name=scope + '/genc4'),
RELU(),
Linear(300, self.bottleneck_dim),
Tanh(),
])
self.noise_sn = tg.StartNode(input_vars=[self.noise_ph])
self.gen_hn = tg.HiddenNode(
prev=[self.noise_sn, enc_hn],
input_merge_mode=Sum(),
layers=[
Linear(self.bottleneck_dim, flat_dim),
RELU(),
######[ Method 0 ]######
# Reshape((-1, h3, w3, 32)),
# Conv2D_Transpose(input_channels=32, num_filters=100, output_shape=(h2,w2),
# kernel_size=(5,5), stride=(2,2), padding='VALID'),
######[ End Method 0 ]######
######[ Method 1 ]######
Reshape((-1, 1, 1, flat_dim)),
# Reshape((-1, h))
Conv2D_Transpose(input_channels=flat_dim,
num_filters=200,
output_shape=(h3, w3),
kernel_size=(h3, w3),
stride=(1, 1),
padding='VALID'),
# BatchNormalization(layer_type='conv', dim=200, short_memory=0.01),
TFBatchNormalization(name=scope + '/g1'),
RELU(),
Conv2D_Transpose(input_channels=200,
num_filters=100,
output_shape=(h2, w2),
kernel_size=(5, 5),
stride=(2, 2),
padding='VALID'),
# BatchNormalization(layer_type='conv', dim=100, short_memory=0.01),
######[ End Method 1 ]######
TFBatchNormalization(name=scope + '/g2'),
RELU(),
Conv2D_Transpose(input_channels=100,
num_filters=50,
output_shape=(h1, w1),
kernel_size=(5, 5),
stride=(2, 2),
padding='VALID'),
# BatchNormalization(layer_type='conv', dim=50, short_memory=0.01),
TFBatchNormalization(name=scope + '/g3'),
RELU(),
Conv2D_Transpose(input_channels=50,
num_filters=self.c,
output_shape=(self.h, self.w),
kernel_size=(5, 5),
stride=(1, 1),
padding='VALID'),
SetShape((-1, self.h, self.w, self.c)),
Sigmoid()
])
h, w = valid(self.h, self.w, kernel_size=(5, 5), stride=(1, 1))
h, w = valid(h, w, kernel_size=(5, 5), stride=(2, 2))
h, w = valid(h, w, kernel_size=(5, 5), stride=(2, 2))
h, w = valid(h, w, kernel_size=(h3, w3), stride=(1, 1))
y_en = tg.EndNode(prev=[self.gen_hn])
graph = tg.Graph(start=[self.noise_sn, self.gen_real_sn],
end=[y_en])
G_train_sb = graph.train_fprop()[0]
G_test_sb = graph.test_fprop()[0]
gen_var_list = tf.get_collection(tf.GraphKeys.GLOBAL_VARIABLES,
scope=scope)
return self.y_ph, self.noise_ph, G_train_sb, G_test_sb, gen_var_list
def generator(self):
self.generator_called = True
with self.tf_graph.as_default():
scope = 'Generator'
with tf.name_scope(scope):
# X_ph = tf.placeholder('float32', [None, self.h, self.w, 1], name='X')
# X_sn = tg.StartNode(input_vars=[X_ph])
noise_ph = tf.placeholder('float32',
[None, self.bottleneck_dim],
name='noise')
self.noise_sn = tg.StartNode(input_vars=[noise_ph])
h1, w1 = valid(self.h,
self.w,
kernel_size=(5, 5),
stride=(1, 1))
h2, w2 = valid(h1, w1, kernel_size=(5, 5), stride=(2, 2))
h3, w3 = valid(h2, w2, kernel_size=(5, 5), stride=(2, 2))
flat_dim = int(h3 * w3 * 32)
print('h1:{}, w1:{}'.format(h1, w1))
print('h2:{}, w2:{}'.format(h2, w2))
print('h3:{}, w3:{}'.format(h3, w3))
print('flat dim:{}'.format(flat_dim))
# enc_hn = tg.HiddenNode(prev=[X_sn],
# layers=[Conv2D(input_channels=1, num_filters=32, kernel_size=(5,5), stride=(1,1), padding='VALID'),
# RELU(),
# Conv2D(input_channels=32, num_filters=32, kernel_size=(5,5), stride=(2,2), padding='VALID'),
# RELU(),
# Conv2D(input_channels=32, num_filters=32, kernel_size=(5,5), stride=(2,2), padding='VALID'),
# RELU(),
# # Conv2D(input_channels=32, num_filters=32, kernel_size=(5,5), stride=(2,2), padding='VALID'),
# # RELU(),
# Flatten(),
# Linear(flat_dim, 300),
# RELU(),
# # seq.add(Dropout(0.5))
# Linear(300, self.bottleneck_dim),
# Tanh(),
# ])
y_ph = tf.placeholder('float32', [None, self.nclass], name='y')
self.y_sn = tg.StartNode(input_vars=[y_ph])
noise_hn = tg.HiddenNode(prev=[self.noise_sn, self.y_sn],
input_merge_mode=Concat(1))
self.gen_hn = tg.HiddenNode(
prev=[noise_hn],
layers=[
Linear(self.bottleneck_dim + 10, flat_dim),
RELU(),
######[ Method 0 ]######
# Reshape((-1, h3, w3, 32)),
# Conv2D_Transpose(input_channels=32, num_filters=100, output_shape=(h2,w2),
# kernel_size=(5,5), stride=(2,2), padding='VALID'),
######[ End Method 0 ]######
######[ Method 1 ]######
Reshape((-1, 1, 1, flat_dim)),
Conv2D_Transpose(input_channels=flat_dim,
num_filters=200,
output_shape=(2, 2),
kernel_size=(2, 2),
stride=(1, 1),
padding='VALID'),
TFBatchNormalization(name=scope + '/dc1'),
RELU(),
Conv2D_Transpose(input_channels=200,
num_filters=100,
output_shape=(h2, w2),
kernel_size=(9, 9),
stride=(1, 1),
padding='VALID'),
######[ End Method 1 ]######
TFBatchNormalization(name=scope + '/dc2'),
RELU(),
Conv2D_Transpose(input_channels=100,
num_filters=50,
output_shape=(h1, w1),
kernel_size=(5, 5),
stride=(2, 2),
padding='VALID'),
TFBatchNormalization(name=scope + '/dc3'),
RELU(),
Conv2D_Transpose(input_channels=50,
num_filters=1,
output_shape=(self.h, self.w),
kernel_size=(5, 5),
stride=(1, 1),
padding='VALID'),
SetShape((-1, self.h, self.w, 1)),
Sigmoid()
])
y_en = tg.EndNode(prev=[self.gen_hn])
graph = tg.Graph(start=[self.noise_sn, self.y_sn], end=[y_en])
G_train_sb = graph.train_fprop()[0]
G_test_sb = graph.test_fprop()[0]
# import pdb; pdb.set_trace()
gen_var_list = tf.get_collection(tf.GraphKeys.GLOBAL_VARIABLES,
scope=scope)
return y_ph, noise_ph, G_train_sb, G_test_sb, gen_var_list
def classifier(X_ph, X_gen_ph, h, w):
with tf.variable_scope('Classifier'):
X_sn = tg.StartNode(input_vars=[X_ph])
X_gen_sn = tg.StartNode(input_vars=[X_gen_ph])
h1, w1 = same(in_height=h,
in_width=w,
stride=(1, 1),
kernel_size=(3, 3))
h2, w2 = same(in_height=h1,
in_width=w1,
stride=(2, 2),
kernel_size=(2, 2))
h3, w3 = same(in_height=h2,
in_width=w2,
stride=(1, 1),
kernel_size=(3, 3))
h4, w4 = same(in_height=h3,
in_width=w3,
stride=(2, 2),
kernel_size=(2, 2))
print('---', h, w)
X_hn = tg.HiddenNode(prev=[X_sn],
layers=[
Conv2D(input_channels=1,
num_filters=32,
kernel_size=(3, 3),
stride=(1, 1),
padding='SAME'),
BatchNormalization(input_shape=[h1, w1, 32]),
RELU(),
MaxPooling(poolsize=(2, 2),
stride=(2, 2),
padding='SAME'),
LRN(),
Conv2D(input_channels=32,
num_filters=64,
kernel_size=(3, 3),
stride=(1, 1),
padding='SAME'),
BatchNormalization(input_shape=[h3, w3, 64]),
RELU(),
MaxPooling(poolsize=(2, 2),
stride=(2, 2),
padding='SAME'),
Flatten(),
])
X_gen_hn = tg.HiddenNode(
prev=[X_gen_sn],
layers=[
Conv2D(input_channels=1,
num_filters=32,
kernel_size=(3, 3),
stride=(1, 1),
padding='SAME'),
BatchNormalization(input_shape=[h1, w1, 32]),
RELU(),
MaxPooling(poolsize=(2, 2), stride=(2, 2), padding='SAME'),
LRN(),
Conv2D(input_channels=32,
num_filters=64,
kernel_size=(3, 3),
stride=(1, 1),
padding='SAME'),
BatchNormalization(input_shape=[h3, w3, 64]),
RELU(),
MaxPooling(poolsize=(2, 2), stride=(2, 2), padding='SAME'),
Flatten(),
])
print('===', h4 * w4 * 64 * 2)
merge_hn = tg.HiddenNode(prev=[X_hn, X_gen_hn],
input_merge_mode=Concat(),
layers=[
Linear(h4 * w4 * 64 * 2, 100),
RELU(),
BatchNormalization(input_shape=[100]),
Linear(100, 1),
Sigmoid()
])
en = tg.EndNode(prev=[merge_hn])
graph = tg.Graph(start=[X_sn, X_gen_sn], end=[en])
y_train, = graph.train_fprop()
y_test, = graph.test_fprop()
return y_train, y_test
def discriminator(self):
if not self.generator_called:
raise Exception(
'self.generator() has to be called first before self.discriminator()'
)
scope = 'Discriminator'
with self.tf_graph.as_default():
with tf.name_scope(scope):
h1, w1 = valid(self.h,
self.w,
kernel_size=(5, 5),
stride=(1, 1))
h2, w2 = valid(h1, w1, kernel_size=(5, 5), stride=(2, 2))
h3, w3 = valid(h2, w2, kernel_size=(5, 5), stride=(2, 2))
flat_dim = int(h3 * w3 * 32)
real_ph = tf.placeholder('float32', [None, self.h, self.w, 1],
name='real')
real_sn = tg.StartNode(input_vars=[real_ph])
# fake_ph = tf.placeholder('float32', [None, self.h, self.w, 1], name='fake')
# fake_sn = tg.StartNode(input_vars=[fake_ph])
disc_hn = tg.HiddenNode(
prev=[real_sn, self.gen_hn],
layers=[
Conv2D(input_channels=1,
num_filters=32,
kernel_size=(5, 5),
stride=(1, 1),
padding='VALID'),
TFBatchNormalization(name=scope + '/c1'),
LeakyRELU(),
Conv2D(input_channels=32,
num_filters=32,
kernel_size=(5, 5),
stride=(2, 2),
padding='VALID'),
TFBatchNormalization(name=scope + '/c2'),
LeakyRELU(),
Conv2D(input_channels=32,
num_filters=32,
kernel_size=(5, 5),
stride=(2, 2),
padding='VALID'),
TFBatchNormalization(name=scope + '/c3'),
LeakyRELU(),
# Conv2D(input_channels=32, num_filters=32, kernel_size=(5,5), stride=(2,2), padding='VALID'),
# RELU(),
Flatten(),
Linear(flat_dim, self.bottleneck_dim),
TFBatchNormalization(name=scope + '/l1'),
LeakyRELU(),
# Dropout(0.5),
])
class_hn = tg.HiddenNode(prev=[disc_hn],
layers=[
Linear(self.bottleneck_dim,
self.nclass),
Softmax()
])
judge_hn = tg.HiddenNode(
prev=[disc_hn],
layers=[
Linear(self.bottleneck_dim, 1),
# Sigmoid()
])
real_class_en = tg.EndNode(prev=[class_hn])
real_judge_en = tg.EndNode(prev=[judge_hn])
fake_class_en = tg.EndNode(prev=[class_hn])
fake_judge_en = tg.EndNode(prev=[judge_hn])
graph = tg.Graph(start=[real_sn],
end=[real_class_en, real_judge_en])
real_train = graph.train_fprop()
real_valid = graph.test_fprop()
# dis_var_list = graph.variables
# for var in dis_var_list:
# print var.name
graph = tg.Graph(start=[self.noise_sn, self.y_sn],
end=[fake_class_en, fake_judge_en])
fake_train = graph.train_fprop()
fake_valid = graph.test_fprop()
# print('========')
# for var in graph.variables:
# print var.name
dis_var_list = tf.get_collection(tf.GraphKeys.GLOBAL_VARIABLES,
scope=scope)
# for var in dis_var_list:
# print(var.name)
#
# print('=========')
# for var in tf.global_variables():
# print(var.name)
# import pdb; pdb.set_trace()
# print()
# graph = tg.Graph(start=[G_sn], end=[class_en, judge_en])
# class_train_sb, judge_train_sb = graph.train_fprop() # symbolic outputs
# class_test_sb, judge_test_sb = graph.test_fprop() # symbolic outputs
return real_ph, real_train, real_valid, fake_train, fake_valid, dis_var_list
