def run(self, img):
H, W = get_dim(img)
count = 0
while count < self._num:
(y, x, h, w) = self.__get_rand_block(H, W)
tmp = img[y:y + h, x:x + w]
count += 1
yield tmp, (y, x, h, w)
def run(self, img):
H, W = get_dim(img)
count = 0
while count < self._num:
(y, x, h, w) = self.__get_rand_block(H, W)
tmp = img[y:y+h, x:x+w]
count += 1
yield tmp, (y, x, h, w)
def set_model(self, figs, labels, is_training, reuse=False):
fig_shape = figs.get_shape().as_list()
height, width = fig_shape[1:3]
class_num = get_dim(labels)
with tf.variable_scope(self.name_scope_label, reuse=reuse):
tmp = linear_layer(labels, class_num, height * width, 'reshape')
tmp = tf.reshape(tmp, [-1, height, width, 1])
h = tf.concat((figs, tmp), 3)
# convolution
with tf.variable_scope(self.name_scope_conv, reuse=reuse):
for i, (in_chan, out_chan) in enumerate(
zip(self.layer_chanels, self.layer_chanels[1:])):
conved = conv_layer(inputs=h,
out_num=out_chan,
filter_width=5,
filter_hight=5,
stride=2,
l_id=i)
if i == 0:
h = tf.nn.relu(conved)
#h = lrelu(conved)
else:
bn_conved = batch_norm(conved, i, is_training)
h = tf.nn.relu(bn_conved)
#h = lrelu(bn_conved)
# full connect
dim = get_dim(h)
h = tf.reshape(h, [-1, dim])
with tf.variable_scope(self.name_scope_fc, reuse=reuse):
h = linear_layer(h, dim, self.fc_dim, 'fc')
h = batch_norm(h, 'en_fc_bn', is_training)
h = tf.nn.relu(h)
mu = linear_layer(h, self.fc_dim, self.z_dim, 'mu')
log_sigma = linear_layer(h, self.fc_dim, self.z_dim, 'sigma')
return mu, log_sigma
def run(self, img):
self._img = img.copy()
M, N = get_dim(img)
tmp = MyThreshold(val=1, ksize=0).run(img)
def enough_elem(x):
return x.sum() / (self._w * self._h) * 100 > self._mep
pts = [(y, x) for y in np.arange(0, M - self._w, self._w)
for x in np.arange(0, N - self._h, self._h)
if enough_elem(tmp[y:y + self._h, x:x + self._w])]
self._pts = pts
return pts
def run(self, img):
self._img = img.copy()
M, N = get_dim(img)
tmp = MyThreshold(val=1, ksize=0).run(img)
def enough_elem(x):
return x.sum()/(self._w * self._h)*100 > self._mep
pts = [(y, x)
for y in np.arange(0, M - self._w, self._w)
for x in np.arange(0, N - self._h, self._h)
if enough_elem(tmp[y:y+self._h, x:x+self._w])]
self._pts = pts
return pts
def set_model(self, figs, is_training, reuse=False):
# return only logits
h = figs
# convolution
with tf.variable_scope(self.name_scope_conv, reuse=reuse):
for i, (in_chan, out_chan) in enumerate(
zip(self.layer_chanels, self.layer_chanels[1:])):
if i == 0:
conved = conv_layer(inputs=h,
out_num=out_chan,
filter_width=5,
filter_hight=5,
stride=1,
l_id=i)
h = tf.nn.relu(conved)
#h = lrelu(conved)
else:
conved = conv_layer(inputs=h,
out_num=out_chan,
filter_width=5,
filter_hight=5,
stride=2,
l_id=i)
bn_conved = batch_norm(conved, i, is_training)
h = tf.nn.relu(bn_conved)
#h = lrelu(bn_conved)
feature_image = h
# full connect
dim = get_dim(h)
h = tf.reshape(h, [-1, dim])
with tf.variable_scope(self.name_scope_fc, reuse=reuse):
weights = get_weights('fc', [dim, self.fc_dim], 0.02)
biases = get_biases('fc', [self.fc_dim], 0.0)
h = tf.matmul(h, weights) + biases
h = batch_norm(h, 'fc', is_training)
h = tf.nn.relu(h)
weights = get_weights('fc2', [self.fc_dim, 1], 0.02)
biases = get_biases('fc2', [1], 0.0)
h = tf.matmul(h, weights) + biases
return h, feature_image
def set_model(self, figs, is_training, reuse=False):
u'''
return only logits. not sigmoid(logits).
'''
h = figs
# convolution
with tf.variable_scope(self.name_scope_conv, reuse=reuse):
for i, (in_chan, out_chan) in enumerate(
zip(self.layer_chanels, self.layer_chanels[1:])):
conved = conv_layer(inputs=h,
out_num=out_chan,
filter_width=5,
filter_hight=5,
stride=2,
l_id=i)
if i == 0:
h = tf.nn.relu(conved)
#h = lrelu(conved)
else:
bn_conved = batch_norm(conved, i, is_training)
h = tf.nn.relu(bn_conved)
#h = lrelu(bn_conved)
# full connect
dim = get_dim(h)
h = tf.reshape(h, [-1, dim])
with tf.variable_scope(self.name_scope_fc, reuse=reuse):
weights = get_weights('fc', [dim, self.fc_dim], 0.02)
biases = get_biases('fc', [self.fc_dim], 0.0)
h = tf.matmul(h, weights) + biases
h = batch_norm(h, 'en_fc_bn', is_training)
h = tf.nn.relu(h)
weights = get_weights('mu', [self.fc_dim, self.z_dim], 0.02)
biases = get_biases('mu', [self.z_dim], 0.0)
mu = tf.matmul(h, weights) + biases
weights = get_weights('sigma', [self.fc_dim, self.z_dim], 0.02)
biases = get_biases('sigma', [self.z_dim], 0.0)
log_sigma = tf.matmul(h, weights) + biases
return mu, log_sigma
def set_model(self, figs, is_training, reuse = False):
u'''
return only logits.
'''
h = figs
# convolution
with tf.variable_scope(self.name_scope, reuse = reuse):
for i, (in_dim, out_dim) in enumerate(zip(self.layer_list, self.layer_list[1:])):
h = linear_layer(h, in_dim, out_dim, i)
h = batch_norm(h, i, is_training)
h = tf.nn.relu(h)
dim = get_dim(h)
mu = linear_layer(h, dim, self.z_dim, 'mu')
log_sigma = linear_layer(h, dim, self.z_dim, 'log_sigma')
return mu, log_sigma
