|
|
|
|
"""
|
|
|
|
|
from data.params import SYS_ARGS
|
|
|
|
|
self.G_STRUCTURE = [self.Z_DIM,self.Z_DIM]
|
|
|
|
|
self.mkdir (os.sep.join([self.log_dir,key,self.CONTEXT,str(args['partition'])]))
|
|
|
|
|
if not os.path.exists(os.sep.join(root)) :
|
|
|
|
|
x = x + h2
|
|
|
|
|
# This seems to be the output layer
|
|
|
|
|
#
|
|
|
|
|
kernel = self.get.variables(name='W_' + str(i+1), shape=[self.Z_DIM, self.X_SPACE_SIZE])
|
|
|
|
|
bias = self.get.variables(name='b_' + str(i+1), shape=[self.X_SPACE_SIZE])
|
|
|
|
|
x = tf.nn.sigmoid(tf.add(tf.matmul(x, kernel), bias))
|
|
|
|
|
return x
|
|
|
|
|
|
|
|
|
|
grads = self.average_gradients(tower_grads)
|
|
|
|
|
for i in range(self.STEPS_PER_EPOCH):
|
|
|
|
|
for _ in range(2):
|
|
|
|
|
_, w = sess.run([train_d, w_distance])
|
|
|
|
|
w_sum += w
|
|
|
|
|
sess.run(train_g)
|
|
|
|
|
duration = time.time() - start_time
|
|
|
|
|
|
|
|
|
|
assert not np.isnan(w_sum), 'Model diverged with loss = NaN'
|
|
|
|
|
|
|
|
|
|
format_str = 'epoch: %d, w_distance = %f (%.1f)'
|
|
|
|
|
print(format_str % (epoch, -w_sum/(self.STEPS_PER_EPOCH*2), duration))
|
|
|
|
|
# print (dir (w_distance))
|
|
|
|
|
|
|
|
|
|
logs.append({"epoch":epoch,"distance":-w_sum/(self.STEPS_PER_EPOCH*2) })
|
|
|
|
|
|
|
|
|
|
self.logger.write(row)
|
|
|
|
|
self.ROW_COUNT = self.oROW_COUNT
|
|
|
|
|
def apply(self,**args):
|
|
|
|
|
# The code below will insure we have some acceptable cardinal relationships between id and synthetic values
|
|
|
|
|
#
|
|
|
|
|
|
|
|
|
|
# df = pd.DataFrame(np.round(f)).astype(np.int32)
|
|
|
|
|
p = 0 not in df.sum(axis=1).values
|
