manifestfile = os.path.join(root_files, 'train-index.csv')
testmanifest = os.path.join(root_files, 'val-index.csv')
train = train_loader(manifestfile,
root_files,
be,
h=im_size[0],
w=im_size[1],
scale=[0.875, 0.875])
test = validation_loader(testmanifest,
root_files,
be,
h=im_size[0],
w=im_size[1],
scale=[0.875, 0.875],
ncls=n_classes)
OneHot = OneHot(be, n_classes)
# Graph input
is_train = tf.placeholder(tf.bool)
keep_prob = tf.placeholder(tf.float32)
x_n = tf.placeholder(tf.float32, [batch_size, 3, im_size[0], im_size[1]])
y = tf.placeholder(tf.float32, [batch_size, n_classes])
lr_tf = tf.placeholder(tf.float32)
z = tf.random_uniform([batch_size, zdim], -1, 1)
iny = tf.placeholder(tf.float32, [batch_size, n_classes])
# Discriminator
def discriminator(inp, reuse=False):
with tf.variable_scope('Encoder', reuse=reuse):
# 64
ninput = np.asarray(input_vector)
expect = [1.0 for x in range(states.siz())]
res = sess.run(
[self.nn.out, self.nn.optimize, self.nn.error, self.nn.fill], {
self.nn.state: [ninput],
self.nn.expect: [expect],
self.nn.fill: [[self.stack.fill()]]
})
print(res[2], res[3], act, res[0], self.stack.debug())
self.stack.clear()
#sess.run()
[open, data, close, last] = oh.Item.items(['open', 'data', 'close', 'last'])
inputs = oh.Group(['open', 'data', 'close', 'last'])
states = oh.Group.array('state', 4)
nnpda = NNPDA(states, inputs, 20, .01)
sess = tf.InteractiveSession()
sess.run(tf.global_variables_initializer())
tf.summary.SessionLog
vec = [[open, data, close], [open, data, data, close],
[open, data, data, data, close]]
for x in range(100):
for y in range(4):
nnpda.train(vec[x % 1])