def sg_argmax(tensor, opt):
r"""Returns the indices of the maximum values along the specified dimension.
See `tf.argmax()` in tensorflow.
Args:
tensor: A `Tensor` (automatically given by chain).
opt:
dim: Target dimension. Default is the last one.
name: If provided, replace current tensor's name.
Returns:
A `Tensor`.
"""
opt += tf.sg_opt(dim=tensor.get_shape().ndims - 1)
return tf.argmax(tensor, opt.dim, opt.name)
def sg_argmax(tensor, opt):
opt += tf.sg_opt(dim=tensor.get_shape().ndims - 1)
return tf.argmax(tensor, opt.dim, opt.name)
W = tf.Variable(
tf.random_normal([n_hidden_units_three, num_classes], mean=0, stddev=sd))
b = tf.Variable(tf.random_normal([num_classes], mean=0, stddev=sd))
with tf.name_scope('out'):
y_ = tf.nn.softmax(tf.matmul(h_3, W) + b, name="out")
init = tf.global_variables_initializer()
cost_function = tf.reduce_mean(
-tf.reduce_sum(Y * tf.log(y_), reduction_indices=[1]))
#optimizer = tf.train.RMSPropOptimizer(learning_rate,decay=0.9,momentum=0.9,centered=True).minimize(cost_function)
optimizer = tf.train.GradientDescentOptimizer(learning_rate).minimize(
cost_function)
correct_prediction = tf.equal(tf.argmax(y_, 1), tf.argmax(Y, 1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
cost_history = np.empty(shape=[1], dtype=float)
acc_history = np.empty(shape=[1], dtype=float)
t_cost_history = np.empty(shape=[1], dtype=float)
t_acc_history = np.empty(shape=[1], dtype=float)
y_true, y_pred = None, None
with tf.Session() as session:
session.run(init)
saver = tf.train.Saver()
for epoch in range(epochs):
for batch in range(int(db_size / batchsize)):
indices = get_indices(batchsize)
feed = data_tools.next_minibatch(indices, db)