python artificial intelligence tensorflow function usage

(
    inputs,					# layer inputs
    units,					# Output dimensions of the layer
    activation=None,		# activation function
    use_bias=True,			
    kernel_initializer=None,  	# Initializer for convolution kernel
    bias_initializer=tf.zeros_initializer(),  # Initializer for bias items
    kernel_regularizer=None,    # Regularization of convolutional kernels
    bias_regularizer=None,    	# Regularization of bias terms
    activity_regularizer=None, 
    kernel_constraint=None,
    bias_constraint=None,
    trainable=True,
    name=None,  # Name of the layer
    reuse=None  # Whether to reuse parameters
)

import numpy as np
import tensorflow as tf
from  import input_data
def compute_accuracy(x_data,y_data):
    global dense2
    y_pre = (dense2,feed_dict={xs:x_data})
    correct_prediction = (tf.arg_max(y_data,1),tf.arg_max(y_pre,1))     #Determine if they are equal
    accuracy = tf.reduce_mean((correct_prediction,tf.float32))   # Assign float32 data type to average.
    result = (accuracy,feed_dict = {xs:batch_xs,ys:batch_ys})   #Execute
    return result
mnist = input_data.read_data_sets("MNIST_data",one_hot = "true")
xs = (tf.float32,[None,784])
ys = (tf.float32,[None,10])
dense1 = (
    xs,
    200,
    activation = ,            
    kernel_initializer=tf.random_normal_initializer(mean=0, stddev=0.3),
    bias_initializer=tf.constant_initializer(0.1),
    name='fc1'
)
dense2 = (
    dense1,
    10,
    activation = ,            
    kernel_initializer=tf.random_normal_initializer(mean=0, stddev=0.3),
    bias_initializer=tf.constant_initializer(0.1),
    name='fc2'
)
loss = tf.reduce_mean(.softmax_cross_entropy_with_logits(logits = dense2, labels = ys),name = 'loss')
#label is the label, logits are the predicted values, and cross-entropy.
train = (0.5).minimize(loss)
init = tf.initialize_all_variables()
with () as sess:
    (init)
    for i in range(5001):
        batch_xs,batch_ys = .next_batch(100)
        (train,feed_dict = {xs:batch_xs,ys:batch_ys})
        if i % 1000 == 0:
            print("The recognition rate for training %d times is: %f."%((i+1),compute_accuracy(,)))