TensorFlow Trained Model Predicts Always Zero - python-3.x

Question

I have one simple TensorFlow model and accuracy for that is 1. But when I try to predict some new inputs it always returns Zero(0).
import numpy as np
import tensorflow as tf
sess = tf.InteractiveSession()
# generate data
np.random.seed(10)
#inputs = np.random.uniform(low=1.2, high=1.5, size=[5000, 150]).astype('float32')
inputs = np.random.randint(low=50, high=500, size=[5000, 150])
label = np.random.uniform(low=1.3, high=1.4, size=[5000, 1])
# reverse_label = 1 - label
reverse_label = np.random.uniform(
low=1.3, high=1.4, size=[5000, 1])
reverse_label1 = np.random.randint(
low=80, high=140, size=[5000, 1])
#labels = np.append(label, reverse_label, 1)
#labels = np.append(labels, reverse_label1, 1)
labels = reverse_label1
print(inputs)
print(labels)
# parameters
learn_rate = 0.001
epochs = 100
n_input = 150
n_hidden = 15
n_output = 1
# set weights/biases
x = tf.placeholder(tf.float32, [None, n_input])
y = tf.placeholder(tf.float32, [None, n_output])
b0 = tf.Variable(tf.truncated_normal([n_hidden], stddev=0.2, seed=0))
b1 = tf.Variable(tf.truncated_normal([n_output], stddev=0.2, seed=0))
w0 = tf.Variable(tf.truncated_normal([n_input, n_hidden], stddev=0.2, seed=0))
w1 = tf.Variable(tf.truncated_normal([n_hidden, n_output], stddev=0.2, seed=0))
# step function
def returnPred(x, w0, w1, b0, b1):
z1 = tf.add(tf.matmul(x, w0), b0)
a2 = tf.nn.relu(z1)
z2 = tf.add(tf.matmul(a2, w1), b1)
h = tf.nn.relu(z2)
return h # return the first response vector from the
y_ = returnPred(x, w0, w1, b0, b1) # predict operation
loss = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(
logits=y_, labels=y)) # calculate loss between prediction and actual
model = tf.train.AdamOptimizer(learning_rate=learn_rate).minimize(
loss) # apply gradient descent based on loss
init = tf.global_variables_initializer()
tf.Session = sess
sess.run(init) # initialize graph
for step in range(0, epochs):
sess.run([model, loss], feed_dict={x: inputs, y: labels}) # train model
correct_prediction = tf.equal(tf.argmax(y, 1), tf.argmax(y_, 1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
print(sess.run(accuracy, feed_dict={x: inputs, y: labels})) # print accuracy
inp = np.random.randint(low=50, high=500, size=[5, 150])
print(sess.run(tf.argmax(y_, 1), feed_dict={x: inp})) # predict some new inputs
All functions are working properly and my problem is with the latest line of code. I tried only "y_" instead "tf.argmax(y_, 1)" but not worked too.
How can I fix that?
Regards,

Answer 1

There are multiple mistakes in your code.
Starting with this lines of code:
correct_prediction = tf.equal(tf.argmax(y, 1), tf.argmax(y_, 1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
print(sess.run(accuracy, feed_dict={x: inputs, y: labels})) # print accuracy
You are performing linear regression but you are checking accuracy with that of logistic regression methodology. If you want to see how your linear regression network is performing, print the loss. Ensure that your loss is decreasing after each epoch of training.
If you look into that accuracy code, run the following code:
print(y_.get_shape()) # Outputs (?, 1)
There is only one input and both of your function tf.argmax(y,1) and tf.argmax(y_,1) will always return [0,0,..]. So as a result your accuracy will be always 1.0. Delete those three lines of code.
Next, to get the outputs, just run the following code:
print(sess.run(y_, feed_dict={x: inp}))
But since your data is random, don't expect good set of outputs.