I'm learning TensorFlow and tired to apply on mnist database. My question is (see attached image) :
- what could cause such output for accuracy (improving and then degrading!) & Loss (almost constant!)
- the accuracy isn't that great just hovering around 10%
Despite:
- 5 layer network (incl. output layer), with 200/10/60/30/10 neurons respectively
- Is the network not learning ? despite 0.1 learning rate (which is quite high I believe)
Full code: https://github.com/vibhorj/tf > mnist-2.py
1) here's how the layers are defined:
K,L,M,N=200,100,60,30
""" Layer 1 """
with tf.name_scope('L1'):
w1 = tf.Variable(initial_value = tf.truncated_normal([28*28,K],mean=0,stddev=0.1), name = 'w1')
b1 = tf.Variable(initial_value = tf.truncated_normal([K],mean=0,stddev=0.1), name = 'b1')
""" Layer 2 """
with tf.name_scope('L2'):
w2 = tf.Variable(initial_value =tf.truncated_normal([K,L],mean=0,stddev=0.1), name = 'w2')
b2 = tf.Variable(initial_value = tf.truncated_normal([L],mean=0,stddev=0.1), name = 'b2')
""" Layer 3 """
with tf.name_scope('L3'):
w3 = tf.Variable(initial_value = tf.truncated_normal([L,M],mean=0,stddev=0.1), name = 'w3')
b3 = tf.Variable(initial_value = tf.truncated_normal([M],mean=0,stddev=0.1), name = 'b3')
""" Layer 4 """
with tf.name_scope('L4'):
w4 = tf.Variable(initial_value = tf.truncated_normal([M,N],mean=0,stddev=0.1), name = 'w4')
b4 = tf.Variable(initial_value = tf.truncated_normal([N],mean=0,stddev=0.1), name = 'b4')
""" Layer output """
with tf.name_scope('L_out'):
w_out = tf.Variable(initial_value = tf.truncated_normal([N,10],mean=0,stddev=0.1), name = 'w_out')
b_out = tf.Variable(initial_value = tf.truncated_normal([10],mean=0,stddev=0.1), name = 'b_out')
2) loss function
Y1 = tf.nn.sigmoid(tf.add(tf.matmul(X,w1),b1), name='Y1')
Y2 = tf.nn.sigmoid(tf.add(tf.matmul(Y1,w2),b2), name='Y2')
Y3 = tf.nn.sigmoid(tf.add(tf.matmul(Y2,w3),b3), name='Y3')
Y4 = tf.nn.sigmoid(tf.add(tf.matmul(Y3,w4),b4), name='Y4')
Y_pred_logits = tf.add(tf.matmul(Y4, w_out),b_out,name='logits')
Y_pred_prob = tf.nn.softmax(Y_pred_logits, name='probs')
error = -tf.matmul(Y
, tf.reshape(tf.log(Y_pred_prob),[10,-1]), name ='err')
loss = tf.reduce_mean(error, name = 'loss')
3) optimization function
opt = tf.train.GradientDescentOptimizer(0.1)
grads_and_vars = opt.compute_gradients(loss)
ctr = tf.Variable(0.0, name='ctr')
z = opt.apply_gradients(grads_and_vars, global_step=ctr)
4) Tensorboard code:
evt_file = tf.summary.FileWriter('/Users/vibhorj/python/-tf/g_mnist')
evt_file.add_graph(tf.get_default_graph())
s1 = tf.summary.scalar(name='accuracy', tensor=accuracy)
s2 = tf.summary.scalar(name='loss', tensor=loss)
m1 = tf.summary.merge([s1,s2])
5) run the session (test data is mnist.test.images & mnist.test.labels
with tf.Session() as sess:
sess.run(tf.variables_initializer(tf.global_variables()))
for i in range(300):
""" calc. accuracy on test data - TENSORBOARD before iteration beings """
summary = sess.run(m1, feed_dict=test_data)
evt_file.add_summary(summary, sess.run(ctr))
evt_file.flush()
""" fetch train data """
a_train, b_train = mnist.train.next_batch(batch_size=100)
train_data = {X: a_train , Y: b_train}
""" train """
sess.run(z, feed_dict = train_data)
Appreciate your time to provide any insight into it. I'm completely clueless hwo to proceed further (even tried initializing w & b with random_normal, played with learning rates [0.1,0.01, 0.001])
Cheers!