I'm training a classifier to get a factor for an optimization. My data-set contains 800 samples as beginning (some are similar with just few modification).
I developed my model with TensorFlow using GoogleColab environment.
I have used a simple MLP for this problem, with 3 hidden layers each one has 256 nodes as first stage. I have also 64 classes .
I have variable length inputs and I had fixed this problem with "-1" padding.
with my actual features I know that I will get bad accuracy, but I did not expect zero accuracy and the very big loss.
This was my data-set after omitting some features that I have noticed that influence negatively the accuracy :
0 1 2 4 5 6 8 9 11 13 15 17 19 21
805 6 10 11 1 3 1 6 64 2 1.0 64.0 64.0 64.0 -1.0
334 6 12 18 0 2 4 7 2 1 32.0 128.0 64.0 128.0 -1.0
781 7 10 11 1 3 1 6 2 2 2.0 64.0 32.0 32.0 64.0
[Edited] : And here is some lines of my labels:
0
0 108
1 30
2 30
3 16
4 62
5 126
6 22
7 30
8 48
And here is a set of my result :
epoch[0] step [0] train -- loss : 50751.734375, accuracy : 0.0
epoch[0] step [100] train -- loss : 27310.064453125, accuracy : 0.0
epoch[0] step [200] train -- loss : 58120.6015625, accuracy : 0.0
epoch[0] step [300] train -- loss : 31801.9453125, accuracy : 0.0
epoch[0] step [400] train -- loss : 54360.76171875, accuracy : 0.0
epoch[0] step [500] train -- loss : 59946.67578125, accuracy : 0.0
epoch[1] step [0] train -- loss : 40612.06640625, accuracy : 0.0
epoch[1] step [100] train -- loss : 43229.734375, accuracy : 0.0
epoch[1] step [200] train -- loss : 36951.84375, accuracy : 0.0
epoch[1] step [300] train -- loss : 45225.828125, accuracy : 0.0
epoch[1] step [400] train -- loss : 47055.1796875, accuracy : 0.0
epoch[1] step [500] train -- loss : 54023.23046875, accuracy : 0.0
I wonder why I get this big loss, and also that my loss does not converge too :(.
Those was the bizarre graph of accuracy and loss I got :
My code work perfectly, but I still doubt maybe my I did not write things well so I got this mess.
This is the important part of my code :
class MLP():
'''
This is the implementation of the Multi Layer Perceptron
'''
def __init__(self, x_train, y_train, n_classes, n_hiddens=3, activation=tf.nn.relu):
...
################################ Create the model ##############################
def multilayer_perceptron(self,X):
# Hidden fully connected layer with n_hidden_1 neurons
layer_1 = tf.layers.dense(inputs=X, units= self.n_hidden_1, use_bias=True, kernel_initializer=self._init, name= 'layer_1')
layer_1 = tf.layers.batch_normalization(layer_1,training=self.is_train)
layer_1 = self.activation(layer_1)
# Hidden fully connected layer with n_hidden_2 neurons
layer_2 = tf.layers.dense(inputs=layer_1, units= self.n_hidden_2, use_bias=True, kernel_initializer=self._init, name= 'layer_2')
layer_2 = tf.layers.batch_normalization(layer_2,training=self.is_train)
layer_2 = self.activation(layer_2)
# Hidden fully connected layer with n_hidden_3 neurons
layer_3 = tf.layers.dense(inputs=layer_2, units= self.n_hidden_3, use_bias=True, kernel_initializer=self._init, name= 'layer_3')
layer_3 = tf.layers.batch_normalization(layer_3, training=self.is_train)
layer_3 = self.activation(layer_3)
# Output fully connected layer with the output
out_layer = tf.layers.dense(inputs=layer_3, units= self.n_classes, use_bias=True, kernel_initializer=self._init, name= 'out_layer')
tf.summary.histogram('pre-activations', out_layer)
return layer_1, layer_2, layer_3, out_layer
And here where I calculate the loss and accuracy of training set :
def loss(self, X, Y):
_, _, _, self.predicted_out = self.multilayer_perceptron(X)
print("Predicted out", self.predicted_out)
with tf.name_scope('loss'):
loss = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits_v2(logits=self.predicted_out, labels=Y))
tf.summary.scalar('loss', loss)
with tf.name_scope('accuracy'):
predicted_class = tf.nn.softmax(self.predicted_out)
with tf.name_scope('correct_prediction'):
correct_prediction = tf.equal(tf.argmax(predicted_class, 1), tf.argmax(Y, 1))
with tf.name_scope('accuracy'):
accuracy = tf.reduce_mean(tf.cast(correct_prediction, 'float'))
tf.summary.scalar('accuracy', accuracy)
self.merged = tf.summary.merge_all()
return loss, accuracy
This the function of training :
def train(self):
self.train_writer = tf.summary.FileWriter('./Graph', self.sess.graph)
# training data
train_input = self.Normalize(self.x_train)
train_output = self.y_train.copy()
save_sess=self.sess
#costs history :
costs = []
costs_inter=[]
#for early stopping :
best_cost=1000000
stop = False
last_improvement=0
n_samples = train_input.shape[0] # size of the training set
#train the mini_batches model using the early stopping criteria
epoch = 0
while epoch < self.max_epochs and stop == False:
#train the model on the traning set by mini batches
#suffle then split the training set to mini-batches of size self.batch_size
seq =list(range(n_samples))
random.shuffle(seq)
mini_batches = [
seq[k:k+self.batch_size]
for k in range(0,n_samples, self.batch_size)
]
avg_cost = 0. # The average cost of mini_batches
step= 0
for sample in mini_batches:
batch_x = x_train.iloc[sample, :]
batch_y =train_output.iloc[sample, :]
feed_dict={self.X: batch_x,self.Y:batch_y, self.is_train:True}
self.train_summary, _, cost,acc=self.sess.run([self.merged, self.train_step, self.loss_, self.accuracy_], feed_dict=feed_dict)
avg_cost += cost *len(sample)/n_samples
print('epoch[{}] step [{}] train -- loss : {}, accuracy : {}'.format(epoch,step, cost, acc))
self.train_writer.add_summary(self.train_summary, global_step=step)
step += 100
#cost history since the last best cost
costs_inter.append(avg_cost)
epoch +=1
#Test the model
pred = tf.nn.softmax(self.predicted_out) # Apply softmax to logits
correct_prediction = tf.equal(tf.argmax(pred, 1), tf.argmax(self.Y, 1))
# Calculate accuracy
accuracy = tf.reduce_mean(tf.cast(correct_prediction, "float"))
accuracy_test = self.sess.run([accuracy],feed_dict={self.X: x_test, self.Y: y_test,self.is_train:False})
#print("Accuracy:", accuracy.eval({self.X: x_test, self.Y: y_test}))
print("Accuracy_test : ", accuracy_test)
# Writes the summaries to disk
self.train_writer.flush()
# Flushes the summaries to disk and closes the SummaryWriter
self.train_writer.close()
return costs
Here where I call my method train, I was planing to apply cross validation to see if I can improve the model accuracy but I had not yet :
def cross_validation(self,batch_size, n_hidden_1 , n_hidden_2, n_hidden_3, learning_rate):
##### Other parameter
self.batch_size = batch_size
self.n_hidden_1 = n_hidden_1
self.n_hidden_2 = n_hidden_2
self.n_hidden_3 = n_hidden_3
self.learning_rate = learning_rate
self.require_improvement= 20
self.max_epochs = 80
self._init = tf.random_normal_initializer
self.optimizer=tf.train.AdamOptimizer
loss = 0
tf.reset_default_graph()
with tf.name_scope('input'):
self.X=tf.placeholder("float",shape=[None,self.x_train.shape[1]])
self.Y=tf.placeholder("float",shape=[None,self.y_train.shape[1]])
self.is_train = tf.placeholder(tf.bool, name="is_train")
self.loss_, self.accuracy_ = self.loss(self.X, self.Y)
self.train_step = self.optimizer(self.learning_rate).minimize(self.loss_)
# Initiate a tensor session
init = tf.global_variables_initializer()
self.sess = tf.Session()
self.sess.run(init)
#train the model
loss = self.train()
self.sess.close()
del self.sess
return loss
And finally this my main:
if __name__=='__main__':
tbc = tb.TensorBoardColab()
mlp = MLP(x_train, y_train, n_classes)
loss= mlp.cross_validation(batch_size, n_hidden_1 , n_hidden_2, n_hidden_3, learning_rate)
I had expected to get bad accuracy but not "0" and the very big loss without any convergence has shocked me. Can someone tell me where are the problems here?
