This is a layer in tensorflow
def eachLayer(inputX,numberOfHiddenInputs,name,activation=tf.nn.relu):
with tf.variable_scope(name):
init = tf.random_normal(shape=(int(inputX.get_shape()[1]),numberOfHiddenInputs))
weights = tf.Variable(init,dtype="float32",name="weights")
biases = tf.Variable(tf.zeros([numberOfHiddenInputs]),dtype='float32',name="biases")
output=tf.matmul(inputX,weights) + biases
if activation:
return activation(output)
else:
return output
The entire network is created in this function as
def DNN(X=X,reuse=False):
with tf.variable_scope("dnn"):
first_layer = eachLayer(X,hidden_,name="firstLayer")
second_layer = eachLayer(first_layer,hidden_,name="secondLayer")
third_layer = eachLayer(second_layer,hidden_,name="thirdLayer")
output = eachLayer(third_layer,outputSize,name="output",activation=None)
return output
How do I save the "dnn" in session, which can be later used for testing purpose? I have tried saving the session, but it can only restore the weights, and biases and I don't want to build the entire model again to test any image.
with tf.Session() as sess:
saver = tf.train.Saver()
global_init = tf.global_variables_initializer()
sess.run(global_init)
for _ in range(epoch):
k=0
for eachBatch in range(noOfBatch):
batch_xs,batch_ys = x_train[k:k+batchSize], y_train[k:k+batchSize]
nth= sess.run(min_loss,feed_dict={X:batch_xs,Y:batch_ys})
theMinLossVal= mse.eval(feed_dict={X:batch_xs,Y:batch_ys})
k=k+batchSize
print("THE MIN LOSS IS ==> {}".format(theMinLossVal))
saver.save(sess, "mnistModel.ckpt")
print("Model Saved")
