I am Trying to create a Logistic regression Model manually but GradientTape returns NoneType gradients
class LogisticRegressionTF:
def __init__(self,dim):
#dim = X_train.shape[0]
tf.random.set_seed(1)
weight_init = tf.initializers.VarianceScaling(scale=1.0, mode="fan_avg", distribution="uniform", seed=1)
zeros_init = tf.zeros_initializer()
self.W = tf.Variable(zeros_init([dim,1]), trainable=True, name="W")
self.b = tf.Variable(zeros_init([1]), trainable=True, name="b")
def sigmoid(self,z):
x = tf.Variable(z, trainable=True,dtype=tf.float32, name='x')
sigmoid = tf.sigmoid(x)
result = sigmoid
return result
def predict(self, x):
x = tf.cast(x, dtype=tf.float32)
h = tf.sigmoid(tf.add(tf.matmul(tf.transpose(self.W), x), self.b))
return h
def loss(self,logits, labels):
z = tf.Variable(logits, trainable=False,dtype=tf.float32, name='z')
y = tf.Variable(labels, trainable=False,dtype=tf.float32, name='y')
m = tf.cast(tf.size(z), dtype=tf.float32)
cost = tf.divide(tf.reduce_sum(y*tf.math.log(z) + (1-y)*tf.math.log(1-z)),-m)
return cost
def fit(self,X_train, Y_train, lr_rate = 0.01, epochs = 1000):
costs=[]
optimizer = tf.optimizers.SGD(learning_rate=lr_rate)
for i in range(epochs):
current_loss = self.loss(self.predict(X_train), Y_train)
print(current_loss)
with tf.GradientTape() as t:
t.watch([self.W, self.b])
currt_loss = self.loss(self.predict(X_train), Y_train)
print(currt_loss)
grads = t.gradient(currt_loss, [self.W, self.b])
print(grads)
#optimizer.apply_gradients(zip(grads,[self.W, self.b]))
self.W.assign_sub(lr_rate * grads[0])
self.b.assign_sub(lr_rate * grads[1])
if(i %100 == 0):
print('Epoch %2d: , loss=%2.5f' %(i, current_loss))
costs.append(current_loss)
plt.plot(costs)
plt.ylim(0,50)
plt.ylabel('Cost J')
plt.xlabel('Iterations')
log_reg = LogisticRegressionTF(train_set_x.shape[0])
log_reg.fit(train_set_x, train_set_y)
This gives a TypeError which is due to gradients returning None
tf.Tensor(0.6931474, shape=(), dtype=float32)
tf.Tensor(0.6931474, shape=(), dtype=float32)
[None, None]
---------------------------------------------------------------------------
TypeError Traceback (most recent call last)
<ipython-input-192-024668d532b0> in <module>()
1 log_reg = LogisticRegressionTF(train_set_x.shape[0])
----> 2 log_reg.fit(train_set_x, train_set_y)
<ipython-input-191-4fef932eb231> in fit(self, X_train, Y_train, lr_rate, epochs)
40 print(grads)
41 #optimizer.apply_gradients(zip(grads,[self.W, self.b]))
---> 42 self.W.assign_sub(lr_rate * grads[0])
43 self.b.assign_sub(lr_rate * grads[1])
44 if(i %100 == 0):
TypeError: unsupported operand type(s) for *: 'float' and 'NoneType'
My Hypothesis Function is tf.sigmoid(tf.add(tf.matmul(tf.transpose(self.W), x), self.b))
I have defined the cost function manually as tf.divide(tf.reduce_sum(y*tf.math.log(z) + (1-y)*tf.math.log(1-z)),-m), where m is the number of training examples
to verify it is returning the loss as tf.Tensor(0.6931474, shape=(), dtype=float32)
I also did a t.watch() but nothing happened it is still returning [None, None]
train_set_y.dtype is dtype('int64')
train_set_x.dtype is dtype('float64')
train_set_x.shape is (12288, 209)
train_set_y.shape is (1, 209)
type(train_set_x) is numpy.ndarray
Where did I go wrong??
Thanks
in my environment Tensorflow was running Eagerly that is it was on Eager Execution. We can check this using tf.executing_eagerly() for eager execution enabled it returns True
The issue was with the loss(self,logits, labels): Function
The Logits should not be a `tf.Variable(...)'
it should be changed to z = logits , and logits should be treated as Tensor ojects not tf.Variable object.
I also changed tf.divide to Eager mode (Not required though)
Before:
def loss(self,logits, labels):
z = tf.Variable(logits, trainable=False,dtype=tf.float32, name='z')
y = tf.Variable(labels, trainable=False,dtype=tf.float32, name='y')
m = tf.cast(tf.size(z), dtype=tf.float32)
cost = tf.divide(tf.reduce_sum(y*tf.math.log(z) + (1-y)*tf.math.log(1-z)),-m)
return cost
After:
def loss(self,logits, labels):
z = logits
y = tf.constant(labels,dtype=tf.float32, name='y')
m = tf.cast(tf.size(z), dtype=tf.float32)
cost = (-1/m)*tf.reduce_sum(y*tf.math.log(z) + (1-y)*tf.math.log(1-z))
return cost