def train():
    with tf.GradientTape() as tape:
        loss_f = loss()
    trainable_variables = list(weights.values()) + list(biases.values())
    gradients = tape.gradient(loss_f, trainable_variables)
    optimizer.apply_gradients(zip(gradients, trainable_variables))

l1=[]
l3=[]
for i in range(2000):
    train()
    if i % 10 == 0:
         l1.append(loss())
         l3.append((1 / n) * tf.math.reduce_sum(tf.pow(tf.ones(n)-NN(X)[0][0][:n],2)))
         print('loss',i,loss())
         #print('error=', (1 / n) * tf.math.reduce_sum(tf.pow(tf.ones(n)-NN(X)[0][0][:n],2)))
l2=tf.convert_to_tensor(l1)
l4=tf.convert_to_tensor(l3)
#print(NN(x))

I designed a neural network to solve Fredholm’s integral equations.

The loss function is a very large value. The answer of the NN network and the exact answer is 1, represented by ones.
Thank you in advance for your help