Plot the landscape of the loss function. For example, the following code will print the landscape of Z[i][j]. Z is the loss function value of different ww and bb values. X_data and y_data are the arrays of your samples.

bb = np.arange(0,100,1) #bias

ww = np.arange(-5, 5,0.1) #weight

Z = np.zeros((len(bb),len(ww)))

for i in range(len(bb)):

for j in range(len(ww)):

b = bb[i]

w = ww[j]

Z[j][i] = 0

for n in range(len(x_data)):

Z[j][i] =

Z[j][i] =