Pytorch deep learning practice-b station Liu erden-day1

The first 2 speak linear_model Source code

B standing Lord Liu , Portal PyTorch Deep learning practice —— Linear model

Code instructions ：
1、 function forward() in , There is a variable w. The final value of this variable is from for Passed in the loop .
2、for In circulation , Used np.arange.
3、python in zip() Function usage ：
zip The prototype of the function is ：
zip([iterable, …])
Parameters iterable For objects that can be iterated , And can have multiple parameters . This function returns a list with tuples as elements , Among them the first i Tuples contain the... Of each parameter sequence i Elements . The length of the returned list is truncated to the length of the shortest parameter sequence . When there is only one sequence parameter , It returns a 1 A list of tuples . Without parameters , It returns an empty list .

Specific code learned today ：

import numpy as np
import matplotlib.pyplot as plt
 
x_data = [1.0, 2.0, 3.0] #  This is a x Value 
y_data = [2.0, 4.0, 6.0]#  This is a y True value of 
 
 
def forward(x): 
    return x*w
 
 
def loss(x, y): # Calculate the loss value 
    y_pred = forward(x)
    return (y_pred - y)**2
 
 
#  Exhaustive method 
w_list = []
mse_list = []
for w in np.arange(0.0, 4.1, 0.1):
    print("w=", w)
    l_sum = 0
    for x_val, y_val in zip(x_data, y_data):
        y_pred_val = forward(x_val)
        loss_val = loss(x_val, y_val)
        l_sum += loss_val
        print('\t', x_val, y_val, y_pred_val, loss_val) #  Print out the values one by one 
    print('MSE=', l_sum/3)
    w_list.append(w)
    mse_list.append(l_sum/3)
    
plt.plot(w_list,mse_list)
plt.ylabel('Loss')
plt.xlabel('w')
plt.show()    

The assignments are as follows ：

Implementation code ：

import numpy as np
import matplotlib.pyplot as plt
from matplotlib import cm
from mpl_toolkits.mplot3d import Axes3D

# y = x*2.5-1  Construct training data 
x_data = [1.0, 2.0, 3.0]
y_data = [1.5, 4.0, 6.5]
W, B = np.arange(0.0, 4.1, 0.1), np.arange(-2.0, 2.1, 0.1) #  Regulations  W,B  The range of 
w, b = np.meshgrid(W, B, indexing='ij') #  Construction matrix coordinates 

def forward(x):
    return x*w+b
    
def loss(y_pred, y):
    return (y_pred-y)*(y_pred-y)

# Make data.
mse_lst = []
l_sum = 0.
for x_val, y_val in zip(x_data, y_data):
    y_pred_val = forward(x_val)
    loss_val = loss(y_pred_val, y_val)
    l_sum += loss_val
mse_lst.append(l_sum/3)

#  Definition figure
fig = plt.figure(figsize=(10,10), dpi=300)
#  take figure Turn into 3d
ax = Axes3D(fig)
#  mapping ,rstride: The span between rows   cstride: The span between columns 
surf = ax.plot_surface(w, b, np.array(mse_lst[0]), rstride=1, cstride=1, cmap=cm.coolwarm, linewidth=0, antialiased=False)
# Customize the z axis.
ax.set_zlim(0, 40)
#  Set axis labels 
ax.set_xlabel("w")
ax.set_ylabel("b")
ax.set_zlabel("loss")
ax.text(0.2, 2, 43, "Cost Value", color='black')
# Add a color bar which maps values to colors.
fig.colorbar(surf, shrink=0.5, aspect=5)
plt.show()

Running results （ Can't say like , It's as like as two peas. ）