Pruning in fully connected layers

I have been trying to make the entire starting columns in the weight matrix to zero. But after the training, all weight matrices look same. Please help me with a better way in order to achieve this.
#My code::
import torch
import torch.nn as nn
import torchvision
import torchvision.transforms as transforms
import numpy as np

input_size = 784
hidden_size = 500
num_classes = 10
num_epochs = 3
batch_size = 256
learning_rate = 0.01
a = []
b = []
c = []
d = []
e = []
f = []
x = []

train_dataset = torchvision.datasets.MNIST(root=’…/…/data’,
train=True,
transform=transforms.ToTensor(),
download=True)

test_dataset = torchvision.datasets.MNIST(root=’…/…/data’,
train=False,
transform=transforms.ToTensor())

train_loader = torch.utils.data.DataLoader(dataset=train_dataset,
batch_size=batch_size,
shuffle=True)

test_loader = torch.utils.data.DataLoader(dataset=test_dataset,
batch_size=batch_size,
shuffle=False)

class NeuralNet(nn.Module):
def init(self, input_size, hidden_size, num_classes):
super(NeuralNet, self).init()
self.fc1 = nn.Linear(input_size, hidden_size, bias=False)
nn.init.normal_(self.fc1.weight)

    self.relu = nn.ReLU()
    self.fc2 = nn.Linear(hidden_size, num_classes,bias=False)  

def forward(self, x):
    out = self.fc1(x)
    out = self.relu(out)
    out = self.fc2(out)
    return out

model = NeuralNet(input_size, hidden_size, num_classes).to(device)
a=model.fc1.weight

criterion = nn.CrossEntropyLoss()
optimizer = torch.optim.Adam(model.parameters(), lr=learning_rate, weight_decay=0)

total_step = len(train_loader)
for epoch in range(num_epochs):
for i, (images, labels) in enumerate(train_loader):

    images = images.reshape(-1, 28*28).to(device)
    labels = labels.to(device)
    if epoch == 0 & i==0:
        with torch.no_grad():
            d=model.fc1.weight
            d[:,0:1]=0
            model.fc1.weight.data=d
      
    x=model.fc1.weight 
    if epoch == 1:
      b=model.fc1.weight 
    if epoch == 2:
      c=model.fc1.weight
    if epoch == 3:
      e=model.fc1.weight
    if epoch == 4:
      f=model.fc1.weight
   
    outputs = model(images)
    loss = criterion(outputs, labels)
    
    
    
    optimizer.zero_grad()
    loss.backward()
    optimizer.step()
    
    if (i+1) % 100 == 0:
        print ('Epoch [{}/{}], Step [{}/{}], Loss: {:.4f}' 
               .format(epoch+1, num_epochs, i+1, total_step, loss.item()))

b=model.fc1.weight.detach().numpy()
with torch.no_grad():
correct = 0
total = 0
for images, labels in test_loader:
images = images.reshape(-1, 28*28).to(device)
labels = labels.to(device)
outputs = model(images)
loss = criterion(outputs, labels)
#b.append(loss.detach().numpy())
_, predicted = torch.max(outputs.data, 1)
total += labels.size(0)
correct += (predicted == labels).sum().item()

print('Accuracy of the network on the 10000 test images: {} %'.format(100 * correct / total))

torch.save(model.state_dict(), ‘model.ckpt’)