Hello,
I want to change end of encoder layer after training phase and in test phase, as any column and row in feature map be given shifts. this is my code but I dont know how to apply these changes. please help me.
import torch
import torch.nn as nn
import torch.nn.functional as F
import torch.optim as optim
import matplotlib.pyplot as plt
from torch.utils.data.sampler import SubsetRandomSampler
from torch.utils.data import DataLoader
from torchvision import datasets, transforms
#%%
#Converting data to torch.FloatTensor
transform = transforms.ToTensor()
# Download the training and test datasets
train_data = datasets.MNIST(root='data', train=True, download=True, transform=transform)
test_data = datasets.MNIST(root='data', train=False, download=True, transform=transform)
train_loader = torch.utils.data.DataLoader(train_data, batch_size=32, num_workers=0)
test_loader = torch.utils.data.DataLoader(test_data, batch_size=32, num_workers=0)
#train_loader=torch.to
#%%
#Define the Convolutional Autoencoder
class ConvAutoencoder(nn.Module):
def __init__(self):
super(ConvAutoencoder, self).__init__()
#Encoder
self.conv1 = nn.Conv2d(1, 16, 3, stride=2, padding=1)
self.conv2 = nn.Conv2d(16, 8, 3, stride=2, padding=1)
self.conv3 = nn.Conv2d(8,8,3)
#Decoder
self.conv4 = nn.ConvTranspose2d(8, 8, 3)
self.conv5 = nn.ConvTranspose2d(8, 16, 3, stride=2, padding=1, output_padding=1)
self.conv6 = nn.ConvTranspose2d(16, 1, 3, stride=2, padding=1, output_padding=1)
def forward(self, x):
x = F.relu(self.conv1(x))
x = F.relu(self.conv2(x))
x = F.relu(self.conv3(x))
#mask = torch.cat([torch.ones([8,8,2,3]), torch.zeros([8,8,1,3])], 2)
#x=torch.multiply(x,mask)
# x[7,7,:,:]=x[6,6,:,:]
x = F.relu(self.conv4(x))
x = F.relu(self.conv5(x))
x = F.relu(self.conv6(x))
return x
#Instantiate the model
model = ConvAutoencoder()
print(model)
#%%
def train(model, num_epochs=20, batch_size=64, learning_rate=1e-3):
torch.manual_seed(42)
criterion = nn.MSELoss() # mean square error loss
optimizer = torch.optim.Adam(model.parameters(),
lr=learning_rate,
weight_decay=1e-5) # <--
# train_loader =train_loader;
outputs = []
for epoch in range(num_epochs):
for data in train_loader:
img, _ = data
recon = model(img)
loss = criterion(recon, img)
loss.backward()
optimizer.step()
optimizer.zero_grad()
print('Epoch:{}, Loss:{:.4f}'.format(epoch+1, float(loss)))
outputs.append((epoch, img, recon),)
return outputs
#%%
#test_image = test_loader.open(test_image_name).convert('RGB')
model = ConvAutoencoder()
max_epochs =20
outputs = train(model, num_epochs=max_epochs)
#%%
for k in range(0, max_epochs, 9):
plt.figure(figsize=(9, 2))
imgs = outputs[k][1].detach().numpy()
recon = outputs[k][2].detach().numpy()
for i, item in enumerate(imgs):
if i >= 9: break
plt.subplot(2, 9, i+1)
plt.imshow(item[0])
for i, item in enumerate(recon):
if i >= 9: break
plt.subplot(2, 9, 9+i+1)
plt.imshow(item[0])
#%%
a=(ConvAutoencoder().conv3.weight)
print("conv1 filters: ",a.data.size())
#%%
#test phase
with torch.no_grad(): #3
for data in test_loader:
data = torch.tensor(data[0])
a=(ConvAutoencoder().conv3.weight)
a0=a[0,0,:,:]
a1=a[1,1,:,:]
a2=a[2,2,:,:]
a3=a[3,3,:,:]
a4=a[4,4,:,:]
a5=a[5,5,:,:]
a6=a[6,6,:,:]
a7=a[7,7,:,:]
a0=a1
a1=a2
a2=a3
a3=a4
a4=a5
a5=a6
a6=a7
a7=a0
a=[a0,
a1,
a2,
a3,
a4,
a5,
a6,
a7]
output = model(data)
plt.imshow(output[0,0])