Skip to content

Instantly share code, notes, and snippets.

@seieric

seieric/PyTorch VGG

Created June 5, 2024 16:16
Show Gist options
  • Save seieric/685c0efdaa0f0588ff736e0c1c529a27 to your computer and use it in GitHub Desktop.
Save seieric/685c0efdaa0f0588ff736e0c1c529a27 to your computer and use it in GitHub Desktop.
Download ZIP
Raw
PyTorch VGG
net = nn.Sequential(
nn.Conv2d(3, 64, kernel_size = (3,3),stride = (1,1), padding = (1,1)), # (32, 32, 64)
nn.ReLU(),
nn.BatchNorm2d(64),
nn.Conv2d(64, 64, kernel_size = (3,3),stride = (1,1), padding = (1,1)), # (32, 32, 64)
nn.ReLU(),
nn.BatchNorm2d(64),
nn.MaxPool2d(kernel_size = (2,2), stride = (2,2)), # (16, 16, 64)
nn.Conv2d(64, 128, kernel_size = (3,3),stride = (1,1), padding = (1,1)), # (16, 16, 128)
nn.ReLU(),
nn.BatchNorm2d(128),
nn.Conv2d(128, 128, kernel_size = (3,3),stride = (1,1), padding = (1,1)), # (16, 16, 128)
nn.ReLU(),
nn.BatchNorm2d(128),
nn.MaxPool2d(kernel_size = (2,2), stride = (2,2)), # (8, 8, 64)
nn.Conv2d(128, 256, kernel_size = (3,3),stride = (1,1), padding = (1,1)), # (8, 8, 256)
nn.ReLU(),
nn.BatchNorm2d(256),
nn.Conv2d(256, 256, kernel_size = (3,3),stride = (1,1), padding = (1,1)), # (8, 8, 256)
nn.ReLU(),
nn.BatchNorm2d(256),
nn.Conv2d(256, 256, kernel_size = (3,3),stride = (1,1), padding = (1,1)), # (8, 8, 256)
nn.ReLU(),
nn.BatchNorm2d(256),
nn.Conv2d(256, 256, kernel_size = (3,3),stride = (1,1), padding = (1,1)), # (8, 8, 256)
nn.ReLU(),
nn.BatchNorm2d(256),
nn.MaxPool2d(kernel_size = (2,2), stride = (2,2)), # (4, 4, 256)
nn.Conv2d(256, 512, kernel_size = (3,3),stride = (1,1), padding = (1,1)), # (4, 4, 512)
nn.ReLU(),
nn.BatchNorm2d(512),
nn.Conv2d(512, 512, kernel_size = (3,3),stride = (1,1), padding = (1,1)), # (4, 4, 512)
nn.ReLU(),
nn.BatchNorm2d(512),
nn.Conv2d(512, 512, kernel_size = (3,3),stride = (1,1), padding = (1,1)), # (4, 4, 512)
nn.ReLU(),
nn.BatchNorm2d(512),
nn.Conv2d(512, 512, kernel_size = (3,3),stride = (1,1), padding = (1,1)), # (4, 4, 512)
nn.ReLU(),
nn.BatchNorm2d(512),
nn.MaxPool2d(kernel_size = (2,2), stride = (2,2)), # (2, 2, 512)
nn.Conv2d(512, 512, kernel_size = (3,3),stride = (1,1), padding = (1,1)), # (2, 2, 512)
nn.ReLU(),
nn.BatchNorm2d(512),
nn.Conv2d(512, 512, kernel_size = (3,3),stride = (1,1), padding = (1,1)), # (2, 2, 512)
nn.ReLU(),
nn.BatchNorm2d(512),
nn.Conv2d(512, 512, kernel_size = (3,3),stride = (1,1), padding = (1,1)), # (2, 2, 512)
nn.ReLU(),
nn.BatchNorm2d(512),
nn.Conv2d(512, 512, kernel_size = (3,3),stride = (1,1), padding = (1,1)), # (2, 2, 512)
nn.ReLU(),
nn.BatchNorm2d(512),
nn.MaxPool2d(kernel_size = (2,2), stride = (2,2)), # (1, 1, 512)
nn.Flatten(),
nn.Linear(512,4096),
nn.ReLU(),
nn.Dropout(0.5),
nn.Linear(4096,4096),
nn.ReLU(),
nn.Dropout(0.5),
nn.Linear(4096, 10)
)
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment