File size: 1,497 Bytes
ee50dca | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 | from __future__ import annotations
import torch
from torch import nn
class TeacherCNN(nn.Module):
def __init__(self) -> None:
super().__init__()
self.features = nn.Sequential(
nn.Conv2d(1, 16, kernel_size=3, padding=1),
nn.GELU(),
nn.MaxPool2d(2),
nn.Conv2d(16, 32, kernel_size=3, padding=1),
nn.GELU(),
nn.MaxPool2d(2),
)
self.classifier = nn.Sequential(
nn.Flatten(),
nn.Linear(32 * 2 * 2, 64),
nn.GELU(),
nn.Dropout(0.1),
nn.Linear(64, 10),
)
def forward(self, pixels: torch.Tensor) -> torch.Tensor:
return self.classifier(self.features(pixels))
class TinyStudentCNN(nn.Module):
def __init__(self) -> None:
super().__init__()
self.features = nn.Sequential(
nn.Conv2d(1, 8, kernel_size=3, padding=1),
nn.GELU(),
nn.Conv2d(8, 8, kernel_size=3, padding=1, groups=8),
nn.GELU(),
nn.Conv2d(8, 12, kernel_size=1),
nn.GELU(),
nn.MaxPool2d(2),
)
self.classifier = nn.Sequential(
nn.Flatten(),
nn.Linear(12 * 4 * 4, 10),
)
def forward(self, pixels: torch.Tensor) -> torch.Tensor:
return self.classifier(self.features(pixels))
def parameter_count(model: nn.Module) -> int:
return sum(parameter.numel() for parameter in model.parameters())
|