File size: 1,464 Bytes
93e1ff2 |
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 |
# sam2_model_stub.py
import torch
import torch.nn as nn
import torch.nn.functional as F
class SAM2Hierarchical(nn.Module):
def __init__(self, num_classes=6, in_channels=3, backbone="vit_b", freeze_backbone=True, use_cls_head=True):
super().__init__()
self.use_cls_head = use_cls_head
# Minimal vision backbone stub (fake transformer or CNN)
self.backbone = nn.Sequential(
nn.Conv2d(in_channels, 64, kernel_size=3, stride=2, padding=1),
nn.BatchNorm2d(64),
nn.ReLU(inplace=True),
nn.Conv2d(64, 128, kernel_size=3, stride=2, padding=1),
nn.BatchNorm2d(128),
nn.ReLU(inplace=True)
)
# Segmentation head stub
self.segmentation_head = nn.Sequential(
nn.Conv2d(128, 64, kernel_size=3, padding=1),
nn.ReLU(inplace=True),
nn.Conv2d(64, num_classes, kernel_size=1)
)
# Optional classification head
if self.use_cls_head:
self.cls_head = nn.Linear(128, num_classes)
if freeze_backbone:
for param in self.backbone.parameters():
param.requires_grad = False
def forward(self, x):
features = self.backbone(x)
logits = self.segmentation_head(features)
if self.use_cls_head:
# Just return segmentation output; inference only cares about logits
return logits
return logits
|