Views
No views yet
| Property | Value |
|---|---|
| Architecture | U-Net (SmallCloudNet) |
| Parameters | 1.86M |
| Input size (training) | 33×33 px |
| Input size (inference) | any (fully convolutional) |
| Classes | clear, thick cloud, thin cloud, shadow |
| Metric | Value |
|---|---|
| Mean IoU | 0.38 |
| Mean F1 | 0.54 |
| Accuracy | 64% |
| Clear IoU | 0.58 |
| Thick cloud IoU | 0.45 |
| Shadow IoU | 0.27 |
| Thin cloud IoU | 0.22 |
1import torch
2from model import SmallCloudNet
3
4model = SmallCloudNet(in_ch=3, num_classes=4)
5checkpoint = torch.load("best_model.pth", map_location="cpu")
6model.load_state_dict(checkpoint["model_state_dict"])
7model.eval()
8
9# img: float32 tensor (1, 3, H, W) normalised to [0, 1]
10with torch.no_grad():
11 logits = model(img) # (1, 4, H, W)
12 mask = logits.argmax(dim=1) # (1, H, W)