YAML Metadata Warning:empty or missing yaml metadata in repo card
Check out the documentation for more information.
VOC Efficient Segmentation
MobileNetV3-Large + LR-ASPP trained on PASCAL VOC 2012.
Metrics
| Metric | Value |
|---|---|
| Macro DICE | 0.7989 |
| Mean IoU | 0.6801 |
| FLOPs / image | 1.4091e+09 |
| DICE / GFLOPs | 0.5670 |
Best Hyperparameters (Optuna)
{
"lr": 0.0001786162829017358,
"weight_decay": 0.0004384199029959522,
"batch_size": 16,
"loss_alpha": 0.45821908158215957
}
Quickload
from torchvision.models.segmentation import lraspp_mobilenet_v3_large
import torch
model = lraspp_mobilenet_v3_large()
state = torch.load('pytorch_model.bin', map_location='cpu')
model.load_state_dict(state)
model.eval()
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support