Voc Seg Efficient

Best Hyperparameters (from Optuna HPO)

Training Details

• Dataset: Pascal VOC 2012 (train split, 80/20 train/val)
• Image size: 300×300
• Loss: Combined CrossEntropy + Dice Loss
• Optimizer: AdamW + CosineAnnealingLR
• AMP: Mixed precision (PyTorch 2.x)
• Augmentation: HFlip, Rotation, Gaussian noise / blur / salt-pepper / brightness

VOC Classes

background, aeroplane, bicycle, bird, boat, bottle, bus, car, cat, chair, cow, diningtable, dog, horse, motorbike, person, pottedplant, sheep, sofa, train, tvmonitor

Usage

import torch
from model import EfficientSegNet
from config import Config

model = EfficientSegNet(pretrained=False).to(Config.DEVICE)
ckpt  = torch.load("best_model.pth", map_location=Config.DEVICE, weights_only=True)
model.load_state_dict(ckpt["model_state"])
model.eval()

Trained: 2026-03-07 19:25

--- language: en license: mit tags: - image-segmentation - semantic-segmentation - pytorch - pascal-voc - mobilenet - lraspp - optuna datasets: - pascal-voc-2012 metrics: - dice - mean_iou --- # VOC Semantic Segmentation — EfficientSegNet (MobileNetV3-Large + LR-ASPP) Semantic segmentation model trained on Pascal VOC 2012. Architecture: **MobileNetV3-Large + LR-ASPP** (pretrained COCO backbone). Optimised with **Optuna** TPE-sampler HPO. ## Metrics | Metric | Value | |--------|-------| | Macro DICE | 0.7645 | | FLOPs/image | 7.3561e+08 | | DICE / GFLOPs | 1.0392 | | Parameters | 3.22M | ## Best Hyperparameters (from Optuna HPO) | Hyperparameter | Value | |---------------|-------| | — | N/A (direct training) | ## Training Details - Dataset: Pascal VOC 2012 (train split, 80/20 train/val) - Image size: 300×300 - Loss: Combined CrossEntropy + Dice Loss - Optimizer: AdamW + CosineAnnealingLR - AMP: Mixed precision (PyTorch 2.x) - Augmentation: HFlip, Rotation, Gaussian noise / blur / salt-pepper / brightness ## VOC Classes `background, aeroplane, bicycle, bird, boat, bottle, bus, car, cat, chair, cow, diningtable, dog, horse, motorbike, person, pottedplant, sheep, sofa, train, tvmonitor` ## Usage ```python import torch from model import EfficientSegNet from config import Config model = EfficientSegNet(pretrained=False).to(Config.DEVICE) ckpt = torch.load("best_model.pth", map_location=Config.DEVICE, weights_only=True) model.load_state_dict(ckpt["model_state"]) model.eval() ``` --- *Trained: 2026-03-07 19:25*