license: other base_model: nvidia/segformer-b3-finetuned-ade-512-512 tags:

• vision
• image-segmentation
• generated_from_trainer model-index:
• name: segformer-b3-finetuned-UAVid results: []

segformer-b3-finetuned-UAVid

This model is a fine-tuned version of nvidia/segformer-b3-finetuned-ade-512-512 on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.2115
• Mean Iou: 0.6365
• Mean Accuracy: 0.7005
• Overall Accuracy: 0.9263
• Accuracy Wall: nan
• Accuracy Building: 0.9535
• Accuracy Sky: nan
• Accuracy Floor: nan
• Accuracy Tree: 0.9415
• Accuracy Ceiling: nan
• Accuracy Road: 0.8948
• Accuracy Bed : nan
• Accuracy Windowpane: nan
• Accuracy Grass: nan
• Accuracy Cabinet: nan
• Accuracy Sidewalk: nan
• Accuracy Person: 0.0038
• Accuracy Earth: nan
• Accuracy Door: nan
• Accuracy Table: nan
• Accuracy Mountain: nan
• Accuracy Plant: nan
• Accuracy Curtain: nan
• Accuracy Chair: nan
• Accuracy Car: 0.7086
• Accuracy Water: nan
• Accuracy Painting: nan
• Accuracy Sofa: nan
• Accuracy Shelf: nan
• Accuracy House: nan
• Accuracy Sea: nan
• Accuracy Mirror: nan
• Accuracy Rug: nan
• Accuracy Field: nan
• Accuracy Armchair: nan
• Accuracy Seat: nan
• Accuracy Fence: nan
• Accuracy Desk: nan
• Accuracy Rock: nan
• Accuracy Wardrobe: nan
• Accuracy Lamp: nan
• Accuracy Bathtub: nan
• Accuracy Railing: nan
• Accuracy Cushion: nan
• Accuracy Base: nan
• Accuracy Box: nan
• Accuracy Column: nan
• Accuracy Signboard: nan
• Accuracy Chest of drawers: nan
• Accuracy Counter: nan
• Accuracy Sand: nan
• Accuracy Sink: nan
• Accuracy Skyscraper: nan
• Accuracy Fireplace: nan
• Accuracy Refrigerator: nan
• Accuracy Grandstand: nan
• Accuracy Path: nan
• Accuracy Stairs: nan
• Accuracy Runway: nan
• Accuracy Case: nan
• Accuracy Pool table: nan
• Accuracy Pillow: nan
• Accuracy Screen door: nan
• Accuracy Stairway: nan
• Accuracy River: nan
• Accuracy Bridge: nan
• Accuracy Bookcase: nan
• Accuracy Blind: nan
• Accuracy Coffee table: nan
• Accuracy Toilet: nan
• Accuracy Flower: nan
• Accuracy Book: nan
• Accuracy Hill: nan
• Accuracy Bench: nan
• Accuracy Countertop: nan
• Accuracy Stove: nan
• Accuracy Palm: nan
• Accuracy Kitchen island: nan
• Accuracy Computer: nan
• Accuracy Swivel chair: nan
• Accuracy Boat: nan
• Accuracy Bar: nan
• Accuracy Arcade machine: nan
• Accuracy Hovel: nan
• Accuracy Bus: nan
• Accuracy Towel: nan
• Accuracy Light: nan
• Accuracy Truck: nan
• Accuracy Tower: nan
• Accuracy Chandelier: nan
• Accuracy Awning: nan
• Accuracy Streetlight: nan
• Accuracy Booth: nan
• Accuracy Television receiver: nan
• Accuracy Airplane: nan
• Accuracy Dirt track: nan
• Accuracy Apparel: nan
• Accuracy Pole: nan
• Accuracy Land: nan
• Accuracy Bannister: nan
• Accuracy Escalator: nan
• Accuracy Ottoman: nan
• Accuracy Bottle: nan
• Accuracy Buffet: nan
• Accuracy Poster: nan
• Accuracy Stage: nan
• Accuracy Van: nan
• Accuracy Ship: nan
• Accuracy Fountain: nan
• Accuracy Conveyer belt: nan
• Accuracy Canopy: nan
• Accuracy Washer: nan
• Accuracy Plaything: nan
• Accuracy Swimming pool: nan
• Accuracy Stool: nan
• Accuracy Barrel: nan
• Accuracy Basket: nan
• Accuracy Waterfall: nan
• Accuracy Tent: nan
• Accuracy Bag: nan
• Accuracy Minibike: nan
• Accuracy Cradle: nan
• Accuracy Oven: nan
• Accuracy Ball: nan
• Accuracy Food: nan
• Accuracy Step: nan
• Accuracy Tank: nan
• Accuracy Trade name: nan
• Accuracy Microwave: nan
• Accuracy Pot: nan
• Accuracy Animal: nan
• Accuracy Bicycle: nan
• Accuracy Lake: nan
• Accuracy Dishwasher: nan
• Accuracy Screen: nan
• Accuracy Blanket: nan
• Accuracy Sculpture: nan
• Accuracy Hood: nan
• Accuracy Sconce: nan
• Accuracy Vase: nan
• Accuracy Traffic light: nan
• Accuracy Tray: nan
• Accuracy Ashcan: nan
• Accuracy Fan: nan
• Accuracy Pier: nan
• Accuracy Crt screen: nan
• Accuracy Plate: nan
• Accuracy Monitor: nan
• Accuracy Bulletin board: nan
• Accuracy Shower: nan
• Accuracy Radiator: nan
• Accuracy Glass: nan
• Accuracy Clock: nan
• Accuracy Flag: nan
• Iou Wall: nan
• Iou Building: 0.9105
• Iou Sky: nan
• Iou Floor: nan
• Iou Tree: 0.8818
• Iou Ceiling: nan
• Iou Road: 0.8152
• Iou Bed : nan
• Iou Windowpane: nan
• Iou Grass: nan
• Iou Cabinet: nan
• Iou Sidewalk: nan
• Iou Person: 0.0038
• Iou Earth: nan
• Iou Door: nan
• Iou Table: nan
• Iou Mountain: nan
• Iou Plant: nan
• Iou Curtain: nan
• Iou Chair: nan
• Iou Car: 0.5711
• Iou Water: nan
• Iou Painting: nan
• Iou Sofa: nan
• Iou Shelf: nan
• Iou House: nan
• Iou Sea: nan
• Iou Mirror: nan
• Iou Rug: nan
• Iou Field: nan
• Iou Armchair: nan
• Iou Seat: nan
• Iou Fence: nan
• Iou Desk: nan
• Iou Rock: nan
• Iou Wardrobe: nan
• Iou Lamp: nan
• Iou Bathtub: nan
• Iou Railing: nan
• Iou Cushion: nan
• Iou Base: nan
• Iou Box: nan
• Iou Column: nan
• Iou Signboard: nan
• Iou Chest of drawers: nan
• Iou Counter: nan
• Iou Sand: nan
• Iou Sink: nan
• Iou Skyscraper: nan
• Iou Fireplace: nan
• Iou Refrigerator: nan
• Iou Grandstand: nan
• Iou Path: nan
• Iou Stairs: nan
• Iou Runway: nan
• Iou Case: nan
• Iou Pool table: nan
• Iou Pillow: nan
• Iou Screen door: nan
• Iou Stairway: nan
• Iou River: nan
• Iou Bridge: nan
• Iou Bookcase: nan
• Iou Blind: nan
• Iou Coffee table: nan
• Iou Toilet: nan
• Iou Flower: nan
• Iou Book: nan
• Iou Hill: nan
• Iou Bench: nan
• Iou Countertop: nan
• Iou Stove: nan
• Iou Palm: nan
• Iou Kitchen island: nan
• Iou Computer: nan
• Iou Swivel chair: nan
• Iou Boat: nan
• Iou Bar: nan
• Iou Arcade machine: nan
• Iou Hovel: nan
• Iou Bus: nan
• Iou Towel: nan
• Iou Light: nan
• Iou Truck: nan
• Iou Tower: nan
• Iou Chandelier: nan
• Iou Awning: nan
• Iou Streetlight: nan
• Iou Booth: nan
• Iou Television receiver: nan
• Iou Airplane: nan
• Iou Dirt track: nan
• Iou Apparel: nan
• Iou Pole: nan
• Iou Land: nan
• Iou Bannister: nan
• Iou Escalator: nan
• Iou Ottoman: nan
• Iou Bottle: nan
• Iou Buffet: nan
• Iou Poster: nan
• Iou Stage: nan
• Iou Van: nan
• Iou Ship: nan
• Iou Fountain: nan
• Iou Conveyer belt: nan
• Iou Canopy: nan
• Iou Washer: nan
• Iou Plaything: nan
• Iou Swimming pool: nan
• Iou Stool: nan
• Iou Barrel: nan
• Iou Basket: nan
• Iou Waterfall: nan
• Iou Tent: nan
• Iou Bag: nan
• Iou Minibike: nan
• Iou Cradle: nan
• Iou Oven: nan
• Iou Ball: nan
• Iou Food: nan
• Iou Step: nan
• Iou Tank: nan
• Iou Trade name: nan
• Iou Microwave: nan
• Iou Pot: nan
• Iou Animal: nan
• Iou Bicycle: nan
• Iou Lake: nan
• Iou Dishwasher: nan
• Iou Screen: nan
• Iou Blanket: nan
• Iou Sculpture: nan
• Iou Hood: nan
• Iou Sconce: nan
• Iou Vase: nan
• Iou Traffic light: nan
• Iou Tray: nan
• Iou Ashcan: nan
• Iou Fan: nan
• Iou Pier: nan
• Iou Crt screen: nan
• Iou Plate: nan
• Iou Monitor: nan
• Iou Bulletin board: nan
• Iou Shower: nan
• Iou Radiator: nan
• Iou Glass: nan
• Iou Clock: nan
• Iou Flag: nan

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 6e-05
• train_batch_size: 2
• eval_batch_size: 2
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 15

Training results