This model is a fine-tuned version of nvidia/mit-b0 on the segments/sidewalk-semantic dataset.
It achieves the following results on the evaluation set:
eval_loss: 1.5643
eval_mean_iou: 0.1299
eval_mean_accuracy: 0.1767
eval_overall_accuracy: 0.7026
eval_accuracy_unlabeled: nan
eval_accuracy_flat-road: 0.7260
eval_accuracy_flat-sidewalk: 0.9208
eval_accuracy_flat-crosswalk: 0.0
eval_accuracy_flat-cyclinglane: 0.0097
eval_accuracy_flat-parkingdriveway: 0.0001
eval_accuracy_flat-railtrack: nan
eval_accuracy_flat-curb: 0.0009
eval_accuracy_human-person: 0.0
eval_accuracy_human-rider: 0.0
eval_accuracy_vehicle-car: 0.9031
eval_accuracy_vehicle-truck: 0.0
eval_accuracy_vehicle-bus: 0.0
eval_accuracy_vehicle-tramtrain: 0.0
eval_accuracy_vehicle-motorcycle: 0.0
eval_accuracy_vehicle-bicycle: 0.0
eval_accuracy_vehicle-caravan: 0.0
eval_accuracy_vehicle-cartrailer: 0.0
eval_accuracy_construction-building: 0.8461
eval_accuracy_construction-door: 0.0
eval_accuracy_construction-wall: 0.0022
eval_accuracy_construction-fenceguardrail: 0.0
eval_accuracy_construction-bridge: 0.0
eval_accuracy_construction-tunnel: nan
eval_accuracy_construction-stairs: 0.0
eval_accuracy_object-pole: 0.0
eval_accuracy_object-trafficsign: 0.0
eval_accuracy_object-trafficlight: 0.0
eval_accuracy_nature-vegetation: 0.9200
eval_accuracy_nature-terrain: 0.4607
eval_accuracy_sky: 0.8653
eval_accuracy_void-ground: 0.0
eval_accuracy_void-dynamic: 0.0
eval_accuracy_void-static: 0.0
eval_accuracy_void-unclear: 0.0
eval_iou_unlabeled: nan
eval_iou_flat-road: 0.4423
eval_iou_flat-sidewalk: 0.7322
eval_iou_flat-crosswalk: 0.0
eval_iou_flat-cyclinglane: 0.0097
eval_iou_flat-parkingdriveway: 0.0001
eval_iou_flat-railtrack: nan
eval_iou_flat-curb: 0.0009
eval_iou_human-person: 0.0
eval_iou_human-rider: 0.0
eval_iou_vehicle-car: 0.5959
eval_iou_vehicle-truck: 0.0
eval_iou_vehicle-bus: 0.0
eval_iou_vehicle-tramtrain: 0.0
eval_iou_vehicle-motorcycle: 0.0
eval_iou_vehicle-bicycle: 0.0
eval_iou_vehicle-caravan: 0.0
eval_iou_vehicle-cartrailer: 0.0
eval_iou_construction-building: 0.5061
eval_iou_construction-door: 0.0
eval_iou_construction-wall: 0.0022
eval_iou_construction-fenceguardrail: 0.0
eval_iou_construction-bridge: 0.0
eval_iou_construction-tunnel: nan
eval_iou_construction-stairs: 0.0
eval_iou_object-pole: 0.0
eval_iou_object-trafficsign: 0.0
eval_iou_object-trafficlight: 0.0
eval_iou_nature-vegetation: 0.7073
eval_iou_nature-terrain: 0.4064
eval_iou_sky: 0.7528
eval_iou_void-ground: 0.0
eval_iou_void-dynamic: 0.0
eval_iou_void-static: 0.0
eval_iou_void-unclear: 0.0
eval_runtime: 34.9281
eval_samples_per_second: 5.726
eval_steps_per_second: 2.863
epoch: 0.1
step: 40
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
