parking-utcustom-train-SF-RGBD-b0_3

This model is a fine-tuned version of nvidia/mit-b0 on the sam1120/parking-utcustom-train dataset. It achieves the following results on the evaluation set:

• Loss: 0.0296
• Mean Iou: 1.0
• Mean Accuracy: 1.0
• Overall Accuracy: 1.0
• Accuracy Unlabeled: nan
• Accuracy Parking: nan
• Accuracy Unparking: 1.0
• Iou Unlabeled: nan
• Iou Parking: nan
• Iou Unparking: 1.0

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: 0.00025
• train_batch_size: 16
• eval_batch_size: 16
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_ratio: 0.05
• num_epochs: 150

Training results

Training Loss	Epoch	Step	Validation Loss	Mean Iou	Mean Accuracy	Overall Accuracy	Accuracy Unlabeled	Accuracy Parking	Accuracy Unparking	Iou Unlabeled	Iou Parking	Iou Unparking
0.531	20.0	20	0.4126	1.0	1.0	1.0	nan	nan	1.0	nan	nan	1.0
0.2633	40.0	40	0.1573	1.0	1.0	1.0	nan	nan	1.0	nan	nan	1.0
0.1835	60.0	60	0.0898	1.0	1.0	1.0	nan	nan	1.0	nan	nan	1.0
0.1465	80.0	80	0.0682	1.0	1.0	1.0	nan	nan	1.0	nan	nan	1.0
0.1247	100.0	100	0.0424	1.0	1.0	1.0	nan	nan	1.0	nan	nan	1.0
0.1065	120.0	120	0.0339	1.0	1.0	1.0	nan	nan	1.0	nan	nan	1.0
0.0961	140.0	140	0.0296	1.0	1.0	1.0	nan	nan	1.0	nan	nan	1.0

Framework versions

• Transformers 4.30.2
• Pytorch 2.0.1+cu117
• Datasets 2.13.1
• Tokenizers 0.13.3