parking-utcustom-train-SF-RGB-b5_4

This model is a fine-tuned version of nvidia/mit-b5 on the sam1120/parking-utcustom-train dataset. It achieves the following results on the evaluation set:

• Loss: 0.1142
• 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: 3e-05
• 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: 120

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
0.6986	20.0	20	0.5550	0.4999	0.9997	0.9997	nan	nan	0.9997	0.0	nan	0.9997
0.4103	40.0	40	0.3053	0.3326	0.9978	0.9978	nan	nan	0.9978	0.0	0.0	0.9978
0.2799	60.0	60	0.2382	0.3328	0.9984	0.9984	nan	nan	0.9984	0.0	0.0	0.9984
0.2218	80.0	80	0.1698	1.0	1.0	1.0	nan	nan	1.0	nan	nan	1.0
0.1729	100.0	100	0.1376	1.0	1.0	1.0	nan	nan	1.0	nan	nan	1.0
0.1575	120.0	120	0.1142	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