parking-utcustom-train-SF-RGBD-b5_3

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: 0.0234
• 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: 5.7e-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: 150

Training results

Training Loss	Epoch	Step	Accuracy Parking	Accuracy Unlabeled	Accuracy Unparking	Iou Parking	Iou Unlabeled	Iou Unparking	Validation Loss	Mean Accuracy	Mean Iou	Overall Accuracy
0.3831	20.0	20	nan	nan	0.9868	0.0	nan	0.9868	0.3810	0.9868	0.4934	0.9868
0.1678	40.0	40	nan	nan	0.9999	0.0	nan	0.9999	0.2179	0.9999	0.5000	0.9999
0.123	60.0	60	nan	nan	0.9994	0.0	nan	0.9994	0.0796	0.9994	0.4997	0.9994
0.09	80.0	80	nan	nan	1.0	nan	nan	1.0	0.0433	1.0	1.0	1.0
0.0626	100.0	100	0.0283	1.0	1.0	1.0	nan	nan	1.0	nan	nan	1.0
0.0493	120.0	120	0.0272	1.0	1.0	1.0	nan	nan	1.0	nan	nan	1.0
0.0525	140.0	140	0.0234	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