Aerial-Drone-Image-Segmentation

This model is a fine-tuned version of nvidia/mit-b0 It achieves the following results on the evaluation set:

• Loss: 0.8852
• Mean Iou: 0.2994
• Mean Accuracy: 0.3923
• Overall Accuracy: 0.7774

Model description

More information needed

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 5e-05
• train_batch_size: 24
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 50

Evaluation Results

{'mean_iou': 0.27989828118195953,
 'mean_accuracy': 0.3712316062110093,
 'overall_accuracy': 0.7671712239583334,
 'per_category_iou': array([       nan, 0.8560476 , 0.32234631, 0.76880948, 0.57517691,
        0.43877125, 0.00114888, 0.14091442, 0.51807365, 0.76964765,
        0.27391949, 0.        , 0.        , 0.        , 0.        ,
        0.05778175, 0.        , 0.45566807, 0.        , 0.25864545,
        0.48767764, 0.        , 0.23313364,        nan]),
 'per_category_accuracy': array([       nan, 0.96170675, 0.43993514, 0.86977593, 0.8149788 ,
        0.49739671, 0.00114987, 0.14445379, 0.80978302, 0.88661108,
        0.46787116, 0.        , 0.        , 0.        , 0.        ,
        0.05947339, 0.        , 0.55639324, 0.        , 0.38358184,
        0.761303  , 0.        , 0.51268161,        nan])}

Training results

Training Loss	Epoch	Step	Validation Loss	Mean Iou	Mean Accuracy	Overall Accuracy
2.7923	1.25	20	2.8338	0.0954	0.1626	0.5529
2.219	2.5	40	2.1391	0.1036	0.1666	0.5929
1.9451	3.75	60	1.7919	0.1154	0.1782	0.6129
1.7558	5.0	80	1.6767	0.1300	0.1961	0.6396
1.6381	6.25	100	1.5817	0.1383	0.2055	0.6550
1.5338	7.5	120	1.4816	0.1464	0.2140	0.6729
1.4478	8.75	140	1.4231	0.1529	0.2219	0.6823
1.361	10.0	160	1.3300	0.1637	0.2315	0.6975
1.306	11.25	180

Framework versions

• Transformers 4.38.1
• Pytorch 2.1.2
• Datasets 2.1.0
• Tokenizers 0.15.2