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 | 1.3034 | 0.1737 | 0.2419 | 0.7060 |
1.2611 | 12.5 | 200 | 1.2692 | 0.1755 | 0.2450 | 0.7093 |
1.2317 | 13.75 | 220 | 1.2190 | 0.1821 | 0.2501 | 0.7145 |
1.1868 | 15.0 | 240 | 1.2063 | 0.1862 | 0.2539 | 0.7188 |
1.1628 | 16.25 | 260 | 1.1832 | 0.1909 | 0.2612 | 0.7234 |
1.1149 | 17.5 | 280 | 1.1368 | 0.2048 | 0.2739 | 0.7317 |
1.1009 | 18.75 | 300 | 1.1117 | 0.2232 | 0.2938 | 0.7387 |
1.0532 | 20.0 | 320 | 1.0923 | 0.2315 | 0.2997 | 0.7414 |
1.0464 | 21.25 | 340 | 1.0821 | 0.2408 | 0.3147 | 0.7480 |
1.0278 | 22.5 | 360 | 1.0541 | 0.2517 | 0.3277 | 0.7530 |
0.9945 | 23.75 | 380 | 1.0352 | 0.2612 | 0.3398 | 0.7573 |
0.9729 | 25.0 | 400 | 1.0207 | 0.2671 | 0.3511 | 0.7609 |
0.9527 | 26.25 | 420 | 1.0067 | 0.2684 | 0.3547 | 0.7609 |
0.9494 | 27.5 | 440 | 0.9870 | 0.2713 | 0.3548 | 0.7627 |
0.9287 | 28.75 | 460 | 0.9729 | 0.2745 | 0.3619 | 0.7640 |
0.9089 | 30.0 | 480 | 0.9561 | 0.2791 | 0.3640 | 0.7680 |
0.9064 | 31.25 | 500 | 0.9500 | 0.2799 | 0.3712 | 0.7672 |
0.8681 | 32.5 | 520 | 0.9397 | 0.2845 | 0.3749 | 0.7696 |
0.8677 | 33.75 | 540 | 0.9340 | 0.2835 | 0.3737 | 0.7692 |
0.8663 | 35.0 | 560 | 0.9243 | 0.2862 | 0.3755 | 0.7716 |
0.8629 | 36.25 | 580 | 0.9173 | 0.2869 | 0.3766 | 0.7719 |
0.8542 | 37.5 | 600 | 0.9112 | 0.2908 | 0.3810 | 0.7740 |
0.8391 | 38.75 | 620 | 0.9050 | 0.2904 | 0.3812 | 0.7734 |
0.8392 | 40.0 | 640 | 0.9027 | 0.2917 | 0.3818 | 0.7734 |
0.8306 | 41.25 | 660 | 0.8949 | 0.2941 | 0.3841 | 0.7755 |
0.8213 | 42.5 | 680 | 0.8936 | 0.2958 | 0.3875 | 0.7760 |
0.8406 | 43.75 | 700 | 0.8910 | 0.2964 | 0.3879 | 0.7763 |
0.8254 | 45.0 | 720 | 0.8889 | 0.2981 | 0.3897 | 0.7764 |
0.8202 | 46.25 | 740 | 0.8880 | 0.2985 | 0.3917 | 0.7767 |
0.8013 | 47.5 | 760 | 0.8891 | 0.2989 | 0.3923 | 0.7767 |
0.8188 | 48.75 | 780 | 0.8861 | 0.2994 | 0.3926 | 0.7772 |
0.8089 | 50.0 | 800 | 0.8852 | 0.2994 | 0.3923 | 0.7774 |
Framework versions
- Transformers 4.38.1
- Pytorch 2.1.2
- Datasets 2.1.0
- Tokenizers 0.15.2
- Downloads last month
- 91
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.
Model tree for Thalirajesh/Aerial-Drone-Image-Segmentation
Base model
nvidia/mit-b0