Tianmu28/segformer-flood-images-finetuned

segformer-b0-segments-sidewalk-finetuned

This model is a fine-tuned version of nvidia/segformer-b0-finetuned-ade-512-512 on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.2634
• Mean Iou: 0.4383
• Mean Accuracy: 0.8765
• Overall Accuracy: 0.8765
• Accuracy Background: nan
• Accuracy Target: 0.8765
• Iou Background: 0.0
• Iou Target: 0.8765

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: 5e-05
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Mean Iou	Mean Accuracy	Overall Accuracy	Accuracy Background	Accuracy Target	Iou Background	Iou Target
0.4747	1.0	26	0.3768	0.4287	0.8573	0.8573	nan	0.8573	0.0	0.8573
0.3193	2.0	52	0.3138	0.4198	0.8395	0.8395	nan	0.8395	0.0	0.8395
0.2792	3.0	78	0.2899	0.4318	0.8636	0.8636	nan	0.8636	0.0	0.8636
0.2569	4.0	104	0.2723	0.4202	0.8405	0.8405	nan	0.8405	0.0	0.8405
0.2504	5.0	130	0.2634	0.4383	0.8765	0.8765	nan	0.8765	0.0	0.8765
0.2294	6.0	156	0.2572	0.4292	0.8584	0.8584	nan	0.8584	0.0	0.8584
0.2337	7.0	182	0.2567	0.4292	0.8584	0.8584	nan	0.8584	0.0	0.8584
0.2255	8.0	208	0.2546	0.4354	0.8707	0.8707	nan	0.8707	0.0	0.8707
0.2213	9.0	234	0.2557	0.4299	0.8597	0.8597	nan	0.8597	0.0	0.8597
0.2203	10.0	260	0.2552	0.4372	0.8744	0.8744	nan	0.8744	0.0	0.8744

Framework versions

• Transformers 4.46.3
• Pytorch 2.5.1+cu121
• Datasets 3.1.0
• Tokenizers 0.20.3