segformer-b0-drivable-area_segmentation

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

• Loss: 0.2781
• Mean Iou: 0.3551
• Mean Accuracy: 0.4409
• Overall Accuracy: 0.9059
• Per Category Iou: [0.16086782865321247, 0.904459670467452, 0.0]
• Per Category Accuracy: [0.39100126742712293, 0.9316527965687352, 0.0]

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: 0.0001
• train_batch_size: 4
• eval_batch_size: 4
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 5

Training results

Training Loss	Epoch	Step	Validation Loss	Mean Iou	Mean Accuracy	Overall Accuracy	Per Category Iou	Per Category Accuracy
0.0717	2.44	100	0.3113	0.3302	0.3801	0.9033	[0.08799146351473365, 0.902610436143179, 0.0]	[0.2023568751179786, 0.9379215030926394, 0.0]
0.0079	4.88	200	0.2781	0.3551	0.4409	0.9059	[0.16086782865321247, 0.904459670467452, 0.0]	[0.39100126742712293, 0.9316527965687352, 0.0]

Framework versions

• Transformers 4.27.4
• Pytorch 1.13.1+cu117
• Datasets 2.12.0
• Tokenizers 0.13.2