segformer-b0-finetuned-segments-sidewalk-2

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

• Loss: 1.5766
• Mean Iou: 0.1371
• Mean Accuracy: 0.1845
• Overall Accuracy: 0.7137
• Per Category Iou: [nan, 0.4878460273549076, 0.7555073936058639, 0.0, 0.021023119916983492, 6.661075803708754e-07, nan, 0.0, 0.0, 0.0, 0.5945035814400078, 0.0, 0.0, nan, 0.0, 0.0, 0.0, 0.0, 0.5297440422960749, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.7198551864914086, 0.489491922020114, 0.7904739581298643, 0.0, 0.0, 0.0, 0.0]
• Per Category Accuracy: [nan, 0.8122402393699828, 0.916307187222316, 0.0, 0.02103704204254936, 6.661204478993891e-07, nan, 0.0, 0.0, 0.0, 0.8989685161351728, 0.0, 0.0, nan, 0.0, 0.0, 0.0, 0.0, 0.8771164563053133, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.9407576559617489, 0.6174625729307718, 0.821407178606353, 0.0, 0.0, 0.0, 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: 6e-05
• 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: 1

Training results

Training Loss	Epoch	Step	Validation Loss	Mean Iou	Mean Accuracy	Overall Accuracy	Per Category Iou	Per Category Accuracy
1.7378	0.5	100	1.8155	0.1247	0.1711	0.6916	[nan, 0.46555602373647126, 0.7353888954834877, 0.0, 0.009228814643632902, 0.00010122529220478676, nan, 0.0, 0.0, 0.0, 0.5739398587525921, 0.0, 0.0, nan, 0.0, 0.0, 0.0, 0.0, 0.5094931557231258, 0.0, 5.3423644732762526e-05, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.6692211552011066, 0.2651198767217891, 0.7633341956468725, 0.0, 0.0, 0.0, 0.0]	[nan, 0.7515868666775908, 0.9079116468110205, 0.0, 0.009233668577520995, 0.00010125030808070715, nan, 0.0, 0.0, 0.0, 0.8690972710699856, 0.0, 0.0, nan, 0.0, 0.0, 0.0, 0.0, 0.8791886402701642, 0.0, 5.361129513400909e-05, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.9598752209264458, 0.3079896302845186, 0.7892434570182117, 0.0, 0.0, 0.0, 0.0]
1.6547	1.0	200	1.5766	0.1371	0.1845	0.7137	[nan, 0.4878460273549076, 0.7555073936058639, 0.0, 0.021023119916983492, 6.661075803708754e-07, nan, 0.0, 0.0, 0.0, 0.5945035814400078, 0.0, 0.0, nan, 0.0, 0.0, 0.0, 0.0, 0.5297440422960749, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.7198551864914086, 0.489491922020114, 0.7904739581298643, 0.0, 0.0, 0.0, 0.0]	[nan, 0.8122402393699828, 0.916307187222316, 0.0, 0.02103704204254936, 6.661204478993891e-07, nan, 0.0, 0.0, 0.0, 0.8989685161351728, 0.0, 0.0, nan, 0.0, 0.0, 0.0, 0.0, 0.8771164563053133, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.9407576559617489, 0.6174625729307718, 0.821407178606353, 0.0, 0.0, 0.0, 0.0]

Framework versions

• Transformers 4.21.1
• Pytorch 1.12.1
• Datasets 2.4.0
• Tokenizers 0.12.1