semantic-segmentation

This model is a fine-tuned version of nvidia/mit-b0 on the scene_parse_150 dataset. It achieves the following results on the evaluation set:

• Loss: 4.9789
• Mean Iou: 0.0046
• Mean Accuracy: 0.0211
• Overall Accuracy: 0.0890
• Per Category Iou: [0.0, 0.0, 0.3370586994883633, 0.0011783885315329683, 0.17971457696228338, 0.0, 0.0, 0.0, 0.0, 0.0005691728633067107, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0013089005235602095, 0.0, 0.0, 0.0, 0.0653821624410708, 0.0, nan, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, nan, 0.0, 0.0, 0.0011844131232974062, 0.0, 0.00022798084960863287, 0.0, nan, 0.0, 0.0, 0.0, 0.0, nan, nan, 0.0, 0.0, 0.0, 0.0, 0.0, nan, 0.0, 0.0, 0.0, nan, 0.0, nan, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, nan, 0.0, 0.0, 0.0, 0.0, 0.0, nan, 0.0, 0.0, nan, 0.0, 0.0, 0.0, 0.0, nan, 0.0, nan, 0.0, 0.0, 0.0, 0.0, nan, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, nan, 0.0, nan, 0.0, nan, 0.0, nan, 0.0, nan, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, nan, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, nan, 0.0, 0.0, 0.0, 0.0, nan, 0.0, 0.0, 0.0, nan, 0.0, 0.0]
• Per Category Accuracy: [0.0, 0.0, 0.578173337775451, 0.0014208794495961712, 0.18539355381460645, 0.0, nan, 0.0, 0.0, 0.0006200661403883081, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.002337228714524207, nan, 0.0, nan, 0.1557566040616888, nan, nan, 0.0, nan, 0.0, nan, nan, 0.0, nan, nan, 0.0, 0.0, 0.0, nan, 0.0, nan, 0.0, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, 0.002759128115515497, nan, 0.0008389261744966443, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan]

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: 2
• eval_batch_size: 2
• 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
4.9015	1.0	20	4.9789	0.0046	0.0211	0.0890	[0.0, 0.0, 0.3370586994883633, 0.0011783885315329683, 0.17971457696228338, 0.0, 0.0, 0.0, 0.0, 0.0005691728633067107, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0013089005235602095, 0.0, 0.0, 0.0, 0.0653821624410708, 0.0, nan, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, nan, 0.0, 0.0, 0.0011844131232974062, 0.0, 0.00022798084960863287, 0.0, nan, 0.0, 0.0, 0.0, 0.0, nan, nan, 0.0, 0.0, 0.0, 0.0, 0.0, nan, 0.0, 0.0, 0.0, nan, 0.0, nan, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, nan, 0.0, 0.0, 0.0, 0.0, 0.0, nan, 0.0, 0.0, nan, 0.0, 0.0, 0.0, 0.0, nan, 0.0, nan, 0.0, 0.0, 0.0, 0.0, nan, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, nan, 0.0, nan, 0.0, nan, 0.0, nan, 0.0, nan, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, nan, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, nan, 0.0, 0.0, 0.0, 0.0, nan, 0.0, 0.0, 0.0, nan, 0.0, 0.0]	[0.0, 0.0, 0.578173337775451, 0.0014208794495961712, 0.18539355381460645, 0.0, nan, 0.0, 0.0, 0.0006200661403883081, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.002337228714524207, nan, 0.0, nan, 0.1557566040616888, nan, nan, 0.0, nan, 0.0, nan, nan, 0.0, nan, nan, 0.0, 0.0, 0.0, nan, 0.0, nan, 0.0, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, 0.002759128115515497, nan, 0.0008389261744966443, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan]

Framework versions

• Transformers 4.39.3
• Pytorch 2.1.2+cpu
• Datasets 2.18.0
• Tokenizers 0.15.2