segformer-b0-scene-parse-150

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: -34.0382
• Mean Iou: 0.0
• Mean Accuracy: nan
• Overall Accuracy: nan
• Per Category Iou: [0.0]
• Per Category Accuracy: [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: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Mean Iou	Mean Accuracy	Overall Accuracy	Per Category Iou	Per Category Accuracy
-14.0066	0.95	20	-4.7161	0.0	nan	nan	[0.0]	[nan]
-22.6107	1.9	40	-10.5378	0.0	nan	nan	[0.0]	[nan]
-19.9201	2.86	60	-21.2021	0.0	nan	nan	[0.0]	[nan]
-28.3712	3.81	80	-21.2437	0.0	nan	nan	[0.0]	[nan]
-37.3469	4.76	100	-28.5338	0.0	nan	nan	[0.0]	[nan]
-37.3102	5.71	120	-31.3866	0.0	nan	nan	[0.0]	[nan]
-39.3847	6.67	140	-36.0143	0.0	nan	nan	[0.0]	[nan]
-39.0931	7.62	160	-31.5379	0.0	nan	nan	[0.0]	[nan]
-43.0727	8.57	180	-33.0026	0.0	nan	nan	[0.0]	[nan]
-47.8338	9.52	200	-34.0382	0.0	nan	nan	[0.0]	[nan]

Framework versions

• Transformers 4.38.2
• Pytorch 2.2.1+cu121
• Datasets 2.18.0
• Tokenizers 0.15.2