segformer-b0-scene-parse-150

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: 4.9393
• Mean Iou: 0.0036
• Mean Accuracy: 0.0214
• Overall Accuracy: 0.0867
• Per Category Iou: [0.16545709180085544, 0.0, 0.0, 0.0, 0.0, 0.058472783227543755, nan, 0.0, 0.0, 0.0, 0.007622227522060578, nan, 3.137911197113122e-05, 0.0, 0.058198708972300964, 0.0, 0.0, 0.0, 0.0, 0.0, nan, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.041340794105739556, nan, 0.0, 0.0, 0.0, nan, nan, 0.0, 0.0, 0.0, 0.0024778587375187066, 0.0, nan, nan, 0.0, 0.0, 0.0, nan, 0.0, 0.0, 0.016656203154428628, 0.0, 0.0, 0.0, 0.0, nan, 0.0, nan, 0.0, 0.0, 0.0, 0.0007263579350175389, 0.0, nan, nan, 0.0, 0.0, 0.0, 0.0697279103015839, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, nan, 0.0, nan, nan, nan, 0.012292855202390655, 0.0, 0.0, 0.0, 0.0, nan, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, nan, 0.0, nan, 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, 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, nan, nan, nan, 0.0, 0.0, nan, 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, 0.0, 0.0, nan, 0.0, 0.0]
• Per Category Accuracy: [0.18326833008776816, nan, 0.0, 0.0, 0.0, 0.09695526450076544, nan, nan, 0.0, nan, 0.009522447471605468, nan, 0.0035169988276670576, 0.0, 0.06740772973614463, 0.0, nan, 0.0, 0.0, 0.0, nan, 0.0, 0.0, nan, nan, nan, nan, 0.07055362102652567, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, 0.0025769907891715358, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.018805149717922753, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0010196214966054064, nan, nan, nan, nan, nan, nan, 0.23142163272931066, 0.0, nan, 0.0, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.019714628036161638, 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, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, 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
4.8574	1.0	20	4.9393	0.0036	0.0214	0.0867	[0.16545709180085544, 0.0, 0.0, 0.0, 0.0, 0.058472783227543755, nan, 0.0, 0.0, 0.0, 0.007622227522060578, nan, 3.137911197113122e-05, 0.0, 0.058198708972300964, 0.0, 0.0, 0.0, 0.0, 0.0, nan, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.041340794105739556, nan, 0.0, 0.0, 0.0, nan, nan, 0.0, 0.0, 0.0, 0.0024778587375187066, 0.0, nan, nan, 0.0, 0.0, 0.0, nan, 0.0, 0.0, 0.016656203154428628, 0.0, 0.0, 0.0, 0.0, nan, 0.0, nan, 0.0, 0.0, 0.0, 0.0007263579350175389, 0.0, nan, nan, 0.0, 0.0, 0.0, 0.0697279103015839, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, nan, 0.0, nan, nan, nan, 0.012292855202390655, 0.0, 0.0, 0.0, 0.0, nan, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, nan, 0.0, nan, 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, 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, nan, nan, nan, 0.0, 0.0, nan, 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, 0.0, 0.0, nan, 0.0, 0.0]	[0.18326833008776816, nan, 0.0, 0.0, 0.0, 0.09695526450076544, nan, nan, 0.0, nan, 0.009522447471605468, nan, 0.0035169988276670576, 0.0, 0.06740772973614463, 0.0, nan, 0.0, 0.0, 0.0, nan, 0.0, 0.0, nan, nan, nan, nan, 0.07055362102652567, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, 0.0025769907891715358, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.018805149717922753, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0010196214966054064, nan, nan, nan, nan, nan, nan, 0.23142163272931066, 0.0, nan, 0.0, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.019714628036161638, 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, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan]

Framework versions

• Transformers 4.31.0
• Pytorch 2.0.1+cu118
• Datasets 2.14.4
• Tokenizers 0.13.3