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: 4.9476
• Mean Iou: 0.0059
• Mean Accuracy: 0.0467
• Overall Accuracy: 0.0792
• Per Category Iou: [0.015290646787191019, 0.0, 0.0, 0.29707155265364804, 0.0, 0.08276914236227738, 0.0, 0.0, 0.0, 0.0, 0.012636310927907107, 0.0, 0.0, 0.0, 0.08227787105184403, 0.0, 0.0, 0.0, 0.02964898714815463, 0.0, 0.0, nan, 0.001510992695378508, nan, 0.0, 0.0, 0.0, 0.0008937418640346616, 0.0, nan, 0.0, 0.0, nan, 0.0, 0.0, 0.0, 0.0, 0.0006580782683957911, 0.0, nan, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.15182749560810285, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, nan, nan, nan, 0.0, 4.8507583352197394e-05, 0.0, 0.0, nan, 0.0, 0.0, 0.0, 0.09386101051905502, 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, 0.0, 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, 0.0, 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, nan, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, nan, 0.0, nan, 0.0, 0.0, nan, nan, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, nan, 0.0, 0.0, nan, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0]
• Per Category Accuracy: [0.015300257646825658, nan, nan, 0.3063194873378629, nan, 0.4663087217719412, nan, nan, 0.0, nan, 0.015581846316572973, nan, nan, nan, 0.09177343204121063, 0.0, nan, nan, 0.040619224731872905, 0.0, nan, nan, 0.00745248489659126, nan, 0.0, nan, nan, 0.0011775849269129355, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0006601654719106768, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, 0.1750304681339164, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 5.521201413427562e-05, nan, nan, nan, nan, nan, nan, 0.18748493024857915, 0.0, nan, nan, nan, 0.0, nan, nan, 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, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, 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, 0.0, 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
4.8424	1.0	20	4.9476	0.0059	0.0467	0.0792	[0.015290646787191019, 0.0, 0.0, 0.29707155265364804, 0.0, 0.08276914236227738, 0.0, 0.0, 0.0, 0.0, 0.012636310927907107, 0.0, 0.0, 0.0, 0.08227787105184403, 0.0, 0.0, 0.0, 0.02964898714815463, 0.0, 0.0, nan, 0.001510992695378508, nan, 0.0, 0.0, 0.0, 0.0008937418640346616, 0.0, nan, 0.0, 0.0, nan, 0.0, 0.0, 0.0, 0.0, 0.0006580782683957911, 0.0, nan, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.15182749560810285, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, nan, nan, nan, 0.0, 4.8507583352197394e-05, 0.0, 0.0, nan, 0.0, 0.0, 0.0, 0.09386101051905502, 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, 0.0, 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, 0.0, 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, nan, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, nan, 0.0, nan, 0.0, 0.0, nan, nan, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, nan, 0.0, 0.0, nan, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0]	[0.015300257646825658, nan, nan, 0.3063194873378629, nan, 0.4663087217719412, nan, nan, 0.0, nan, 0.015581846316572973, nan, nan, nan, 0.09177343204121063, 0.0, nan, nan, 0.040619224731872905, 0.0, nan, nan, 0.00745248489659126, nan, 0.0, nan, nan, 0.0011775849269129355, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0006601654719106768, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, 0.1750304681339164, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 5.521201413427562e-05, nan, nan, nan, nan, nan, nan, 0.18748493024857915, 0.0, nan, nan, nan, 0.0, nan, nan, 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, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, 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, 0.0, nan, nan]

Framework versions

• Transformers 4.41.2
• Pytorch 2.2.0
• Datasets 2.20.0
• Tokenizers 0.19.1