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: 4.9822
• Mean Iou: 0.0050
• Mean Accuracy: 0.0259
• Overall Accuracy: 0.0659
• Per Category Iou: [0.0, 0.0, 0.42791763087856327, 0.002705563443913773, 0.11484260881675644, 0.004469078471025891, 0.00010464003826835685, 0.0, 0.0, 0.0, 0.0, 0.0, 0.04216482322102168, 0.0006308115510378447, 0.021786914921127488, 0.0, 0.0, 0.0, 0.0, 1.0116644915880098e-05, 0.0011043283536304794, 0.0, 0.0, 0.0, nan, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.012403422514526532, 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, 0.0, 0.0, nan, 0.0, nan, 0.0, nan, 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, 0.014823049842505095, 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, nan, nan, 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, 0.0, nan, 0.0, 0.0, nan, 0.0, 0.0, 0.0, 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, 0.0, 0.0, 0.0, nan, nan, 0.0]
• Per Category Accuracy: [0.0, 0.0, 0.5983735141415003, 0.002898678998960016, 0.12777657657657657, 0.005584500670764047, 0.00011662099011220605, 0.0, 0.0, 0.0, nan, nan, 0.051474509905948776, 0.0006435111270405004, 0.1369918699186992, nan, 0.0, 0.0, 0.0, 0.00011761938367442955, 0.001417434443656981, 0.0, 0.0, nan, nan, nan, 0.0, 0.0, nan, 0.0, nan, nan, 0.0955641193834044, 0.0, 0.0, nan, 0.0, nan, nan, 0.0, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, 0.04036326942482341, 0.0, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, 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, 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, 0.0, 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
4.8784	1.0	20	4.9822	0.0050	0.0259	0.0659	[0.0, 0.0, 0.42791763087856327, 0.002705563443913773, 0.11484260881675644, 0.004469078471025891, 0.00010464003826835685, 0.0, 0.0, 0.0, 0.0, 0.0, 0.04216482322102168, 0.0006308115510378447, 0.021786914921127488, 0.0, 0.0, 0.0, 0.0, 1.0116644915880098e-05, 0.0011043283536304794, 0.0, 0.0, 0.0, nan, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.012403422514526532, 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, 0.0, 0.0, nan, 0.0, nan, 0.0, nan, 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, 0.014823049842505095, 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, nan, nan, 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, 0.0, nan, 0.0, 0.0, nan, 0.0, 0.0, 0.0, 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, 0.0, 0.0, 0.0, nan, nan, 0.0]	[0.0, 0.0, 0.5983735141415003, 0.002898678998960016, 0.12777657657657657, 0.005584500670764047, 0.00011662099011220605, 0.0, 0.0, 0.0, nan, nan, 0.051474509905948776, 0.0006435111270405004, 0.1369918699186992, nan, 0.0, 0.0, 0.0, 0.00011761938367442955, 0.001417434443656981, 0.0, 0.0, nan, nan, nan, 0.0, 0.0, nan, 0.0, nan, nan, 0.0955641193834044, 0.0, 0.0, nan, 0.0, nan, nan, 0.0, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, 0.04036326942482341, 0.0, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, 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, 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, 0.0, nan, nan, nan, nan, nan]

Framework versions

• Transformers 4.35.0
• Pytorch 2.1.0+cu118
• Datasets 2.14.6
• Tokenizers 0.14.1