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: 4.4530
• Mean Iou: 0.0308
• Mean Accuracy: 0.0934
• Overall Accuracy: 0.3126
• Per Category Iou: [0.368405958754407, 0.11499370080653983, 0.5753658515502771, 0.2138805564642673, 0.28958703459911295, 0.191305743989082, 0.003497854077253219, 0.1288281531360376, 0.12360856380177596, 0.0, 0.0, 0.0, 0.003947940713975041, 0.0, 0.0, 0.015025862437481299, nan, 0.0, 0.0, 0.0037038152308109247, 4.4974139869574995e-05, nan, 0.12424162490108151, nan, 0.0, nan, 0.0, 0.0, 0.0, nan, nan, 0.0, 0.0, 0.0, nan, nan, 0.0, nan, nan, 0.0, 0.0, 0.0, 0.0, 0.0, 0.24922118380062305, 0.0, 0.0, nan, nan, 0.0, 0.0, 0.0, nan, nan, nan, nan, 0.0, nan, 0.0, nan, 0.0, nan, 0.0, nan, nan, nan, 0.0, 0.0, nan, 0.0, nan, 0.0, nan, nan, nan, 0.0, 0.0, 0.0, nan, 0.0, nan, nan, 0.0, 0.0, nan, nan, 0.0, 0.0, 0.0, nan, nan, nan, nan, 0.0, 0.0, 0.0, nan, 0.0, 0.0, nan, nan, nan, 0.0, nan, nan, nan, 0.0, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, 0.0, nan, 0.0, 0.0, nan, 0.0, nan, 0.0, nan, 0.0, nan, nan, 0.0, nan, nan, 0.0, nan, nan, 0.0, 0.0, nan, 0.0, nan, nan, nan, 0.0, nan]
• Per Category Accuracy: [0.7566432234358786, 0.24871206280227098, 0.7073059287949548, 0.34911440750830386, 0.992694013910948, 0.2160975230593844, 0.0035416689300031504, 0.5627543803943077, 0.22603353810393492, 0.0, 0.0, nan, 0.17717717717717718, nan, 0.0, 0.017564022485946285, nan, 0.0, 0.0, 0.004741894444658622, 0.004261363636363636, nan, 0.19470855725506409, nan, 0.0, nan, 0.0, nan, 0.0, nan, nan, 0.0, 0.0, 0.0, nan, nan, 0.0, nan, nan, 0.0, nan, 0.0, nan, 0.0, 0.3939161833898676, 0.0, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, 0.0, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, 0.0, 0.0, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, 0.0, nan, nan, 0.0, 0.0, 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
4.6085	1.0	20	4.4530	0.0308	0.0934	0.3126	[0.368405958754407, 0.11499370080653983, 0.5753658515502771, 0.2138805564642673, 0.28958703459911295, 0.191305743989082, 0.003497854077253219, 0.1288281531360376, 0.12360856380177596, 0.0, 0.0, 0.0, 0.003947940713975041, 0.0, 0.0, 0.015025862437481299, nan, 0.0, 0.0, 0.0037038152308109247, 4.4974139869574995e-05, nan, 0.12424162490108151, nan, 0.0, nan, 0.0, 0.0, 0.0, nan, nan, 0.0, 0.0, 0.0, nan, nan, 0.0, nan, nan, 0.0, 0.0, 0.0, 0.0, 0.0, 0.24922118380062305, 0.0, 0.0, nan, nan, 0.0, 0.0, 0.0, nan, nan, nan, nan, 0.0, nan, 0.0, nan, 0.0, nan, 0.0, nan, nan, nan, 0.0, 0.0, nan, 0.0, nan, 0.0, nan, nan, nan, 0.0, 0.0, 0.0, nan, 0.0, nan, nan, 0.0, 0.0, nan, nan, 0.0, 0.0, 0.0, nan, nan, nan, nan, 0.0, 0.0, 0.0, nan, 0.0, 0.0, nan, nan, nan, 0.0, nan, nan, nan, 0.0, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, 0.0, nan, 0.0, 0.0, nan, 0.0, nan, 0.0, nan, 0.0, nan, nan, 0.0, nan, nan, 0.0, nan, nan, 0.0, 0.0, nan, 0.0, nan, nan, nan, 0.0, nan]	[0.7566432234358786, 0.24871206280227098, 0.7073059287949548, 0.34911440750830386, 0.992694013910948, 0.2160975230593844, 0.0035416689300031504, 0.5627543803943077, 0.22603353810393492, 0.0, 0.0, nan, 0.17717717717717718, nan, 0.0, 0.017564022485946285, nan, 0.0, 0.0, 0.004741894444658622, 0.004261363636363636, nan, 0.19470855725506409, nan, 0.0, nan, 0.0, nan, 0.0, nan, nan, 0.0, 0.0, 0.0, nan, nan, 0.0, nan, nan, 0.0, nan, 0.0, nan, 0.0, 0.3939161833898676, 0.0, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, 0.0, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, 0.0, 0.0, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, 0.0, nan, nan, 0.0, 0.0, nan, 0.0, nan, nan, nan, nan, nan]

Framework versions

• Transformers 4.28.0
• Pytorch 2.0.1+cu118
• Datasets 2.12.0
• Tokenizers 0.13.3