<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
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: 3.1876
- Mean Iou: 0.0552
- Mean Accuracy: 0.1069
- Overall Accuracy: 0.3425
- Per Category Iou: [0.3214630828545835, 0.20601478596854178, 0.0, 0.27354650591173274, 0.8417970372421432, 0.31385557540188824, 0.0, 0.01546660166853167, 0.22122126594808622, 0.0, 0.0, nan, 0.0, nan, 0.0, 2.2945779123930152e-05, 0.0, 0.0, 0.0, 0.0, 0.7301226048014096, 0.0, 0.0, 0.0, 0.0, nan, nan, 0.0, 0.0, nan, 0.0, nan, nan, nan, 0.0, 0.0, 0.0, nan, nan, 0.0, 0.0, 0.0, 0.0, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, 0.0, nan, 0.0, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, 0.0, 0.0, 0.0, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 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, 0.0, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, 0.0]
- Per Category Accuracy: [0.6886871880793561, 0.21227660902890075, nan, 0.6349079054604727, 0.9073991165234002, 0.4336075205640423, 0.0, 0.7316561844863732, 0.526753854715684, nan, 0.0, nan, 0.0, nan, 0.0, 2.4867580135776987e-05, nan, 0.0, 0.0, 0.0, 0.9956150888995675, 0.0, 0.0, 0.0, 0.0, nan, nan, 0.0, 0.0, nan, 0.0, nan, nan, nan, 0.0, nan, 0.0, nan, nan, 0.0, 0.0, 0.0, 0.0, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, 0.0, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, 0.0, 0.0, 0.0, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 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, 0.0, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, 0.0]
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: 50
Training results
Training Loss | Epoch | Step | Validation Loss | Mean Iou | Mean Accuracy | Overall Accuracy | Per Category Iou | Per Category Accuracy |
---|---|---|---|---|---|---|---|---|
3.3524 | 10.0 | 200 | 3.8180 | 0.0487 | 0.0861 | 0.3106 | [0.28264084958802793, 0.13653014326488203, nan, 0.2426731008687142, 0.5869845712104966, 0.15486259971561986, 0.0, 0.0, 0.12131720003418761, nan, 0.0, nan, 0.1521135572674305, nan, 0.0, 0.003742531845338744, 0.0, 0.0, 0.0, 0.0, 0.804619907601848, 0.0, 0.0, 0.0, 0.0, nan, nan, 0.0, 0.0, nan, 0.0, nan, nan, nan, 0.0, 0.0, 0.0, nan, nan, 0.0, 0.0, 0.0, 0.0, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, 0.0, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, 0.0, nan, nan, 0.0, 0.0, 0.0, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 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, 0.0, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, 0.0] | [0.7354283062800898, 0.14108408460969768, nan, 0.6531312143439283, 0.9640639923591213, 0.19255421429334474, 0.0, 0.0, 0.32526925721020067, nan, 0.0, nan, 0.15791182917918326, nan, 0.0, 0.00412801830253898, nan, 0.0, 0.0, 0.0, 0.9589740509370495, 0.0, 0.0, 0.0, 0.0, nan, nan, 0.0, 0.0, nan, 0.0, nan, nan, nan, 0.0, nan, 0.0, nan, nan, 0.0, 0.0, 0.0, 0.0, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, 0.0, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, 0.0, 0.0, 0.0, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 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, 0.0, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, 0.0] |
2.2636 | 20.0 | 400 | 3.4040 | 0.0517 | 0.1019 | 0.3658 | [0.33166172632681973, 0.25639742510747676, 0.0, 0.31599466350429883, 0.5561154794429266, 0.35978479196556673, 0.0, 0.0, 0.17355201427598316, 0.0, 0.0, nan, 0.044999799108039695, nan, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.8064841803585677, 0.0, 0.0, 0.0, 0.0, nan, nan, 0.0, 0.0, nan, 0.0, nan, nan, 0.0, 0.0, 0.0, 0.0, nan, nan, 0.0, 0.0, 0.0, 0.0, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, 0.0, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, 0.0, nan, nan, 0.0, 0.0, 0.0, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, 0.0, 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, 0.0, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, 0.0] | [0.6326427775083301, 0.2650205202289488, nan, 0.8339168704156479, 0.9963735673352435, 0.5357760922978314, 0.0, 0.0, 0.5921858120273676, nan, 0.0, nan, 0.04546561662742551, nan, 0.0, 0.0, nan, 0.0, 0.0, 0.0, 0.9916506487265737, 0.0, 0.0, 0.0, 0.0, nan, nan, 0.0, 0.0, nan, 0.0, nan, nan, nan, 0.0, nan, 0.0, nan, nan, 0.0, 0.0, 0.0, 0.0, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, 0.0, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, 0.0, 0.0, 0.0, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 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, 0.0, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, 0.0] |
2.2348 | 30.0 | 600 | 3.2677 | 0.0565 | 0.1118 | 0.3566 | [0.3298261859499856, 0.2894205494486437, 0.0, 0.3071140867987943, 0.8268382637402316, 0.29503716045453693, 0.0, 0.016577746627951882, 0.19118079400826032, 0.0, 0.0, nan, 0.0, nan, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.7963919599607332, 0.0, 0.0, 0.0, 0.0, nan, nan, 0.0, 0.0, nan, 0.0, nan, nan, nan, 0.0, 0.0, 0.0, nan, nan, 0.0, 0.0, 0.0, 0.0, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, 0.0, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, 0.0, nan, nan, 0.0, 0.0, 0.0, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, 0.0, 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, 0.0, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, 0.0] | [0.63567038924337, 0.3051832191288764, nan, 0.7506699266503668, 0.9568708213944603, 0.42089520350389914, 0.0, 0.7593029350104822, 0.5481716698857498, nan, 0.0, nan, 0.0, nan, 0.0, 0.0, nan, 0.0, 0.0, 0.0, 0.9908497517219286, 0.0, 0.0, 0.0, 0.0, nan, nan, 0.0, 0.0, nan, 0.0, nan, nan, nan, 0.0, nan, 0.0, nan, nan, 0.0, 0.0, 0.0, 0.0, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, 0.0, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, 0.0, 0.0, 0.0, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 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, 0.0, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, 0.0] |
1.2898 | 40.0 | 800 | 3.2263 | 0.0552 | 0.1117 | 0.3476 | [0.3202981498179875, 0.2523853763872847, 0.0, 0.2830716149865086, 0.8220650746811913, 0.33176841169245147, 0.0, 0.01711185745524551, 0.22195317764572742, 0.0, 0.0, nan, 0.0, nan, 0.0, 2.2602956466705847e-05, 0.0, 0.0, 0.0, 0.0, 0.7303736186117692, 0.0, 0.0, 0.0, 0.0, nan, nan, 0.0, 0.0, nan, 0.0, nan, nan, nan, 0.0, 0.0, 0.0, nan, nan, 0.0, 0.0, 0.0, 0.0, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, 0.0, nan, 0.0, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, 0.0, 0.0, 0.0, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, 0.0, 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, 0.0, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, 0.0] | [0.6443689991034742, 0.2625831715835974, nan, 0.6258581907090465, 0.9437529847182426, 0.47031300074778337, 0.0, 0.8571802935010482, 0.5633859298785479, nan, 0.0, nan, 0.0, nan, 0.0, 2.4867580135776987e-05, nan, 0.0, 0.0, 0.0, 0.9937930482139997, 0.0, 0.0, 0.0, 0.0, nan, nan, 0.0, 0.0, nan, 0.0, nan, nan, nan, 0.0, nan, 0.0, nan, nan, 0.0, 0.0, 0.0, 0.0, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, 0.0, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, 0.0, 0.0, 0.0, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 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, 0.0, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, 0.0] |
0.9923 | 50.0 | 1000 | 3.1876 | 0.0552 | 0.1069 | 0.3425 | [0.3214630828545835, 0.20601478596854178, 0.0, 0.27354650591173274, 0.8417970372421432, 0.31385557540188824, 0.0, 0.01546660166853167, 0.22122126594808622, 0.0, 0.0, nan, 0.0, nan, 0.0, 2.2945779123930152e-05, 0.0, 0.0, 0.0, 0.0, 0.7301226048014096, 0.0, 0.0, 0.0, 0.0, nan, nan, 0.0, 0.0, nan, 0.0, nan, nan, nan, 0.0, 0.0, 0.0, nan, nan, 0.0, 0.0, 0.0, 0.0, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, 0.0, nan, 0.0, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, 0.0, 0.0, 0.0, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 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, 0.0, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, 0.0] | [0.6886871880793561, 0.21227660902890075, nan, 0.6349079054604727, 0.9073991165234002, 0.4336075205640423, 0.0, 0.7316561844863732, 0.526753854715684, nan, 0.0, nan, 0.0, nan, 0.0, 2.4867580135776987e-05, nan, 0.0, 0.0, 0.0, 0.9956150888995675, 0.0, 0.0, 0.0, 0.0, nan, nan, 0.0, 0.0, nan, 0.0, nan, nan, nan, 0.0, nan, 0.0, nan, nan, 0.0, 0.0, 0.0, 0.0, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, 0.0, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, 0.0, 0.0, 0.0, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 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, 0.0, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, 0.0] |
Framework versions
- Transformers 4.29.2
- Pytorch 2.0.1+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3