Hugging Face's logo

alex-levashov
/
segformer-b0-scene-parse-150

Transformers
PyTorch
TensorBoard
Safetensors
segformer
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
segformer-b0-scene-parse-150 / README.md
alex-levashov's picture
alex-levashov
update model card README.md
d1696f9
preview code
|
raw
history blame
14.5 kB
metadata
license: other
tags:
  - generated_from_trainer
datasets:
  - scene_parse_150
model-index:
  - name: segformer-b0-scene-parse-150
    results: []

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: 2.9008
  • Mean Iou: 0.0724
  • Mean Accuracy: 0.1672
  • Overall Accuracy: 0.5120
  • Per Category Iou: [0.3941812537977788, 0.603256614612533, 0.8760437006158173, 0.3979304047884752, 0.38783838783838787, 0.2577783348653241, 0.08173937623669085, 0.0, 0.0, nan, 0.0, 0.04974595603484031, 0.4777014865675622, 0.0, 0.0, 0.0, 0.0, 0.0, nan, 0.018969737427681353, 0.0, 0.0, 0.0, nan, nan, nan, 0.0, 0.0, nan, 0.0, nan, nan, 0.0, 0.0, 0.0, 0.0, nan, nan, nan, nan, nan, 0.0, nan, 0.0, 0.0, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, 0.0, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan, nan, 0.0, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, 0.0, 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, 0.0, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan]
  • Per Category Accuracy: [0.6715442084388291, 0.9704986034018984, 0.9463499620965276, 0.8188327638876325, 0.7766592506112738, 0.7418288210657101, 0.18556943612560964, nan, 0.0, nan, 0.0, 0.8544078361531612, 0.7031464643160855, nan, 0.0, 0.0, 0.0, 0.0, nan, 0.019859642992341515, nan, nan, 0.0, nan, nan, nan, 0.0, 0.0, nan, 0.0, nan, nan, 0.0, 0.0, nan, 0.0, nan, nan, nan, nan, nan, 0.0, nan, 0.0, 0.0, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, 0.0, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, 0.0, 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, nan, nan, 0.0, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, 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: 40

Training results

Training Loss Epoch Step Validation Loss Mean Iou Mean Accuracy Overall Accuracy Per Category Iou Per Category Accuracy
2.8938 10.0 200 3.0006 0.0710 0.1593 0.5191 [0.40383784749628215, 0.6411181006332807, 0.8549643176281934, 0.36384580697175495, 0.31994243914138387, 0.3185986482355738, 0.0, 0.0, 0.0, nan, 0.0, 0.014444130182477836, 0.48976014025021913, 0.0, 0.0, 0.0, 0.0, 0.0, nan, 0.0, nan, nan, 0.0, nan, nan, nan, 0.0, 0.0, nan, 0.0, nan, nan, 0.0, 0.0, 0.0, 0.0, nan, nan, nan, nan, nan, 0.0, nan, 0.0, 0.0, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, 0.0, nan, 0.0, nan, 0.0, nan, nan, 0.0, nan, nan, nan, 0.0, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, 0.0, 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, nan, nan, 0.0, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan] [0.7159983536425658, 0.9649797562807182, 0.9288957455014563, 0.9264197290319887, 0.8227856466286319, 0.7519288190617422, 0.0, nan, 0.0, nan, 0.0, 0.6593944790739091, 0.6030614247399751, nan, 0.0, 0.0, 0.0, 0.0, nan, 0.0, nan, nan, 0.0, nan, nan, nan, 0.0, 0.0, nan, 0.0, nan, nan, 0.0, 0.0, nan, 0.0, nan, nan, nan, nan, nan, 0.0, nan, 0.0, 0.0, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, 0.0, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, 0.0, 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, nan, nan, 0.0, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan]
2.0467 20.0 400 2.8973 0.0747 0.1654 0.5151 [0.3852134422255253, 0.6174974463214196, 0.87619031095557, 0.40460448142613914, 0.39580944893925996, 0.32205428376698875, 0.0, 0.0, 0.0, nan, 0.0, 0.025051789137791273, 0.4838395999259122, 0.0, 0.0, 0.0, 0.0, 0.0, nan, 0.0018080705695422295, nan, nan, 0.0, nan, 0.0, nan, 0.0, 0.0, nan, 0.0, nan, nan, 0.0, 0.0, 0.0, 0.0, nan, nan, nan, nan, nan, 0.0, nan, 0.0, 0.0, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, 0.0, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, 0.0, 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, nan, nan, 0.0, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan] [0.7007745363383514, 0.9559565008363695, 0.9403066856405687, 0.8648569659098025, 0.7985329427054652, 0.8048936895052203, 0.0, nan, 0.0, nan, 0.0, 0.8668744434550312, 0.6835219467521424, nan, 0.0, 0.0, 0.0, 0.0, nan, 0.0019219009347427273, nan, nan, 0.0, nan, nan, nan, 0.0, 0.0, nan, 0.0, nan, nan, 0.0, 0.0, nan, 0.0, nan, nan, nan, nan, nan, 0.0, nan, 0.0, 0.0, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, 0.0, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, 0.0, 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, nan, nan, 0.0, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan]
1.8859 30.0 600 2.8326 0.0734 0.1657 0.5153 [0.38548176994062716, 0.6162153943617358, 0.8639633146456023, 0.405245609206295, 0.3998403471886489, 0.3214837969506011, 0.03200938172869886, 0.0, 0.0, nan, 0.0, 0.034576693670435324, 0.5323921920127478, 0.0, 0.0, 0.0, 0.0, 0.0, nan, 0.0072492273110424275, 0.0, nan, 0.0, nan, 0.0, nan, 0.0, 0.0, nan, 0.0, nan, nan, 0.0, 0.0, 0.0, 0.0, nan, nan, nan, nan, nan, 0.0, nan, 0.0, 0.0, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, 0.0, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, 0.0, 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, 0.0, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan] [0.7012684435686045, 0.9661915981611789, 0.9501562687023712, 0.8093829806481243, 0.7833777562393991, 0.7749343700527044, 0.0712329939248738, nan, 0.0, nan, 0.0, 0.8646482635796973, 0.6993850984496631, nan, 0.0, 0.0, 0.0, 0.0, nan, 0.007512885472176116, nan, nan, 0.0, nan, nan, nan, 0.0, 0.0, nan, 0.0, nan, nan, 0.0, 0.0, nan, 0.0, nan, nan, nan, nan, nan, 0.0, nan, 0.0, 0.0, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, 0.0, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, 0.0, 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, nan, nan, 0.0, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan]
1.6424 40.0 800 2.9008 0.0724 0.1672 0.5120 [0.3941812537977788, 0.603256614612533, 0.8760437006158173, 0.3979304047884752, 0.38783838783838787, 0.2577783348653241, 0.08173937623669085, 0.0, 0.0, nan, 0.0, 0.04974595603484031, 0.4777014865675622, 0.0, 0.0, 0.0, 0.0, 0.0, nan, 0.018969737427681353, 0.0, 0.0, 0.0, nan, nan, nan, 0.0, 0.0, nan, 0.0, nan, nan, 0.0, 0.0, 0.0, 0.0, nan, nan, nan, nan, nan, 0.0, nan, 0.0, 0.0, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, 0.0, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan, nan, 0.0, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, 0.0, 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, 0.0, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan] [0.6715442084388291, 0.9704986034018984, 0.9463499620965276, 0.8188327638876325, 0.7766592506112738, 0.7418288210657101, 0.18556943612560964, nan, 0.0, nan, 0.0, 0.8544078361531612, 0.7031464643160855, nan, 0.0, 0.0, 0.0, 0.0, nan, 0.019859642992341515, nan, nan, 0.0, nan, nan, nan, 0.0, 0.0, nan, 0.0, nan, nan, 0.0, 0.0, nan, 0.0, nan, nan, nan, nan, nan, 0.0, nan, 0.0, 0.0, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, 0.0, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, 0.0, 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, nan, nan, 0.0, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan]

Framework versions

  • Transformers 4.27.4
  • Pytorch 1.13.1+cu116
  • Datasets 2.11.0
  • Tokenizers 0.13.2