Hugging Face's logo

gabryland
/
segformer-b0-scene-parse-150

Transformers
PyTorch
mobilenet_v2
Generated from Trainer
Inference Endpoints
Model card Files Community
segformer-b0-scene-parse-150 / README.md
gabryland's picture
gabryland
End of training
6f24dba
preview code
|
raw
history blame
No virus
8.77 kB
metadata
license: other
base_model: google/deeplabv3_mobilenet_v2_1.0_513
tags:
  - generated_from_trainer
model-index:
  - name: segformer-b0-scene-parse-150
    results: []

segformer-b0-scene-parse-150

This model is a fine-tuned version of google/deeplabv3_mobilenet_v2_1.0_513 on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 1.1442
  • Mean Iou: 0.1706
  • Mean Accuracy: 0.2476
  • Overall Accuracy: 0.6920
  • Per Category Iou: [0.705664723495685, 0.0, 0.2945498698407734, 0.15866935715587488, 0.24342079786953616, 0.11915867259300646, 0.0, 0.5229415532605887, 0.036924608676334424, nan, 0.0, 0.025463760124691207, 0.11154955129652562, 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, 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, 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, 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]
  • Per Category Accuracy: [0.8930569085478202, 0.0, 0.7296482164731961, 0.2190295196554057, 0.35630974275062677, 0.16804377674049947, 0.0, 0.6688736616254668, 0.03693401153549208, nan, 0.0, 0.025467207386923568, 0.12141354618920469, 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, 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, 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, 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]

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: 8
  • eval_batch_size: 8
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 5

Training results

Training Loss Epoch Step Validation Loss Mean Iou Mean Accuracy Overall Accuracy Per Category Iou Per Category Accuracy
1.0965 3.12 400 1.1442 0.1706 0.2476 0.6920 [0.705664723495685, 0.0, 0.2945498698407734, 0.15866935715587488, 0.24342079786953616, 0.11915867259300646, 0.0, 0.5229415532605887, 0.036924608676334424, nan, 0.0, 0.025463760124691207, 0.11154955129652562, 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, 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, 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, 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] [0.8930569085478202, 0.0, 0.7296482164731961, 0.2190295196554057, 0.35630974275062677, 0.16804377674049947, 0.0, 0.6688736616254668, 0.03693401153549208, nan, 0.0, 0.025467207386923568, 0.12141354618920469, 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, 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, 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, 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]

Framework versions

  • Transformers 4.32.1
  • Pytorch 2.0.1+cu118
  • Datasets 2.14.4
  • Tokenizers 0.13.3