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
End of training
22a276a
preview code
|
raw
history blame
3.25 kB
metadata
license: other
base_model: nvidia/mit-b0
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:

  • eval_loss: 3.1572
  • eval_mean_iou: 0.0576
  • eval_mean_accuracy: 0.1024
  • eval_overall_accuracy: 0.4494
  • eval_per_category_iou: [0.4122169623263367, 0.3410702102532667, 0.5602481859291197, 0.4322339707691856, 0.6822868377772705, 0.3710882712402531, 0.035435037700556504, 0.16723774313303955, 0.09070640694672612, 0.0, 0.06035674019253563, nan, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.014934434191355027, nan, nan, 0.0, 0.0, 0.0, nan, 0.0, 0.0, 0.0, nan, 0.0, nan, nan, nan, nan, nan, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, nan, 0.0, nan, nan, nan, 0.0, 0.0, 0.0, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, 0.0, 0.0, nan, 0.0, 0.0, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, 0.0, nan, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan]
  • eval_per_category_accuracy: [0.7521353846678954, 0.6404357015119493, 0.5938931808300726, 0.7152574899548504, 0.9285709756576986, 0.6115768819122369, 0.38490661282180716, 0.3173203627625765, 0.18718022824380376, nan, 0.07594816986664145, nan, 0.0, 0.0, 0.0, 0.0, nan, 0.0, 0.0, 0.015227012472532574, nan, nan, 0.0, 0.0, 0.0, nan, nan, 0.0, 0.0, nan, 0.0, nan, nan, nan, nan, nan, 0.0, 0.0, 0.0, 0.0, nan, 0.0, nan, 0.0, nan, nan, nan, 0.0, 0.0, 0.0, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, 0.0, 0.0, nan, 0.0, 0.0, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, 0.0, nan, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan]
  • eval_runtime: 26.7781
  • eval_samples_per_second: 0.373
  • eval_steps_per_second: 0.187
  • epoch: 20.0
  • step: 400

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

Framework versions

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