segformer-b0-scene-parse-1502

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: 2.4662
• eval_mean_iou: 0.0896
• eval_mean_accuracy: 0.1488
• eval_overall_accuracy: 0.6372
• eval_per_category_iou: [0.49227372671878594, 0.5532565415244596, 0.9483966776020463, 0.4564028097943477, 0.3441962504986039, 0.4576400132036027, 0.5344129222022298, 0.2900375472301515, 0.0, 0.6730487219899952, 0.0, 0.0, 0.0, nan, 0.0, 0.0, nan, 0.0, 0.0, 0.0, 0.0, nan, 0.0, nan, nan, 0.0, 0.0, nan, 0.0, nan, 0.0, 0.0, nan, 0.0, nan, nan, 0.0, nan, 0.0, 0.0, nan, nan, 0.0, 0.0, nan, nan, 0.0, nan, nan, nan, nan, 0.0, 0.0, 0.0, nan, nan, nan, 0.0, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan, 0.0, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, 0.0, 0.0, nan, 0.0, 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, nan, 0.0, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan]
• eval_per_category_accuracy: [0.6219459883933374, 0.9121453160561318, 0.9753296111445005, 0.5487499345286939, 0.7937145485206194, 0.9112436777004357, 0.9588236739306685, 0.623475493316359, 0.0, 0.7976902085634462, nan, 0.0, 0.0, nan, 0.0, 0.0, nan, 0.0, 0.0, 0.0, 0.0, nan, 0.0, nan, nan, 0.0, 0.0, nan, 0.0, nan, 0.0, nan, nan, nan, nan, nan, 0.0, nan, 0.0, 0.0, nan, nan, 0.0, 0.0, nan, nan, 0.0, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, 0.0, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, 0.0, 0.0, nan, 0.0, 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, nan, 0.0, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan]
• eval_runtime: 16.2659
• eval_samples_per_second: 0.615
• eval_steps_per_second: 0.307
• epoch: 11.0
• step: 220

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 4.31.0
• Pytorch 2.0.1+cu118
• Datasets 2.14.4
• Tokenizers 0.13.3