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: 2.4563
• eval_mean_iou: 0.0432
• eval_mean_accuracy: 0.0696
• eval_overall_accuracy: 0.5913
• eval_per_category_iou: [0.4472851919015029, 0.6612097108758626, 0.817339666449671, 0.47928449607416507, 0.5911507360971395, 0.584974453286796, 0.6726074613245039, 0.2589327338580983, 0.022897061669389426, 0.3531389341071555, 0.0009033242331780954, 0.0, 0.38016586218727527, 0.0065494844799213895, 3.5410365901749114e-05, 0.0006227857923162527, 0.1369807957501803, 0.0, 0.0, 0.0, 0.3866305742675126, 0.0, 0.0, 0.0, 0.0, 0.0, 0.15958629131507837, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, nan, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, nan, 0.0, 0.0, 0.0, 0.0, nan, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, nan, 0.0, 0.0, 0.0, 0.0, nan, 0.0, 0.0, nan, 0.0, 0.0, 0.0, 0.0, 0.0, nan, nan, 0.0, 0.0, nan, 0.0, nan, 0.0, nan, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, nan, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0]
• eval_per_category_accuracy: [0.8334025427555467, 0.90546175118556, 0.9576760329344776, 0.9040202679951341, 0.9084813897020947, 0.7543100790506285, 0.924642649916285, 0.6768858942434451, 0.024248627368742136, 0.8855665819147363, 0.0009169818241372258, 0.0, 0.7872266396753254, 0.006739498091427447, 3.561201678944719e-05, 0.0006261997885292518, 0.24443709595222143, 0.0, 0.0, 0.0, 0.6322151772008276, 0.0, 0.0, 0.0, 0.0, 0.0, 0.16159973151359214, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, nan, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, nan, 0.0, 0.0, 0.0, 0.0, nan, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, nan, 0.0, 0.0, 0.0, 0.0, nan, 0.0, 0.0, nan, 0.0, 0.0, 0.0, 0.0, 0.0, nan, nan, 0.0, 0.0, nan, 0.0, nan, 0.0, nan, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, nan, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0]
• eval_runtime: 22.5623
• eval_samples_per_second: 8.864
• eval_steps_per_second: 0.576
• epoch: 4.8
• step: 240

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: 16
• eval_batch_size: 16
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 50

Framework versions

• Transformers 4.40.1
• Pytorch 2.2.1+cu121
• Datasets 2.19.0
• Tokenizers 0.19.1