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: 3.6538
• Mean Iou: 0.0513
• Mean Accuracy: 0.1002
• Overall Accuracy: 0.3674
• Per Category Iou: [0.41523063020750783, 0.009939916202993341, 0.9051053539418947, 0.2405546042011158, 0.5592627102446484, 0.008100205817661452, 0.4158655729996604, 0.0, nan, 0.0, 0.0, 0.0, 0.1653567193403381, nan, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, nan, 0.00014481591921904725, 0.0, 0.0, nan, nan, 0.0, 0.0, nan, 0.0, nan, nan, 0.0, nan, 0.0, 0.0, nan, nan, nan, 0.0, 0.0, nan, 0.0, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, 0.0, 0.0, 0.0, nan, nan, 0.0, 0.0, nan]
• Per Category Accuracy: [0.9111665467920647, 0.5584905660377358, 0.96496051635236, 0.7798917474318848, 0.9961487722881824, 0.008167736993524596, 0.4204927396509486, nan, nan, nan, 0.0, 0.0, 0.17034574845876305, nan, 0.0, 0.0, nan, 0.0, nan, 0.0, 0.0, nan, 0.00014681348014681348, 0.0, 0.0, nan, nan, 0.0, 0.0, nan, 0.0, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, 0.0, 0.0, nan, 0.0, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, 0.0, 0.0, 0.0, nan, nan, 0.0, 0.0, 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: 4
• eval_batch_size: 4
• 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
3.2677	2.0	20	3.6205	0.0524	0.0966	0.3613	[0.40213077197792346, 0.009939273919119628, 0.8721087225424647, 0.2050790121535925, 0.6743243243243243, 0.006688714489444168, 0.4140137237846719, 0.0, nan, 0.0, 0.0, 0.0, 0.15446220048180365, nan, 0.0, 0.0, nan, 0.0, 0.0, 0.003601957810561147, 0.0, nan, 0.0, 0.0, 0.0, nan, nan, 0.0, 0.0, nan, 0.0, nan, nan, 0.0, nan, 0.0, 0.0, nan, nan, nan, 0.0, 0.0, nan, 0.0, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, 0.0, 0.00043712407329696463, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, 0.0, nan, 0.0, nan, nan, nan, nan, 0.03405304544848727, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, 0.0, 0.0, 0.0, nan, nan, 0.0, 0.0, nan]	[0.9390478618316233, 0.46037735849056605, 0.972415533840551, 0.6499966195928399, 0.9874249968083748, 0.006809416501144552, 0.4243094579335574, nan, nan, nan, 0.0, 0.0, 0.1590859588814076, nan, 0.0, 0.0, nan, 0.0, nan, 0.003607242099449421, 0.0, nan, 0.0, 0.0, 0.0, nan, nan, 0.0, 0.0, nan, 0.0, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, 0.0, 0.0, nan, 0.0, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, 0.0, 0.00043712407329696463, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, 0.0, nan, nan, nan, nan, 0.03405304544848727, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, 0.0, 0.0, 0.0, nan, nan, 0.0, 0.0, nan]
3.1569	4.0	40	3.6538	0.0513	0.1002	0.3674	[0.41523063020750783, 0.009939916202993341, 0.9051053539418947, 0.2405546042011158, 0.5592627102446484, 0.008100205817661452, 0.4158655729996604, 0.0, nan, 0.0, 0.0, 0.0, 0.1653567193403381, nan, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, nan, 0.00014481591921904725, 0.0, 0.0, nan, nan, 0.0, 0.0, nan, 0.0, nan, nan, 0.0, nan, 0.0, 0.0, nan, nan, nan, 0.0, 0.0, nan, 0.0, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, 0.0, 0.0, 0.0, nan, nan, 0.0, 0.0, nan]	[0.9111665467920647, 0.5584905660377358, 0.96496051635236, 0.7798917474318848, 0.9961487722881824, 0.008167736993524596, 0.4204927396509486, nan, nan, nan, 0.0, 0.0, 0.17034574845876305, nan, 0.0, 0.0, nan, 0.0, nan, 0.0, 0.0, nan, 0.00014681348014681348, 0.0, 0.0, nan, nan, 0.0, 0.0, nan, 0.0, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, 0.0, 0.0, nan, 0.0, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, 0.0, 0.0, 0.0, nan, nan, 0.0, 0.0, nan]

Framework versions

• Transformers 4.41.2
• Pytorch 2.3.0+cu121
• Datasets 2.20.0
• Tokenizers 0.19.1