README.md

metadata

license: other
tags:
  - image-segmentation
  - vision
  - generated_from_trainer
model-index:
  - name: mobilenet_v2_1-10k-steps
    results: []

mobilenet_v2_1-10k-steps

This model is a fine-tuned version of google/mobilenet_v2_1.0_224 on the Efferbach/lane_master2 dataset. It achieves the following results on the evaluation set:

• Loss: 0.0827
• Mean Iou: 0.0
• Mean Accuracy: 0.0
• Overall Accuracy: 0.0
• Accuracy Background: nan
• Accuracy Left: 0.0
• Accuracy Right: 0.0
• Iou Background: 0.0
• Iou Left: 0.0
• Iou Right: 0.0

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: 1337
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: polynomial
• training_steps: 10000

Training results

Training Loss	Epoch	Step	Validation Loss	Mean Iou	Mean Accuracy	Overall Accuracy	Accuracy Background	Accuracy Left	Accuracy Right	Iou Background	Iou Left	Iou Right
0.3253	1.0	385	0.0989	0.0	0.0	0.0	nan	0.0	0.0	0.0	0.0	0.0
0.128	2.0	770	0.1518	0.0	0.0	0.0	nan	0.0	0.0	0.0	0.0	0.0
0.1212	3.0	1155	0.1852	0.0	0.0	0.0	nan	0.0	0.0	0.0	0.0	0.0
0.117	4.0	1540	0.1446	0.0	0.0	0.0	nan	0.0	0.0	0.0	0.0	0.0
0.1148	5.0	1925	0.1087	0.0	0.0	0.0	nan	0.0	0.0	0.0	0.0	0.0
0.1167	6.0	2310	0.1502	0.0	0.0	0.0	nan	0.0	0.0	0.0	0.0	0.0
0.1128	7.0	2695	0.0882	0.0	0.0	0.0	nan	0.0	0.0	0.0	0.0	0.0
0.1156	8.0	3080	0.1005	0.0	0.0	0.0	nan	0.0	0.0	0.0	0.0	0.0
0.1164	9.0	3465	0.0844	0.0	0.0	0.0	nan	0.0	0.0	0.0	0.0	0.0
0.1128	10.0	3850	0.1497	0.0	0.0	0.0	nan	0.0	0.0	0.0	0.0	0.0
0.1151	11.0	4235	0.1024	0.0	0.0	0.0	nan	0.0	0.0	0.0	0.0	0.0
0.1112	12.0	4620	0.0869	0.0	0.0	0.0	nan	0.0	0.0	0.0	0.0	0.0
0.1093	13.0	5005	0.0940	0.0	0.0	0.0	nan	0.0	0.0	0.0	0.0	0.0
0.1102	14.0	5390	0.0914	0.0	0.0	0.0	nan	0.0	0.0	0.0	0.0	0.0
0.1111	15.0	5775	0.1047	0.0	0.0	0.0	nan	0.0	0.0	0.0	0.0	0.0
0.1087	16.0	6160	0.1104	0.0	0.0	0.0	nan	0.0	0.0	0.0	0.0	0.0
0.1105	17.0	6545	0.0970	0.0	0.0	0.0	nan	0.0	0.0	0.0	0.0	0.0
0.1083	18.0	6930	0.0868	0.0	0.0	0.0	nan	0.0	0.0	0.0	0.0	0.0
0.1077	19.0	7315	0.1121	0.0	0.0	0.0	nan	0.0	0.0	0.0	0.0	0.0
0.1115	20.0	7700	0.2092	0.0	0.0	0.0	nan	0.0	0.0	0.0	0.0	0.0
0.1102	21.0	8085	0.0850	0.0	0.0	0.0	nan	0.0	0.0	0.0	0.0	0.0
0.1077	22.0	8470	0.1011	0.0	0.0	0.0	nan	0.0	0.0	0.0	0.0	0.0
0.1111	23.0	8855	0.1136	0.0	0.0	0.0	nan	0.0	0.0	0.0	0.0	0.0
0.1099	24.0	9240	0.1001	0.0	0.0	0.0	nan	0.0	0.0	0.0	0.0	0.0
0.1086	25.0	9625	0.0997	0.0	0.0	0.0	nan	0.0	0.0	0.0	0.0	0.0
0.1066	25.97	10000	0.0827	0.0	0.0	0.0	nan	0.0	0.0	0.0	0.0	0.0

Framework versions

• Transformers 4.28.0.dev0
• Pytorch 2.0.0+cu118
• Datasets 2.11.0
• Tokenizers 0.13.3