Downloads · 30 days
31
3% of all-time downloads
segformer-trainer-test
nielsr/segformer-trainer-test
segformer-trainer-test is a image segmentation model from nielsr. Use it for the image segmentation task on the model card, and read the license before you ship it in a product. It is set up for transformers. The card lists the license as apache-2.0.
should probably proofread and complete it, then remove this comment. --
All-time downloads
1.2K
Public
Parameters
3.7M
135 MB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin15 MB · 50%
At a glance
- Task
- Image Segmentation
- Library
- transformers
- License
- apache-2.0
- Model type
- segformer
- Access
- Public
- Created
- Apr 19, 2022
- Updated
- Sep 14, 2023
- SHA
- 24609756
Base models
Model card
From the Hugging Face model README
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
segformer-trainer-test
This model is a fine-tuned version of nvidia/mit-b0 on the segments/sidewalk-semantic dataset. It achieves the following results on the evaluation set:
- Loss: 1.3886
- Mean Iou: 0.1391
- Mean Accuracy: 0.1905
- Overall Accuracy: 0.7192
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: 5e-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: 10.0
Training results
Framework versions
- Transformers 4.19.0.dev0
- Pytorch 1.11.0+cu113
- Datasets 2.0.0
- Tokenizers 0.11.6
- Task
- Image Segmentation
- Library
- transformers
- Type
- segformer
- License
- apache-2.0
- Created
- Apr 19, 2022
- Updated
- Sep 14, 2023