|
--- |
|
library_name: transformers |
|
datasets: |
|
- guimCC/gta5-cityscapes-labeling |
|
model-index: |
|
- name: LoRA-Segformer-B0 |
|
results: |
|
- task: |
|
type: Image Segmentation |
|
dataset: |
|
name: cityscapes |
|
type: cityscapes |
|
metrics: |
|
- type: mean_iou |
|
name: mIoU before LoRA |
|
value: 8.527 |
|
- type: mean_iou |
|
name: mIoU after LoRA |
|
value: 23.27 |
|
|
|
pipeline_tag: image-segmentation |
|
--- |
|
|
|
# Model Card for Model ID |
|
|
|
Segformer-b0 pretrained on gta5 for semantic segmentation and performed LoRA domain adaptation to cityscapes |
|
|
|
## Model Details |
|
|
|
### Model Description |
|
|
|
<!-- Provide a longer summary of what this model is. --> |
|
|
|
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. |
|
|
|
- **Developed by:** Guim Casadellà |
|
- **Model type:** [More Information Needed] |
|
- **Finetuned from model :** [segformer-v0-gta](guimCC/segformer-v0-gta) |
|
|
|
### Model Sources [optional] |
|
|
|
<!-- Provide the basic links for the model. --> |
|
|
|
- **Repository:** [Github script link](https://github.com/guimCC/LoRA-for-SemanticSegmentation-domain-adaptation/blob/main/scripts/lora_gta_to_cityscapes_clean.py) |
|
- **Demo [optional]:** [More Information Needed] |
|
|
