Pirate Face
⌘K
Models
Leaderboard
Activity
Rescue
Submit
ZK Inference
Resources
Log in
Sign up
Models
Leaderboard
Activity
Rescue
Submit
ZK Inference
Resources
Articles
How it works
𝕏 @ThePirateFace
Log in
Sign up
Language
中文
Theme
☀ Light
🌙 Dark
alanoix/segformer_b0_flair_one · Pirate Face
alanoix
/
segformer_b0_flair_one
Source: 🤗
At risk
🏴☠️ Rescued by: isilicon
image-segmentation
apache-2.0
15 MB
other
✓ 3 checksums
updated 1,329d ago
Model card
Files & versions
Comments (0)
🧲
Magnet
🌱
0
Download
▾
✓ Verify
▾
Loading…
pretrained model
https://huggingface.co/nvidia/mit-b0
SegFormer (b0-sized) encoder pre-trained-only
SegFormer encoder fine-tuned on Imagenet-1k. It was introduced in the paper SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers by Xie et al. and first released in this repository.
training-set
you can find the training-set here :
https://codalab.lisn.upsaclay.fr/competitions/8769
training-arguments
channels : rgb
batch : 8
epochs : 8
learning-rate : 5e-6
GPU : T4
results on test-set
Mean IoU : 59.9
more information here :
https://codalab.lisn.upsaclay.fr/competitions/8769