Downloads · 30 days
1K
2% of all-time downloads
segformer_b0_clothes
mattmdjaga/segformer_b0_clothes
segformer_b0_clothes is a image segmentation model from mattmdjaga. 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 mit.
SegFormer model fine-tuned on ATR dataset for clothes segmentation. The dataset on hugging face is called "mattmdjaga/humanparsingdataset".
All-time downloads
51.7K
Public
Parameters
3.7M
44.8 MB on disk
Likes
12
Public
Repo makeup
Click a slice to open those files.
.bin14.9 MB · 50%
At a glance
- Task
- Image Segmentation
- Library
- transformers
- License
- mit
- Model type
- segformer
- Access
- Public
- Created
- Apr 20, 2023
- Updated
- Jul 20, 2023
- SHA
- 7142c7f9
Datasets
Spaces
Model card
From the Hugging Face model README
Segformer B0 fine-tuned for clothes segmentation
SegFormer model fine-tuned on ATR dataset for clothes segmentation. The dataset on hugging face is called "mattmdjaga/human_parsing_dataset".
from transformers import SegformerImageProcessor, AutoModelForSemanticSegmentation
from PIL import Image
import requests
import matplotlib.pyplot as plt
import torch.nn as nn
extractor = SegformerImageProcessor.from_pretrained("mattmdjaga/segformer_b0_clothes")
model = AutoModelForSemanticSegmentation.from_pretrained("mattmdjaga/segformer_b0_clothes")
url = "https://plus.unsplash.com/premium_photo-1673210886161-bfcc40f54d1f?ixlib=rb-4.0.3&ixid=MnwxMjA3fDB8MHxzZWFyY2h8MXx8cGVyc29uJTIwc3RhbmRpbmd8ZW58MHx8MHx8&w=1000&q=80"
image = Image.open(requests.get(url, stream=True).raw)
inputs = extractor(images=image, return_tensors="pt")
outputs = model(**inputs)
logits = outputs.logits.cpu()
upsampled_logits = nn.functional.interpolate(
logits,
size=image.size[::-1],
mode="bilinear",
align_corners=False,
)
pred_seg = upsampled_logits.argmax(dim=1)[0]
plt.imshow(pred_seg)
- Task
- Image Segmentation
- Library
- transformers
- Type
- segformer
- License
- mit
- Hf Inference
- live
- Created
- Apr 20, 2023
- Updated
- Jul 20, 2023