jonathandinu

/

face-parsing

like 126

Hi, i wonder this too, did you find a solution?

@Senem @cenahwang

from transformers import SegformerImageProcessor, AutoModelForSemanticSegmentation
from PIL import Image
import requests
import matplotlib.pyplot as plt
import torch.nn as nn
import numpy as np

processor = SegformerImageProcessor.from_pretrained("jonathandinu/face-parsing")
model = AutoModelForSemanticSegmentation.from_pretrained("jonathandinu/face-parsing")

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 = processor(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]

pred_seg_np = pred_seg.detach().numpy()

plt.imshow(pred_seg_np)
plt.axis('off')
plt.show()

Thank you very much. I am able to get the output.
I am wondering that how to get segmentation parts seperately with their names as running on Huggingface.
Such as left eye , nose etc.

@Senem check config.json in files, there you can find labels definition in id2label prop.
Then just filter output by specific number.

finally got around to adding a proper README, thanks for bearing with me and the examples/help here 🙏