Spaces:
Running
on
Zero
Running
on
Zero
File size: 4,207 Bytes
e9e04ce 6c048e6 e9e04ce 8ef822b e9e04ce 6c048e6 37e6825 e9e04ce 37e6825 8ef822b 37e6825 6c048e6 37e6825 e9e04ce 6c048e6 37e6825 e9e04ce 37e6825 e9e04ce 37e6825 e9e04ce 37e6825 e9e04ce 37e6825 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 |
#!/usr/bin/env python
from __future__ import annotations
import os
import pathlib
import sys
import cv2
import gradio as gr
import huggingface_hub
import numpy as np
import spaces
import torch
from huggingface_hub import hf_hub_download
torch.jit.script = lambda f: f
sys.path.insert(0, "face_detection")
sys.path.insert(0, "face_parsing")
sys.path.insert(0, "fpage")
sys.path.insert(0, "roi_tanh_warping")
from ibug.age_estimation import AgeEstimator
from ibug.face_detection import RetinaFacePredictor
from ibug.face_parsing.utils import label_colormap
DESCRIPTION = "# [FP-Age](https://github.com/ibug-group/fpage)"
def is_lfs_pointer_file(path: pathlib.Path) -> bool:
try:
with open(path, "r") as f:
# Git LFS pointer files usually start with version line
version_line = f.readline()
if version_line.startswith("version https://git-lfs.github.com/spec/"):
# Check for the presence of oid and size lines
oid_line = f.readline()
size_line = f.readline()
if oid_line.startswith("oid sha256:") and size_line.startswith("size "):
return True
except Exception as e:
print(f"Error reading file {path}: {e}")
return False
lfs_model_paths = sorted(pathlib.Path("face_parsing").rglob("*.torch"))
for lfs_model_path in lfs_model_paths:
if is_lfs_pointer_file(lfs_model_path):
os.remove(lfs_model_path)
out_path = hf_hub_download(
"public-data/ibug-face-parsing",
filename=lfs_model_path.name,
repo_type="model",
subfolder=lfs_model_path.parts[-3],
)
os.symlink(out_path, lfs_model_path)
device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
detector = RetinaFacePredictor(threshold=0.8, device="cpu", model=RetinaFacePredictor.get_model("mobilenet0.25"))
detector.device = device
detector.net.to(device)
model = AgeEstimator(
device=device,
ckpt=huggingface_hub.hf_hub_download("hysts/ibug", "fpage/models/fpage-resnet50-fcn-14-97.torch"),
encoder="resnet50",
decoder="fcn",
age_classes=97,
face_classes=14,
)
@spaces.GPU
def predict(image: np.ndarray, max_num_faces: int) -> np.ndarray:
colormap = label_colormap(14)
# RGB -> BGR
image = image[:, :, ::-1]
faces = detector(image, rgb=False)
if len(faces) == 0:
raise RuntimeError("No face was found.")
faces = sorted(list(faces), key=lambda x: -x[4])[:max_num_faces][::-1]
ages, masks = model.predict_img(image, faces, rgb=False)
mask_image = np.zeros_like(image)
for mask in masks:
temp = colormap[mask]
mask_image[temp > 0] = temp[temp > 0]
res = image.astype(float) * 0.5 + mask_image[:, :, ::-1] * 0.5
res = np.clip(np.round(res), 0, 255).astype(np.uint8)
for face, age in zip(faces, ages):
bbox = np.round(face[:4]).astype(int)
cv2.rectangle(
res,
(bbox[0], bbox[1]),
(bbox[2], bbox[3]),
color=(0, 255, 0),
thickness=2,
)
text_content = f"Age: ({age: .1f})"
cv2.putText(
res,
text_content,
(bbox[0], bbox[1] - 10),
cv2.FONT_HERSHEY_DUPLEX,
1,
(255, 255, 255),
lineType=cv2.LINE_AA,
)
return res[:, :, ::-1]
with gr.Blocks(css="style.css") as demo:
gr.Markdown(DESCRIPTION)
with gr.Row():
with gr.Column():
image = gr.Image(label="Input")
max_num_faces = gr.Slider(label="Max Number of Faces", minimum=1, maximum=20, step=1, value=5)
run_button = gr.Button()
with gr.Column():
result = gr.Image(label="Output")
gr.Examples(
examples=[[path.as_posix(), 5] for path in sorted(pathlib.Path("images").rglob("*.jpg"))],
inputs=[image, max_num_faces],
outputs=result,
fn=predict,
)
run_button.click(
fn=predict,
inputs=[image, max_num_faces],
outputs=result,
api_name="predict",
)
if __name__ == "__main__":
demo.queue(max_size=20).launch()
|