File size: 5,290 Bytes
2071150 |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 |
#!/usr/bin/env python
import argparse
import functools
import os
import pathlib
import cv2
import dlib
import gradio as gr
import huggingface_hub
import numpy as np
import pretrainedmodels
import torch
import torch.nn as nn
import torch.nn.functional as F
TOKEN = os.environ['TOKEN']
MODEL_REPO = 'hysts/yu4u-age-estimation-pytorch'
MODEL_FILENAME = 'pretrained.pth'
def parse_args() -> argparse.Namespace:
parser = argparse.ArgumentParser()
parser.add_argument('--device', type=str, default='cpu')
parser.add_argument('--theme', type=str)
parser.add_argument('--live', action='store_true')
parser.add_argument('--share', action='store_true')
parser.add_argument('--port', type=int)
parser.add_argument('--disable-queue',
dest='enable_queue',
action='store_false')
parser.add_argument('--allow-flagging', type=str, default='never')
parser.add_argument('--allow-screenshot', action='store_true')
return parser.parse_args()
def get_model(model_name='se_resnext50_32x4d',
num_classes=101,
pretrained='imagenet'):
model = pretrainedmodels.__dict__[model_name](pretrained=pretrained)
dim_feats = model.last_linear.in_features
model.last_linear = nn.Linear(dim_feats, num_classes)
model.avg_pool = nn.AdaptiveAvgPool2d(1)
return model
def load_model(device):
model = get_model(model_name='se_resnext50_32x4d', pretrained=None)
path = huggingface_hub.hf_hub_download(MODEL_REPO,
MODEL_FILENAME,
use_auth_token=TOKEN)
model.load_state_dict(torch.load(path))
model = model.to(device)
model.eval()
return model
def load_image(path):
image = cv2.imread(path)
h_orig, w_orig = image.shape[:2]
size = max(h_orig, w_orig)
scale = 640 / size
w, h = int(w_orig * scale), int(h_orig * scale)
image = cv2.resize(image, (w, h))
return image
def draw_label(image,
point,
label,
font=cv2.FONT_HERSHEY_SIMPLEX,
font_scale=0.8,
thickness=1):
size = cv2.getTextSize(label, font, font_scale, thickness)[0]
x, y = point
cv2.rectangle(image, (x, y - size[1]), (x + size[0], y), (255, 0, 0),
cv2.FILLED)
cv2.putText(image,
label,
point,
font,
font_scale, (255, 255, 255),
thickness,
lineType=cv2.LINE_AA)
@torch.inference_mode()
def predict(image, model, face_detector, device, margin=0.4, input_size=224):
image = cv2.imread(image.name, cv2.IMREAD_COLOR)[:, :, ::-1].copy()
image_h, image_w = image.shape[:2]
# detect faces using dlib detector
detected = face_detector(image, 1)
faces = np.empty((len(detected), input_size, input_size, 3))
if len(detected) > 0:
for i, d in enumerate(detected):
x1, y1, x2, y2, w, h = d.left(), d.top(
), d.right() + 1, d.bottom() + 1, d.width(), d.height()
xw1 = max(int(x1 - margin * w), 0)
yw1 = max(int(y1 - margin * h), 0)
xw2 = min(int(x2 + margin * w), image_w - 1)
yw2 = min(int(y2 + margin * h), image_h - 1)
faces[i] = cv2.resize(image[yw1:yw2 + 1, xw1:xw2 + 1],
(input_size, input_size))
cv2.rectangle(image, (x1, y1), (x2, y2), (255, 255, 255), 2)
cv2.rectangle(image, (xw1, yw1), (xw2, yw2), (255, 0, 0), 2)
# predict ages
inputs = torch.from_numpy(
np.transpose(faces.astype(np.float32), (0, 3, 1, 2))).to(device)
outputs = F.softmax(model(inputs), dim=-1).cpu().numpy()
ages = np.arange(0, 101)
predicted_ages = (outputs * ages).sum(axis=-1)
# draw results
for age, d in zip(predicted_ages, detected):
draw_label(image, (d.left(), d.top()), f'{int(age)}')
return image
def main():
gr.close_all()
args = parse_args()
device = torch.device(args.device)
model = load_model(device)
face_detector = dlib.get_frontal_face_detector()
func = functools.partial(predict,
model=model,
face_detector=face_detector,
device=device)
func = functools.update_wrapper(func, predict)
image_dir = pathlib.Path('sample_images')
examples = [path.as_posix() for path in sorted(image_dir.glob('*.jpg'))]
repo_url = 'https://github.com/yu4u/age-estimation-pytorch'
title = 'yu4u/age-estimation-pytorch'
description = f'A demo for {repo_url}'
article = None
gr.Interface(
func,
gr.inputs.Image(type='file', label='Input'),
gr.outputs.Image(label='Output'),
theme=args.theme,
title=title,
description=description,
article=article,
examples=examples,
allow_screenshot=args.allow_screenshot,
allow_flagging=args.allow_flagging,
live=args.live,
).launch(
enable_queue=args.enable_queue,
server_port=args.port,
share=args.share,
)
if __name__ == '__main__':
main()
|