mirror of
https://github.com/Zeyi-Lin/HivisionIDPhotos.git
synced 2026-08-28 19:45:12 +08:00
feat(new model): retinaface (#90)
* init * update retinaface code * preload * docs
This commit is contained in:
Ze-Yi LIN
@@ -52,13 +52,13 @@
|
||||
|
||||
- 在线体验： [](https://swanhub.co/ZeYiLin/HivisionIDPhotos/demo)、[](https://huggingface.co/spaces/TheEeeeLin/HivisionIDPhotos)
|
||||
|
||||
- 2024.09.10: 增加新的**人脸检测模型** Retinaface-resnet50，以稍弱于mtcnn的速度换取更高的检测精度，推荐使用
|
||||
- 2024.09.09: 增加新的**抠图模型** [BiRefNet-v1-lite](https://github.com/ZhengPeng7/BiRefNet) | Gradio增加**高级参数设置**和**水印**选项卡
|
||||
- 2024.09.08: 增加新的**抠图模型** [RMBG-1.4](https://huggingface.co/briaai/RMBG-1.4) | **ComfyUI工作流** - [HivisionIDPhotos-ComfyUI](https://github.com/AIFSH/HivisionIDPhotos-ComfyUI) 贡献 by [AIFSH](https://github.com/AIFSH/HivisionIDPhotos-ComfyUI)
|
||||
- 2024.09.07: 增加**人脸检测API选项** [Face++](docs/face++_CN.md)，实现更高精度的人脸检测
|
||||
- 2024.09.06: 增加新的抠图模型 [modnet_photographic_portrait_matting.onnx](https://github.com/ZHKKKe/MODNet)
|
||||
- 2024.09.05: 更新 [Restful API 文档](docs/api_CN.md)
|
||||
- 2024.09.02: 更新**调整照片 KB 大小**，[DockerHub](https://hub.docker.com/r/linzeyi/hivision_idphotos/tags)
|
||||
- 2023.12.01: 更新**API 部署（基于 fastapi）**
|
||||
|
||||
<br>
|
||||
|
||||
@@ -142,7 +142,8 @@ python scripts/download_model.py --models all
|
||||
|
||||
| 拓展人脸检测模型 | 介绍 | 使用文档 |
|
||||
| -- | -- | -- |
|
||||
| MTCNN | **离线**人脸检测模型，高性能CPU推理，为默认模型，检测精度较低 | Clone此项目后直接使用 |
|
||||
| MTCNN | **离线**人脸检测模型，高性能CPU推理（毫秒级），为默认模型，检测精度较低 | Clone此项目后直接使用 |
|
||||
| RetinaFace | **离线**人脸检测模型，CPU推理速度中等（秒级），精度较高| [下载](https://github.com/Zeyi-Lin/HivisionIDPhotos/releases/download/pretrained-model/retinaface-resnet50.onnx)后放到`hivision/creator/retinaface/weights`目录下 |
|
||||
| Face++ | 旷视推出的在线人脸检测API，检测精度较高，[官方文档](https://console.faceplusplus.com.cn/documents/4888373) | [使用文档](docs/face++_CN.md)|
|
||||
|
||||
## 5. GPU推理加速（可选）
|
||||
|
||||
+2
-1
@@ -50,13 +50,13 @@ English / [中文](README.md) / [日本語](README_JP.md) / [한국어](README_K
|
||||
|
||||
- Online Experience: [](https://swanhub.co/ZeYiLin/HivisionIDPhotos/demo)、[](https://huggingface.co/spaces/TheEeeeLin/HivisionIDPhotos)
|
||||
|
||||
- 2024.09.10: Added a new **face detection model** Retinaface-resnet50, which offers higher detection accuracy at a slightly slower speed compared to mtcnn. Recommended for use.
|
||||
- 2024.09.09: Added a new **Background Removal Model** [BiRefNet-v1-lite](https://github.com/ZhengPeng7/BiRefNet) | Gradio added **Advanced Parameter Settings** and **Watermark** tabs
|
||||
- 2024.09.08: Added new **Matting Model** [RMBG-1.4](https://huggingface.co/briaai/RMBG-1.4) | **ComfyUI Workflow** - [HivisionIDPhotos-ComfyUI](https://github.com/AIFSH/HivisionIDPhotos-ComfyUI) contributed by [AIFSH](https://github.com/AIFSH/HivisionIDPhotos-ComfyUI)
|
||||
- 2024.09.07: Added **Face Detection API Option** [Face++](docs/face++_EN.md), achieving higher precision in face detection
|
||||
- 2024.09.06: Added new matting model [modnet_photographic_portrait_matting.onnx](https://github.com/ZHKKKe/MODNet)
|
||||
- 2024.09.05: Updated [Restful API Documentation](docs/api_EN.md)
|
||||
- 2024.09.02: Updated **Adjust Photo KB Size**, [DockerHub](https://hub.docker.com/r/linzeyi/hivision_idphotos/tags)
|
||||
- 2023.12.01: Updated **API Deployment (based on fastapi)**
|
||||
|
||||
<br>
|
||||
|
||||
@@ -140,6 +140,7 @@ Store in the project's `hivision/creator/weights` directory:
|
||||
| Extended Face Detection Model | Description | Documentation |
|
||||
| -- | -- | -- |
|
||||
| MTCNN | **Offline** face detection model, high-performance CPU inference, default model, lower detection accuracy | Use it directly after cloning this project |
|
||||
| RetinaFace | **Offline** face detection model, moderate CPU inference speed (in seconds), and high accuracy | [Download](https://github.com/Zeyi-Lin/HivisionIDPhotos/releases/download/pretrained-model/retinaface-resnet50.onnx) and place it in the `hivision/creator/retinaface/weights` directory |
|
||||
| Face++ | Online face detection API launched by Megvii, higher detection accuracy, [official documentation](https://console.faceplusplus.com.cn/documents/4888373) | [Usage Documentation](docs/face++_EN.md)|
|
||||
|
||||
## 5. GPU Inference Acceleration (Optional)
|
||||
|
||||
@@ -16,6 +16,18 @@ HUMAN_MATTING_MODELS = [
|
||||
model for model in HUMAN_MATTING_MODELS if model in HUMAN_MATTING_MODELS_EXIST
|
||||
]
|
||||
|
||||
FACE_DETECT_MODELS = ["face++ (联网Online API)", "mtcnn"]
|
||||
FACE_DETECT_MODELS_EXPAND = (
|
||||
["retinaface-resnet50"]
|
||||
if os.path.exists(
|
||||
os.path.join(
|
||||
root_dir, "hivision/creator/retinaface/weights/retinaface-resnet50.onnx"
|
||||
)
|
||||
)
|
||||
else []
|
||||
)
|
||||
FACE_DETECT_MODELS += FACE_DETECT_MODELS_EXPAND
|
||||
|
||||
if __name__ == "__main__":
|
||||
argparser = argparse.ArgumentParser()
|
||||
argparser.add_argument(
|
||||
@@ -34,7 +46,9 @@ if __name__ == "__main__":
|
||||
|
||||
processor = IDPhotoProcessor()
|
||||
|
||||
demo = create_ui(processor, root_dir, HUMAN_MATTING_MODELS_EXIST)
|
||||
demo = create_ui(
|
||||
processor, root_dir, HUMAN_MATTING_MODELS_EXIST, FACE_DETECT_MODELS
|
||||
)
|
||||
demo.launch(
|
||||
server_name=args.host,
|
||||
server_port=args.port,
|
||||
|
||||
+4
-2
@@ -11,7 +11,9 @@ def load_description(fp):
|
||||
return content
|
||||
|
||||
|
||||
def create_ui(processor, root_dir, human_matting_models: list):
|
||||
def create_ui(
|
||||
processor, root_dir, human_matting_models: list, face_detect_models: list
|
||||
):
|
||||
DEFAULT_LANG = "zh"
|
||||
DEFAULT_HUMAN_MATTING_MODEL = "modnet_photographic_portrait_matting"
|
||||
DEFAULT_FACE_DETECT_MODEL = "mtcnn"
|
||||
@@ -61,7 +63,7 @@ def create_ui(processor, root_dir, human_matting_models: list):
|
||||
)
|
||||
|
||||
face_detect_model_options = gr.Dropdown(
|
||||
choices=FACE_DETECT_MODELS,
|
||||
choices=face_detect_models,
|
||||
label=LOCALES["face_model"][DEFAULT_LANG]["label"],
|
||||
value=DEFAULT_FACE_DETECT_MODEL,
|
||||
)
|
||||
|
||||
@@ -9,7 +9,7 @@ HUMAN_MATTING_MODELS = [
|
||||
"rmbg-1.4",
|
||||
]
|
||||
|
||||
FACE_DETECT_MODELS = ["face++ (联网Online API)", "mtcnn"]
|
||||
FACE_DETECT_MODELS = ["face++ (联网Online API)", "mtcnn", "retinaface-resnet50"]
|
||||
|
||||
|
||||
def choose_handler(creator, matting_model_option=None, face_detect_option=None):
|
||||
@@ -29,5 +29,7 @@ def choose_handler(creator, matting_model_option=None, face_detect_option=None):
|
||||
or face_detect_option == "face++ (联网Online API)"
|
||||
):
|
||||
creator.detection_handler = detect_face_face_plusplus
|
||||
elif face_detect_option == "retinaface-resnet50":
|
||||
creator.detection_handler = detect_face_retinaface
|
||||
else:
|
||||
creator.detection_handler = detect_face_mtcnn
|
||||
|
||||
@@ -16,12 +16,15 @@ except ImportError:
|
||||
from .context import Context
|
||||
from hivision.error import FaceError, APIError
|
||||
from hivision.utils import resize_image_to_kb_base64
|
||||
from hivision.creator.retinaface import retinaface_detect_faces
|
||||
import requests
|
||||
import cv2
|
||||
import os
|
||||
|
||||
|
||||
mtcnn = None
|
||||
base_dir = os.path.dirname(os.path.abspath(__file__))
|
||||
RETINAFCE_SESS = None
|
||||
|
||||
|
||||
def detect_face_mtcnn(ctx: Context, scale: int = 2):
|
||||
@@ -129,3 +132,45 @@ def detect_face_face_plusplus(ctx: Context):
|
||||
f"Face++ Status code {status_code} Request entity too large: The image exceeds the 2MB limit.",
|
||||
status_code,
|
||||
)
|
||||
|
||||
|
||||
def detect_face_retinaface(ctx: Context):
|
||||
"""
|
||||
基于RetinaFace模型的人脸检测处理器，只进行人脸数量的检测
|
||||
:param ctx: 上下文，此时已获取到原始图和抠图结果，但是我们只需要原始图
|
||||
:raise FaceError: 人脸检测错误，多个人脸或者没有人脸
|
||||
"""
|
||||
from time import time
|
||||
|
||||
global RETINAFCE_SESS
|
||||
|
||||
if RETINAFCE_SESS is None:
|
||||
print("首次加载RetinaFace模型...")
|
||||
# 计算用时
|
||||
tic = time()
|
||||
faces_dets, sess = retinaface_detect_faces(
|
||||
ctx.origin_image,
|
||||
os.path.join(base_dir, "retinaface/weights/retinaface-resnet50.onnx"),
|
||||
sess=None,
|
||||
)
|
||||
RETINAFCE_SESS = sess
|
||||
print("首次RetinaFace模型推理用时: {:.4f}s".format(time() - tic))
|
||||
else:
|
||||
tic = time()
|
||||
faces_dets, _ = retinaface_detect_faces(
|
||||
ctx.origin_image,
|
||||
os.path.join(base_dir, "retinaface/weights/retinaface-resnet50.onnx"),
|
||||
sess=RETINAFCE_SESS,
|
||||
)
|
||||
print("二次RetinaFace模型推理用时: {:.4f}s".format(time() - tic))
|
||||
|
||||
faces_num = len(faces_dets)
|
||||
if faces_num != 1:
|
||||
raise FaceError("Expected 1 face, but got {}".format(faces_num), faces_num)
|
||||
face_det = faces_dets[0]
|
||||
ctx.face = (
|
||||
face_det[0],
|
||||
face_det[1],
|
||||
face_det[2] - face_det[0] + 1,
|
||||
face_det[3] - face_det[1] + 1,
|
||||
)
|
||||
|
||||
@@ -0,0 +1 @@
|
||||
from .inference import retinaface_detect_faces
|
||||
@@ -0,0 +1,57 @@
|
||||
import numpy as np
|
||||
|
||||
|
||||
def decode(loc, priors, variances):
|
||||
"""Decode locations from predictions using priors to undo
|
||||
the encoding we did for offset regression at train time.
|
||||
Args:
|
||||
loc (tensor): location predictions for loc layers,
|
||||
Shape: [num_priors,4]
|
||||
priors (tensor): Prior boxes in center-offset form.
|
||||
Shape: [num_priors,4].
|
||||
variances: (list[float]) Variances of priorboxes
|
||||
Return:
|
||||
decoded bounding box predictions
|
||||
"""
|
||||
|
||||
boxes = None
|
||||
|
||||
boxes = np.concatenate(
|
||||
(
|
||||
priors[:, :2] + loc[:, :2] * variances[0] * priors[:, 2:],
|
||||
priors[:, 2:] * np.exp(loc[:, 2:] * variances[1]),
|
||||
),
|
||||
axis=1,
|
||||
)
|
||||
|
||||
boxes[:, :2] -= boxes[:, 2:] / 2
|
||||
boxes[:, 2:] += boxes[:, :2]
|
||||
return boxes
|
||||
|
||||
|
||||
def decode_landm(pre, priors, variances):
|
||||
"""Decode landm from predictions using priors to undo
|
||||
the encoding we did for offset regression at train time.
|
||||
Args:
|
||||
pre (tensor): landm predictions for loc layers,
|
||||
Shape: [num_priors,10]
|
||||
priors (tensor): Prior boxes in center-offset form.
|
||||
Shape: [num_priors,4].
|
||||
variances: (list[float]) Variances of priorboxes
|
||||
Return:
|
||||
decoded landm predictions
|
||||
"""
|
||||
landms = None
|
||||
|
||||
landms = np.concatenate(
|
||||
(
|
||||
priors[:, :2] + pre[:, :2] * variances[0] * priors[:, 2:],
|
||||
priors[:, :2] + pre[:, 2:4] * variances[0] * priors[:, 2:],
|
||||
priors[:, :2] + pre[:, 4:6] * variances[0] * priors[:, 2:],
|
||||
priors[:, :2] + pre[:, 6:8] * variances[0] * priors[:, 2:],
|
||||
priors[:, :2] + pre[:, 8:10] * variances[0] * priors[:, 2:],
|
||||
),
|
||||
axis=1,
|
||||
)
|
||||
|
||||
return landms
|
||||
@@ -0,0 +1,190 @@
|
||||
import numpy as np
|
||||
import cv2
|
||||
import onnxruntime as ort
|
||||
from hivision.creator.retinaface.box_utils import decode, decode_landm
|
||||
from hivision.creator.retinaface.prior_box import PriorBox
|
||||
import argparse
|
||||
|
||||
|
||||
def py_cpu_nms(dets, thresh):
|
||||
"""Pure Python NMS baseline."""
|
||||
x1 = dets[:, 0]
|
||||
y1 = dets[:, 1]
|
||||
x2 = dets[:, 2]
|
||||
y2 = dets[:, 3]
|
||||
scores = dets[:, 4]
|
||||
|
||||
areas = (x2 - x1 + 1) * (y2 - y1 + 1)
|
||||
order = scores.argsort()[::-1]
|
||||
|
||||
keep = []
|
||||
while order.size > 0:
|
||||
i = order[0]
|
||||
keep.append(i)
|
||||
xx1 = np.maximum(x1[i], x1[order[1:]])
|
||||
yy1 = np.maximum(y1[i], y1[order[1:]])
|
||||
xx2 = np.minimum(x2[i], x2[order[1:]])
|
||||
yy2 = np.minimum(y2[i], y2[order[1:]])
|
||||
|
||||
w = np.maximum(0.0, xx2 - xx1 + 1)
|
||||
h = np.maximum(0.0, yy2 - yy1 + 1)
|
||||
inter = w * h
|
||||
ovr = inter / (areas[i] + areas[order[1:]] - inter)
|
||||
|
||||
inds = np.where(ovr <= thresh)[0]
|
||||
order = order[inds + 1]
|
||||
|
||||
return keep
|
||||
|
||||
|
||||
parser = argparse.ArgumentParser(description="Retinaface")
|
||||
|
||||
parser.add_argument(
|
||||
"--network", default="resnet50", help="Backbone network mobile0.25 or resnet50"
|
||||
)
|
||||
parser.add_argument(
|
||||
"--cpu", action="store_true", default=False, help="Use cpu inference"
|
||||
)
|
||||
parser.add_argument(
|
||||
"--confidence_threshold", default=0.8, type=float, help="confidence_threshold"
|
||||
)
|
||||
parser.add_argument("--top_k", default=5000, type=int, help="top_k")
|
||||
parser.add_argument("--nms_threshold", default=0.2, type=float, help="nms_threshold")
|
||||
parser.add_argument("--keep_top_k", default=750, type=int, help="keep_top_k")
|
||||
parser.add_argument(
|
||||
"-s",
|
||||
"--save_image",
|
||||
action="store_true",
|
||||
default=True,
|
||||
help="show detection results",
|
||||
)
|
||||
parser.add_argument(
|
||||
"--vis_thres", default=0.6, type=float, help="visualization_threshold"
|
||||
)
|
||||
args = parser.parse_args()
|
||||
|
||||
|
||||
def load_model_ort(model_path):
|
||||
ort_session = ort.InferenceSession(model_path)
|
||||
return ort_session
|
||||
|
||||
|
||||
def retinaface_detect_faces(image, model_path: str, sess=None):
|
||||
cfg = {
|
||||
"name": "Resnet50",
|
||||
"min_sizes": [[16, 32], [64, 128], [256, 512]],
|
||||
"steps": [8, 16, 32],
|
||||
"variance": [0.1, 0.2],
|
||||
"clip": False,
|
||||
"loc_weight": 2.0,
|
||||
"gpu_train": True,
|
||||
"batch_size": 24,
|
||||
"ngpu": 4,
|
||||
"epoch": 100,
|
||||
"decay1": 70,
|
||||
"decay2": 90,
|
||||
"image_size": 840,
|
||||
"pretrain": True,
|
||||
"return_layers": {"layer2": 1, "layer3": 2, "layer4": 3},
|
||||
"in_channel": 256,
|
||||
"out_channel": 256,
|
||||
}
|
||||
|
||||
# Load ONNX model
|
||||
if sess is None:
|
||||
retinaface = load_model_ort(model_path)
|
||||
else:
|
||||
retinaface = sess
|
||||
|
||||
resize = 1
|
||||
|
||||
# Read and preprocess the image
|
||||
img_rgb = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)
|
||||
img = np.float32(img_rgb)
|
||||
|
||||
im_height, im_width, _ = img.shape
|
||||
scale = np.array([img.shape[1], img.shape[0], img.shape[1], img.shape[0]])
|
||||
img -= (104, 117, 123)
|
||||
img = img.transpose(2, 0, 1)
|
||||
img = np.expand_dims(img, axis=0)
|
||||
|
||||
# Run the model
|
||||
inputs = {"input": img}
|
||||
loc, conf, landms = retinaface.run(None, inputs)
|
||||
|
||||
# tic = time.time()
|
||||
priorbox = PriorBox(cfg, image_size=(im_height, im_width))
|
||||
priors = priorbox.forward()
|
||||
|
||||
prior_data = priors
|
||||
|
||||
boxes = decode(np.squeeze(loc, axis=0), prior_data, cfg["variance"])
|
||||
boxes = boxes * scale / resize
|
||||
scores = np.squeeze(conf, axis=0)[:, 1]
|
||||
|
||||
landms = decode_landm(np.squeeze(landms.data, axis=0), prior_data, cfg["variance"])
|
||||
|
||||
scale1 = np.array(
|
||||
[
|
||||
img.shape[3],
|
||||
img.shape[2],
|
||||
img.shape[3],
|
||||
img.shape[2],
|
||||
img.shape[3],
|
||||
img.shape[2],
|
||||
img.shape[3],
|
||||
img.shape[2],
|
||||
img.shape[3],
|
||||
img.shape[2],
|
||||
]
|
||||
)
|
||||
landms = landms * scale1 / resize
|
||||
|
||||
# ignore low scores
|
||||
inds = np.where(scores > args.confidence_threshold)[0]
|
||||
boxes = boxes[inds]
|
||||
landms = landms[inds]
|
||||
scores = scores[inds]
|
||||
|
||||
# keep top-K before NMS
|
||||
order = scores.argsort()[::-1][: args.top_k]
|
||||
boxes = boxes[order]
|
||||
landms = landms[order]
|
||||
scores = scores[order]
|
||||
|
||||
# do NMS
|
||||
dets = np.hstack((boxes, scores[:, np.newaxis])).astype(np.float32, copy=False)
|
||||
keep = py_cpu_nms(dets, args.nms_threshold)
|
||||
# keep = nms(dets, args.nms_threshold,force_cpu=args.cpu)
|
||||
dets = dets[keep, :]
|
||||
landms = landms[keep]
|
||||
|
||||
# keep top-K faster NMS
|
||||
dets = dets[: args.keep_top_k, :]
|
||||
landms = landms[: args.keep_top_k, :]
|
||||
|
||||
dets = np.concatenate((dets, landms), axis=1)
|
||||
# print("post processing time: {:.4f}s".format(time.time() - tic))
|
||||
|
||||
return dets, retinaface
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
import gradio as gr
|
||||
|
||||
# Create Gradio interface
|
||||
iface = gr.Interface(
|
||||
fn=retinaface_detect_faces,
|
||||
inputs=[
|
||||
gr.Image(
|
||||
type="numpy", label="上传图片", height=400
|
||||
), # Set the height to 400
|
||||
gr.Textbox(value="./FaceDetector.onnx", label="ONNX模型路径"),
|
||||
],
|
||||
outputs=gr.Number(label="检测到的人脸数量"),
|
||||
title="人脸检测",
|
||||
description="上传图片并提供ONNX模型路径以检测人脸数量。",
|
||||
)
|
||||
|
||||
# Launch the Gradio app
|
||||
iface.launch()
|
||||
@@ -0,0 +1,41 @@
|
||||
from itertools import product as product
|
||||
import numpy as np
|
||||
from math import ceil
|
||||
|
||||
|
||||
class PriorBox(object):
|
||||
def __init__(self, cfg, image_size=None):
|
||||
super(PriorBox, self).__init__()
|
||||
self.min_sizes = cfg["min_sizes"]
|
||||
self.steps = cfg["steps"]
|
||||
self.clip = cfg["clip"]
|
||||
self.image_size = image_size
|
||||
self.feature_maps = [
|
||||
[ceil(self.image_size[0] / step), ceil(self.image_size[1] / step)]
|
||||
for step in self.steps
|
||||
]
|
||||
self.name = "s"
|
||||
|
||||
def forward(self):
|
||||
anchors = []
|
||||
for k, f in enumerate(self.feature_maps):
|
||||
min_sizes = self.min_sizes[k]
|
||||
for i, j in product(range(f[0]), range(f[1])):
|
||||
for min_size in min_sizes:
|
||||
s_kx = min_size / self.image_size[1]
|
||||
s_ky = min_size / self.image_size[0]
|
||||
dense_cx = [
|
||||
x * self.steps[k] / self.image_size[1] for x in [j + 0.5]
|
||||
]
|
||||
dense_cy = [
|
||||
y * self.steps[k] / self.image_size[0] for y in [i + 0.5]
|
||||
]
|
||||
for cy, cx in product(dense_cy, dense_cx):
|
||||
anchors += [cx, cy, s_kx, s_ky]
|
||||
|
||||
output = np.array(anchors).reshape(-1, 4)
|
||||
|
||||
if self.clip:
|
||||
output = np.clip(output, 0, 1)
|
||||
|
||||
return output
|
||||
@@ -32,14 +32,14 @@ def download_file(url, save_path):
|
||||
|
||||
|
||||
def download_models(model_urls):
|
||||
# 指定下载保存的目录
|
||||
save_dir = "hivision/creator/weights"
|
||||
|
||||
# 创建目录（如果不存在的话）
|
||||
os.makedirs(os.path.join(base_path, save_dir), exist_ok=True)
|
||||
|
||||
# 下载每个模型
|
||||
for model_name, model_info in model_urls.items():
|
||||
# 指定下载保存的目录
|
||||
save_dir = model_info["location"]
|
||||
|
||||
# 创建目录（如果不存在的话）
|
||||
os.makedirs(os.path.join(base_path, save_dir), exist_ok=True)
|
||||
|
||||
url = model_info["url"]
|
||||
file_format = model_info["format"]
|
||||
|
||||
@@ -63,10 +63,12 @@ def main(models_to_download):
|
||||
"hivision_modnet": {
|
||||
"url": "https://github.com/Zeyi-Lin/HivisionIDPhotos/releases/download/pretrained-model/hivision_modnet.onnx",
|
||||
"format": "onnx",
|
||||
"location": "hivision/creator/weights",
|
||||
},
|
||||
"modnet_photographic_portrait_matting": {
|
||||
"url": "https://github.com/Zeyi-Lin/HivisionIDPhotos/releases/download/pretrained-model/modnet_photographic_portrait_matting.onnx",
|
||||
"format": "onnx",
|
||||
"location": "hivision/creator/weights",
|
||||
},
|
||||
# "mnn_hivision_modnet": {
|
||||
# "url": "https://github.com/Zeyi-Lin/HivisionIDPhotos/releases/download/pretrained-model/mnn_hivision_modnet.mnn",
|
||||
@@ -75,10 +77,17 @@ def main(models_to_download):
|
||||
"rmbg-1.4": {
|
||||
"url": "https://huggingface.co/briaai/RMBG-1.4/resolve/main/onnx/model.onnx?download=true",
|
||||
"format": "onnx",
|
||||
"location": "hivision/creator/weights",
|
||||
},
|
||||
"birefnet-v1-lite": {
|
||||
"url": "https://github.com/ZhengPeng7/BiRefNet/releases/download/v1/BiRefNet-general-bb_swin_v1_tiny-epoch_232.onnx",
|
||||
"format": "onnx",
|
||||
"location": "hivision/creator/weights",
|
||||
},
|
||||
"retinaface-resnet50": {
|
||||
"url": "https://github.com/Zeyi-Lin/HivisionIDPhotos/releases/download/pretrained-model/retinaface-resnet50.onnx",
|
||||
"format": "onnx",
|
||||
"location": "hivision/creator/retinaface/weights",
|
||||
},
|
||||
}
|
||||
|
||||
|
||||
Reference in New Issue
Block a user