Spaces:
Runtime error
Runtime error
File size: 21,836 Bytes
ad2ecf0 6451b1b ad2ecf0 fe9546f ad2ecf0 fe9546f ad2ecf0 fe9546f ad2ecf0 fe9546f ad2ecf0 fe9546f ad2ecf0 fe9546f ad2ecf0 fe9546f ad2ecf0 fe9546f ad2ecf0 24dd5fd ad2ecf0 fe9546f ad2ecf0 24dd5fd ad2ecf0 fe9546f ad2ecf0 fe9546f ad2ecf0 8dd584f ad2ecf0 24dd5fd ad2ecf0 24dd5fd ad2ecf0 5b2a05b ad2ecf0 0938b66 ad2ecf0 5b2a05b ad2ecf0 |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 |
# Gradio YOLOv5 Det v0.4
# author: Zeng Yifu(曾逸夫)
# creation time: 2022-05-28
# email: zyfiy1314@163.com
# project homepage: https://gitee.com/CV_Lab/gradio_yolov5_det
import argparse
import csv
import gc
import json
import os
import sys
from collections import Counter
from pathlib import Path
import cv2
import gradio as gr
import numpy as np
import pandas as pd
import torch
import yaml
from PIL import Image, ImageDraw, ImageFont
from util.fonts_opt import is_fonts
from util.pdf_opt import pdf_generate
ROOT_PATH = sys.path[0] # root directory
# model path
model_path = "ultralytics/yolov5"
# Gradio YOLOv5 Det version
GYD_VERSION = "Gradio YOLOv5 Det v0.4"
# model name temporary variable
model_name_tmp = ""
# Device temporary variables
device_tmp = ""
# File extension
suffix_list = [".csv", ".yaml"]
# font size
FONTSIZE = 25
# object style
obj_style = ["Small Object", "Medium Object", "Large Object"]
def parse_args(known=False):
parser = argparse.ArgumentParser(description="Gradio YOLOv5 Det v0.4")
parser.add_argument("--source", "-src", default="upload", type=str, help="input source")
parser.add_argument("--source_video", "-src_v", default="webcam", type=str, help="video input source")
parser.add_argument("--img_tool", "-it", default="editor", type=str, help="input image tool")
parser.add_argument("--model_name", "-mn", default="yolov5s", type=str, help="model name")
parser.add_argument(
"--model_cfg",
"-mc",
default="./model_config/model_name_p5_p6_all.yaml",
type=str,
help="model config",
)
parser.add_argument(
"--cls_name",
"-cls",
default="./cls_name/cls_name_en.yaml",
type=str,
help="cls name",
)
parser.add_argument(
"--nms_conf",
"-conf",
default=0.5,
type=float,
help="model NMS confidence threshold",
)
parser.add_argument("--nms_iou", "-iou", default=0.45, type=float, help="model NMS IoU threshold")
parser.add_argument(
"--device",
"-dev",
default="cpu",
type=str,
help="cuda or cpu",
)
parser.add_argument("--inference_size", "-isz", default=640, type=int, help="model inference size")
parser.add_argument("--max_detnum", "-mdn", default=50, type=float, help="model max det num")
parser.add_argument("--slider_step", "-ss", default=0.05, type=float, help="slider step")
parser.add_argument(
"--is_login",
"-isl",
action="store_true",
default=False,
help="is login",
)
parser.add_argument('--usr_pwd',
"-up",
nargs='+',
type=str,
default=["admin", "admin"],
help="user & password for login")
parser.add_argument(
"--is_share",
"-is",
action="store_true",
default=False,
help="is login",
)
args = parser.parse_known_args()[0] if known else parser.parse_args()
return args
# yaml file parsing
def yaml_parse(file_path):
return yaml.safe_load(open(file_path, encoding="utf-8").read())
# yaml csv file parsing
def yaml_csv(file_path, file_tag):
file_suffix = Path(file_path).suffix
if file_suffix == suffix_list[0]:
# model name
file_names = [i[0] for i in list(csv.reader(open(file_path)))] # csv version
elif file_suffix == suffix_list[1]:
# model name
file_names = yaml_parse(file_path).get(file_tag) # yaml version
else:
print(f"{file_path} is not in the correct format! Program exits!")
sys.exit()
return file_names
# model loading
def model_loading(model_name, device):
# load model
model = torch.hub.load(model_path, model_name, force_reload=True, device=device, _verbose=False)
return model
# check information
def export_json(results, img_size):
return [[{
"ID": i,
"CLASS": int(result[i][5]),
"CLASS_NAME": model_cls_name_cp[int(result[i][5])],
"BOUNDING_BOX": {
"XMIN": round(result[i][:4].tolist()[0], 6),
"YMIN": round(result[i][:4].tolist()[1], 6),
"XMAX": round(result[i][:4].tolist()[2], 6),
"YMAX": round(result[i][:4].tolist()[3], 6),},
"CONF": round(float(result[i][4]), 2),
"FPS": round(1000 / float(results.t[1]), 2),
"IMG_WIDTH": img_size[0],
"IMG_HEIGHT": img_size[1],} for i in range(len(result))] for result in results.xyxyn]
# frame conversion
def pil_draw(img, countdown_msg, textFont, xyxy, font_size, opt, obj_cls_index, color_list):
img_pil = ImageDraw.Draw(img)
img_pil.rectangle(xyxy, fill=None, outline=color_list[obj_cls_index]) # bounding box
if "label" in opt:
text_w, text_h = textFont.getsize(countdown_msg) # Label size
img_pil.rectangle(
(xyxy[0], xyxy[1], xyxy[0] + text_w, xyxy[1] + text_h),
fill=color_list[obj_cls_index],
outline=color_list[obj_cls_index],
) # label background
img_pil.multiline_text(
(xyxy[0], xyxy[1]),
countdown_msg,
fill=(255, 255, 255),
font=textFont,
align="center",
)
return img
def color_set(cls_num):
color_list = []
for i in range(cls_num):
color = tuple(np.random.choice(range(256), size=3))
# color = ["#"+''.join([random.choice('0123456789ABCDEF') for j in range(6)])]
color_list.append(color)
return color_list
# YOLOv5 image detection function
def yolo_det_img(img, device, model_name, infer_size, conf, iou, max_num, model_cls, opt):
global model, model_name_tmp, device_tmp
# object size num
s_obj, m_obj, l_obj = 0, 0, 0
# object area list
area_obj_all = []
# cls num stat
cls_det_stat = []
if model_name_tmp != model_name:
# Model judgment to avoid repeated loading
model_name_tmp = model_name
model = model_loading(model_name_tmp, device)
elif device_tmp != device:
device_tmp = device
model = model_loading(model_name_tmp, device)
# -------------Model tuning -------------
model.conf = conf # NMS confidence threshold
model.iou = iou # NMS IoU threshold
model.max_det = int(max_num) # Maximum number of detection frames
model.classes = model_cls # model classes
color_list = color_set(len(model_cls_name_cp)) # 设置颜色
img_size = img.size # frame size
results = model(img, size=infer_size) # detection
# ----------------目标裁剪----------------
crops = results.crop(save=False)
img_crops = []
for i in range(len(crops)):
img_crops.append(crops[i]["im"][..., ::-1])
# Data Frame
dataframe = results.pandas().xyxy[0].round(2)
# ----------------Load fonts----------------
yaml_index = cls_name.index(".yaml")
cls_name_lang = cls_name[yaml_index - 2:yaml_index]
if cls_name_lang == "zh":
# Chinese
textFont = ImageFont.truetype(str(f"{ROOT_PATH}/fonts/SimSun.ttf"), size=FONTSIZE)
elif cls_name_lang in ["en", "ru", "es", "ar"]:
# English, Russian, Spanish, Arabic
textFont = ImageFont.truetype(str(f"{ROOT_PATH}/fonts/TimesNewRoman.ttf"), size=FONTSIZE)
elif cls_name_lang == "ko":
# Korean
textFont = ImageFont.truetype(str(f"{ROOT_PATH}/fonts/malgun.ttf"), size=FONTSIZE)
for result in results.xyxyn:
for i in range(len(result)):
id = int(i) # instance ID
obj_cls_index = int(result[i][5]) # category index
obj_cls = model_cls_name_cp[obj_cls_index] # category
cls_det_stat.append(obj_cls)
# ------------ border coordinates ------------
x0 = float(result[i][:4].tolist()[0])
y0 = float(result[i][:4].tolist()[1])
x1 = float(result[i][:4].tolist()[2])
y1 = float(result[i][:4].tolist()[3])
# ------------ Actual coordinates of the border ------------
x0 = int(img_size[0] * x0)
y0 = int(img_size[1] * y0)
x1 = int(img_size[0] * x1)
y1 = int(img_size[1] * y1)
conf = float(result[i][4]) # confidence
# fps = f"{(1000 / float(results.t[1])):.2f}" # FPS
det_img = pil_draw(
img,
f"{id}-{obj_cls}:{conf:.2f}",
textFont,
[x0, y0, x1, y1],
FONTSIZE,
opt,
obj_cls_index,
color_list,
)
# ----------add object size----------
w_obj = x1 - x0
h_obj = y1 - y0
area_obj = w_obj * h_obj
area_obj_all.append(area_obj)
# ------------JSON generate------------
det_json = export_json(results, img.size)[0] # Detection information
det_json_format = json.dumps(det_json, sort_keys=False, indent=4, separators=(",", ":"),
ensure_ascii=False) # JSON formatting
if "json" not in opt:
det_json = None
# -------PDF generate-------
report = "./Det_Report.pdf"
if "pdf" in opt:
pdf_generate(f"{det_json_format}", report, GYD_VERSION)
else:
report = None
# --------------object size compute--------------
for i in range(len(area_obj_all)):
if (0 < area_obj_all[i] <= 32 ** 2):
s_obj = s_obj + 1
elif (32 ** 2 < area_obj_all[i] <= 96 ** 2):
m_obj = m_obj + 1
elif (area_obj_all[i] > 96 ** 2):
l_obj = l_obj + 1
sml_obj_total = s_obj + m_obj + l_obj
objSize_dict = {obj_style[i]: [s_obj, m_obj, l_obj][i] / sml_obj_total for i in range(3)}
# ------------cls stat------------
clsRatio_dict = {}
clsDet_dict = Counter(cls_det_stat)
clsDet_dict_sum = sum(clsDet_dict.values())
for k, v in clsDet_dict.items():
clsRatio_dict[k] = v / clsDet_dict_sum
return det_img, objSize_dict, clsRatio_dict, det_json, report, dataframe, img_crops
# YOLOv5 video detection function
def yolo_det_video(video, device, model_name, infer_size, conf, iou, max_num, model_cls, opt):
global model, model_name_tmp, device_tmp
os.system("""
if [ -e './output.mp4' ]; then
rm ./output.mp4
fi
""")
if model_name_tmp != model_name:
# Model judgment to avoid repeated loading
model_name_tmp = model_name
model = model_loading(model_name_tmp, device)
elif device_tmp != device:
device_tmp = device
model = model_loading(model_name_tmp, device)
# -------------Model tuning -------------
model.conf = conf # NMS confidence threshold
model.iou = iou # NMS IOU threshold
model.max_det = int(max_num) # Maximum number of detection frames
model.classes = model_cls # model classes
color_list = color_set(len(model_cls_name_cp)) # 设置颜色
# ----------------Load fonts----------------
yaml_index = cls_name.index(".yaml")
cls_name_lang = cls_name[yaml_index - 2:yaml_index]
if cls_name_lang == "zh":
# Chinese
textFont = ImageFont.truetype(str(f"{ROOT_PATH}/fonts/SimSun.ttf"), size=FONTSIZE)
elif cls_name_lang in ["en", "ru", "es", "ar"]:
# English, Russian, Spanish, Arabic
textFont = ImageFont.truetype(str(f"{ROOT_PATH}/fonts/TimesNewRoman.ttf"), size=FONTSIZE)
elif cls_name_lang == "ko":
# Korean
textFont = ImageFont.truetype(str(f"{ROOT_PATH}/fonts/malgun.ttf"), size=FONTSIZE)
# video->frame
gc.collect()
output_video_path = "./output.avi"
cap = cv2.VideoCapture(video)
fourcc = cv2.VideoWriter_fourcc(*"I420") # encoder
out = cv2.VideoWriter(output_video_path, fourcc, 30.0, (int(cap.get(3)), int(cap.get(4))))
while cap.isOpened():
ret, frame = cap.read()
# Determine empty frame
if not ret:
break
frame2 = frame.copy()
results = model(frame2, size=infer_size) # detection
h, w, _ = frame.shape # frame size
img_size = (w, h) # frame size
for result in results.xyxyn:
for i in range(len(result)):
id = int(i) # instance ID
obj_cls_index = int(result[i][5]) # category index
obj_cls = model_cls_name_cp[obj_cls_index] # category
# ------------ border coordinates ------------
x0 = float(result[i][:4].tolist()[0])
y0 = float(result[i][:4].tolist()[1])
x1 = float(result[i][:4].tolist()[2])
y1 = float(result[i][:4].tolist()[3])
# ------------ Actual coordinates of the border ------------
x0 = int(img_size[0] * x0)
y0 = int(img_size[1] * y0)
x1 = int(img_size[0] * x1)
y1 = int(img_size[1] * y1)
conf = float(result[i][4]) # confidence
# fps = f"{(1000 / float(results.t[1])):.2f}" # FPS
frame = Image.fromarray(cv2.cvtColor(frame, cv2.COLOR_BGR2RGB))
frame = pil_draw(
frame,
f"{id}-{obj_cls}:{conf:.2f}",
textFont,
[x0, y0, x1, y1],
FONTSIZE,
opt,
obj_cls_index,
color_list,
)
frame = cv2.cvtColor(np.asarray(frame), cv2.COLOR_RGB2BGR)
# frame->video
out.write(frame)
out.release()
cap.release()
# cv2.destroyAllWindows()
return output_video_path
def main(args):
gr.close_all()
global model, model_cls_name_cp, cls_name
source = args.source
source_video = args.source_video
img_tool = args.img_tool
nms_conf = args.nms_conf
nms_iou = args.nms_iou
model_name = args.model_name
model_cfg = args.model_cfg
cls_name = args.cls_name
device = args.device
inference_size = args.inference_size
max_detnum = args.max_detnum
slider_step = args.slider_step
is_login = args.is_login
usr_pwd = args.usr_pwd
is_share = args.is_share
is_fonts(f"{ROOT_PATH}/fonts") # Check font files
# model loading
model = model_loading(model_name, device)
model_names = yaml_csv(model_cfg, "model_names") # model names
model_cls_name = yaml_csv(cls_name, "model_cls_name") # class name
model_cls_name_cp = model_cls_name.copy() # class name
# ------------------- Input Components -------------------
inputs_img = gr.Image(image_mode="RGB", source=source, tool=img_tool, type="pil", label="original image")
inputs_device01 = gr.Radio(choices=["cuda:0", "cpu"], value=device, label="device")
inputs_model01 = gr.Dropdown(choices=model_names, value=model_name, type="value", label="model")
inputs_size01 = gr.Radio(choices=[320, 640, 1280], value=inference_size, label="inference size")
input_conf01 = gr.Slider(0, 1, step=slider_step, value=nms_conf, label="confidence threshold")
inputs_iou01 = gr.Slider(0, 1, step=slider_step, value=nms_iou, label="IoU threshold")
inputs_maxnum01 = gr.Number(value=max_detnum, label="Maximum number of detections")
inputs_clsName01 = gr.CheckboxGroup(choices=model_cls_name, value=model_cls_name, type="index", label="category")
inputs_opt01 = gr.CheckboxGroup(choices=["label", "pdf", "json"],
value=["label", "pdf"],
type="value",
label="operate")
# ------------------- Input Components -------------------
inputs_video = gr.Video(format="mp4", source=source_video, label="original video") # webcam
inputs_device02 = gr.Radio(choices=["cuda:0", "cpu"], value=device, label="device")
inputs_model02 = gr.Dropdown(choices=model_names, value=model_name, type="value", label="model")
inputs_size02 = gr.Radio(choices=[320, 640, 1280], value=inference_size, label="inference size")
input_conf02 = gr.Slider(0, 1, step=slider_step, value=nms_conf, label="confidence threshold")
inputs_iou02 = gr.Slider(0, 1, step=slider_step, value=nms_iou, label="IoU threshold")
inputs_maxnum02 = gr.Number(value=max_detnum, label="Maximum number of detections")
inputs_clsName02 = gr.CheckboxGroup(choices=model_cls_name, value=model_cls_name, type="index", label="category")
inputs_opt02 = gr.CheckboxGroup(choices=["label"], value=["label"], type="value", label="operate")
# Input parameters
inputs_img_list = [
inputs_img, # input image
inputs_device01, # device
inputs_model01, # model
inputs_size01, # inference size
input_conf01, # confidence threshold
inputs_iou01, # IoU threshold
inputs_maxnum01, # maximum number of detections
inputs_clsName01, # category
inputs_opt01, # detect operations
]
inputs_video_list = [
inputs_video, # input image
inputs_device02, # device
inputs_model02, # model
inputs_size02, # inference size
input_conf02, # confidence threshold
inputs_iou02, # IoU threshold
inputs_maxnum02, # maximum number of detections
inputs_clsName02, # category
inputs_opt02, # detect operation
]
# -------------------output component-------------------
outputs_img = gr.Image(type="pil", label="Detection image")
outputs_json = gr.JSON(label="Detection information")
outputs_pdf = gr.File(label="Download test report")
outputs_df = gr.Dataframe(max_rows=5,
overflow_row_behaviour="paginate",
type="pandas",
label="List of detection information")
outputs_objSize = gr.Label(label="Object size ratio statistics")
outputs_clsSize = gr.Label(label="Category detection proportion statistics")
outputs_crops = gr.Gallery(label="Object crop")
# -------------------output component-------------------
outputs_video = gr.Video(format='mp4', label="Detection video")
# output parameters
outputs_img_list = [outputs_img, outputs_objSize, outputs_clsSize, outputs_json, outputs_pdf, outputs_df, outputs_crops]
outputs_video_list = [outputs_video]
# title
title = "Gradio YOLOv5 Det v0.4"
# describe
description = "<div align='center'>Customizable target detection model, easy to install, easy to use</div>"
# article="https://gitee.com/CV_Lab/gradio_yolov5_det"
# example image
examples = [
[
"./img_example/bus.jpg",
"cpu",
"yolov5s",
640,
0.6,
0.5,
10,
["person", "bus"],
["label", "pdf"],],
[
"./img_example/giraffe.jpg",
"cpu",
"yolov5l",
320,
0.5,
0.45,
12,
["giraffe"],
["label", "pdf"],],
[
"./img_example/zidane.jpg",
"cpu",
"yolov5m",
640,
0.6,
0.5,
15,
["person", "tie"],
["pdf", "json"],],
[
"./img_example/Millenial-at-work.jpg",
"cpu",
"yolov5s6",
1280,
0.5,
0.5,
20,
["person", "chair", "cup", "laptop"],
["label", "pdf"],],]
# interface
gyd_img = gr.Interface(
fn=yolo_det_img,
inputs=inputs_img_list,
outputs=outputs_img_list,
title=title,
description=description,
# article=article,
# examples=examples,
# theme="seafoam",
# live=True, # Change output in real time
flagging_dir="run", # output directory
# allow_flagging="manual",
# flagging_options=["good", "generally", "bad"],
)
gyd_video = gr.Interface(
# fn=yolo_det_video_test,
fn=yolo_det_video,
inputs=inputs_video_list,
outputs=outputs_video_list,
title=title,
description=description,
# article=article,
examples=examples,
# theme="seafoam",
# live=True, # Change output in real time
flagging_dir="run", # output directory
allow_flagging="never",
# flagging_options=["good", "generally", "bad"],
)
gyd = gr.TabbedInterface(interface_list=[gyd_img, gyd_video], tab_names=["Image Mode", "Video Mode"])
if not is_login:
gyd.launch(
inbrowser=True, # Automatically open default browser
show_tips=True, # Automatically display the latest features of gradio
share=is_share, # Project sharing, other devices can access
favicon_path="./icon/logo.ico", # web icon
show_error=True, # Display error message in browser console
quiet=True, # Suppress most print statements
)
else:
gyd.launch(
inbrowser=True, # Automatically open default browser
show_tips=True, # Automatically display the latest features of gradio
auth=usr_pwd, # login interface
share=is_share, # Project sharing, other devices can access
favicon_path="./icon/logo.ico", # web icon
show_error=True, # Display error message in browser console
quiet=True, # Suppress most print statements
)
if __name__ == "__main__":
args = parse_args()
main(args)
|