|
import gradio as gr |
|
import os |
|
|
|
import argparse |
|
import time |
|
from pathlib import Path |
|
|
|
import cv2 |
|
import torch |
|
import torch.backends.cudnn as cudnn |
|
from numpy import random |
|
|
|
from models.experimental import attempt_load |
|
from utils.datasets import LoadStreams, LoadImages |
|
from utils.general import check_img_size, check_requirements, check_imshow, non_max_suppression, apply_classifier, \ |
|
scale_coords, xyxy2xywh, strip_optimizer, set_logging, increment_path |
|
from utils.plots import plot_one_box |
|
from utils.torch_utils import select_device, load_classifier, time_synchronized, TracedModel |
|
from PIL import Image |
|
|
|
from sort import * |
|
|
|
from huggingface_hub import hf_hub_download |
|
|
|
def load_model(model_name): |
|
model_path = hf_hub_download(repo_id=f"Yolov7/{model_name}", filename=f"{model_name}.pt") |
|
|
|
return model_path |
|
|
|
|
|
model_names = [ |
|
"yolov7", |
|
"yolov7-e6e", |
|
"yolov7-e6", |
|
] |
|
|
|
models = {model_name: load_model(model_name) for model_name in model_names} |
|
|
|
|
|
"""Function to Draw Bounding boxes""" |
|
def draw_boxes(img, bbox, identities=None, categories=None, confidences = None, names=None, colors = None): |
|
for i, box in enumerate(bbox): |
|
x1, y1, x2, y2 = [int(i) for i in box] |
|
tl = opt.thickness or round(0.002 * (img.shape[0] + img.shape[1]) / 2) + 1 |
|
|
|
cat = int(categories[i]) if categories is not None else 0 |
|
id = int(identities[i]) if identities is not None else 0 |
|
|
|
|
|
color = colors[cat] |
|
|
|
if not opt.nobbox: |
|
cv2.rectangle(img, (x1, y1), (x2, y2), color, tl) |
|
|
|
if not opt.nolabel: |
|
label = str(id) + ":"+ names[cat] if identities is not None else f'{names[cat]} {confidences[i]:.2f}' |
|
tf = max(tl - 1, 1) |
|
t_size = cv2.getTextSize(label, 0, fontScale=tl / 3, thickness=tf)[0] |
|
c2 = x1 + t_size[0], y1 - t_size[1] - 3 |
|
cv2.rectangle(img, (x1, y1), c2, color, -1, cv2.LINE_AA) |
|
cv2.putText(img, label, (x1, y1 - 2), 0, tl / 3, [225, 255, 255], thickness=tf, lineType=cv2.LINE_AA) |
|
|
|
|
|
return img |
|
|
|
|
|
|
|
def detect(img, model): |
|
parser = argparse.ArgumentParser() |
|
parser.add_argument('--weights', nargs='+', type=str, default='yolov7.pt', help='model.pt path(s)') |
|
parser.add_argument('--source', type=str, default='inference/images', help='source') |
|
parser.add_argument('--img-size', type=int, default=640, help='inference size (pixels)') |
|
parser.add_argument('--conf-thres', type=float, default=0.25, help='object confidence threshold') |
|
parser.add_argument('--iou-thres', type=float, default=0.45, help='IOU threshold for NMS') |
|
parser.add_argument('--device', default='', help='cuda device, i.e. 0 or 0,1,2,3 or cpu') |
|
parser.add_argument('--view-img', action='store_true', help='display results') |
|
parser.add_argument('--save-txt', action='store_true', help='save results to *.txt') |
|
parser.add_argument('--save-conf', action='store_true', help='save confidences in --save-txt labels') |
|
parser.add_argument('--nosave', action='store_true', help='do not save images/videos') |
|
parser.add_argument('--classes', nargs='+', type=int, help='filter by class: --class 0, or --class 0 2 3') |
|
parser.add_argument('--agnostic-nms', action='store_true', help='class-agnostic NMS') |
|
parser.add_argument('--augment', action='store_true', help='augmented inference') |
|
parser.add_argument('--update', action='store_true', help='update all models') |
|
parser.add_argument('--project', default='runs/detect', help='save results to project/name') |
|
parser.add_argument('--name', default='exp', help='save results to project/name') |
|
parser.add_argument('--exist-ok', action='store_true', help='existing project/name ok, do not increment') |
|
parser.add_argument('--no-trace', action='store_true', help='don`t trace model') |
|
|
|
parser.add_argument('--track', action='store_true', help='run tracking') |
|
parser.add_argument('--show-track', action='store_true', help='show tracked path') |
|
parser.add_argument('--show-fps', action='store_true', help='show fps') |
|
parser.add_argument('--thickness', type=int, default=2, help='bounding box and font size thickness') |
|
parser.add_argument('--seed', type=int, default=1, help='random seed to control bbox colors') |
|
parser.add_argument('--nobbox', action='store_true', help='don`t show bounding box') |
|
parser.add_argument('--nolabel', action='store_true', help='don`t show label') |
|
parser.add_argument('--unique-track-color', action='store_true', help='show each track in unique color') |
|
|
|
np.random.seed(opt.seed) |
|
|
|
sort_tracker = Sort(max_age=5, |
|
min_hits=2, |
|
iou_threshold=0.2) |
|
|
|
source, weights, view_img, save_txt, imgsz, trace = opt.source, opt.weights, opt.view_img, opt.save_txt, opt.img_size, not opt.no_trace |
|
save_img = not opt.nosave and not source.endswith('.txt') |
|
webcam = source.isnumeric() or source.endswith('.txt') or source.lower().startswith( |
|
('rtsp://', 'rtmp://', 'http://', 'https://')) |
|
save_dir = Path(increment_path(Path(opt.project) / opt.name, exist_ok=opt.exist_ok)) |
|
if not opt.nosave: |
|
(save_dir / 'labels' if save_txt else save_dir).mkdir(parents=True, exist_ok=True) |
|
|
|
|
|
set_logging() |
|
device = select_device(opt.device) |
|
half = device.type != 'cpu' |
|
|
|
|
|
model = attempt_load(weights, map_location=device) |
|
stride = int(model.stride.max()) |
|
imgsz = check_img_size(imgsz, s=stride) |
|
|
|
if trace: |
|
model = TracedModel(model, device, opt.img_size) |
|
|
|
if half: |
|
model.half() |
|
|
|
|
|
classify = False |
|
if classify: |
|
modelc = load_classifier(name='resnet101', n=2) |
|
modelc.load_state_dict(torch.load('weights/resnet101.pt', map_location=device)['model']).to(device).eval() |
|
|
|
|
|
vid_path, vid_writer = None, None |
|
if webcam: |
|
view_img = check_imshow() |
|
cudnn.benchmark = True |
|
dataset = LoadStreams(source, img_size=imgsz, stride=stride) |
|
else: |
|
dataset = LoadImages(source, img_size=imgsz, stride=stride) |
|
|
|
|
|
names = model.module.names if hasattr(model, 'module') else model.names |
|
colors = [[random.randint(0, 255) for _ in range(3)] for _ in names] |
|
|
|
|
|
if device.type != 'cpu': |
|
model(torch.zeros(1, 3, imgsz, imgsz).to(device).type_as(next(model.parameters()))) |
|
old_img_w = old_img_h = imgsz |
|
old_img_b = 1 |
|
|
|
t0 = time.time() |
|
|
|
startTime = 0 |
|
|
|
for path, img, im0s, vid_cap in dataset: |
|
img = torch.from_numpy(img).to(device) |
|
img = img.half() if half else img.float() |
|
img /= 255.0 |
|
if img.ndimension() == 3: |
|
img = img.unsqueeze(0) |
|
|
|
|
|
if device.type != 'cpu' and (old_img_b != img.shape[0] or old_img_h != img.shape[2] or old_img_w != img.shape[3]): |
|
old_img_b = img.shape[0] |
|
old_img_h = img.shape[2] |
|
old_img_w = img.shape[3] |
|
for i in range(3): |
|
model(img, augment=opt.augment)[0] |
|
|
|
|
|
t1 = time_synchronized() |
|
pred = model(img, augment=opt.augment)[0] |
|
t2 = time_synchronized() |
|
|
|
|
|
pred = non_max_suppression(pred, opt.conf_thres, opt.iou_thres, classes=opt.classes, agnostic=opt.agnostic_nms) |
|
t3 = time_synchronized() |
|
|
|
|
|
if classify: |
|
pred = apply_classifier(pred, modelc, img, im0s) |
|
|
|
|
|
for i, det in enumerate(pred): |
|
if webcam: |
|
p, s, im0, frame = path[i], '%g: ' % i, im0s[i].copy(), dataset.count |
|
else: |
|
p, s, im0, frame = path, '', im0s, getattr(dataset, 'frame', 0) |
|
|
|
p = Path(p) |
|
save_path = str(save_dir / p.name) |
|
txt_path = str(save_dir / 'labels' / p.stem) + ('' if dataset.mode == 'image' else f'_{frame}') |
|
gn = torch.tensor(im0.shape)[[1, 0, 1, 0]] |
|
if len(det): |
|
|
|
det[:, :4] = scale_coords(img.shape[2:], det[:, :4], im0.shape).round() |
|
|
|
|
|
for c in det[:, -1].unique(): |
|
n = (det[:, -1] == c).sum() |
|
s += f"{n} {names[int(c)]}{'s' * (n > 1)}, " |
|
|
|
dets_to_sort = np.empty((0,6)) |
|
|
|
for x1,y1,x2,y2,conf,detclass in det.cpu().detach().numpy(): |
|
dets_to_sort = np.vstack((dets_to_sort, |
|
np.array([x1, y1, x2, y2, conf, detclass]))) |
|
|
|
|
|
if opt.track: |
|
|
|
tracked_dets = sort_tracker.update(dets_to_sort, opt.unique_track_color) |
|
tracks =sort_tracker.getTrackers() |
|
|
|
|
|
if len(tracked_dets)>0: |
|
bbox_xyxy = tracked_dets[:,:4] |
|
identities = tracked_dets[:, 8] |
|
categories = tracked_dets[:, 4] |
|
confidences = None |
|
|
|
if opt.show_track: |
|
|
|
for t, track in enumerate(tracks): |
|
|
|
track_color = colors[int(track.detclass)] if not opt.unique_track_color else sort_tracker.color_list[t] |
|
|
|
[cv2.line(im0, (int(track.centroidarr[i][0]), |
|
int(track.centroidarr[i][1])), |
|
(int(track.centroidarr[i+1][0]), |
|
int(track.centroidarr[i+1][1])), |
|
track_color, thickness=opt.thickness) |
|
for i,_ in enumerate(track.centroidarr) |
|
if i < len(track.centroidarr)-1 ] |
|
else: |
|
bbox_xyxy = dets_to_sort[:,:4] |
|
identities = None |
|
categories = dets_to_sort[:, 5] |
|
confidences = dets_to_sort[:, 4] |
|
|
|
im0 = draw_boxes(im0, bbox_xyxy, identities, categories, confidences, names, colors) |
|
|
|
|
|
|
|
|
|
|
|
|
|
print(f'{s}Done. ({(1E3 * (t2 - t1)):.1f}ms) Inference, ({(1E3 * (t3 - t2)):.1f}ms) NMS') |
|
|
|
|
|
|
|
if dataset.mode != 'image' and opt.show_fps: |
|
currentTime = time.time() |
|
|
|
fps = 1/(currentTime - startTime) |
|
startTime = currentTime |
|
cv2.putText(im0, "FPS: " + str(int(fps)), (20, 70), cv2.FONT_HERSHEY_PLAIN, 2, (0,255,0),2) |
|
|
|
|
|
if view_img: |
|
cv2.imshow(str(p), im0) |
|
cv2.waitKey(1) |
|
|
|
|
|
if save_img: |
|
if dataset.mode == 'image': |
|
cv2.imwrite(save_path, im0) |
|
print(f" The image with the result is saved in: {save_path}") |
|
else: |
|
if vid_path != save_path: |
|
vid_path = save_path |
|
if isinstance(vid_writer, cv2.VideoWriter): |
|
vid_writer.release() |
|
if vid_cap: |
|
fps = vid_cap.get(cv2.CAP_PROP_FPS) |
|
w = int(vid_cap.get(cv2.CAP_PROP_FRAME_WIDTH)) |
|
h = int(vid_cap.get(cv2.CAP_PROP_FRAME_HEIGHT)) |
|
else: |
|
fps, w, h = 30, im0.shape[1], im0.shape[0] |
|
save_path += '.mp4' |
|
vid_writer = cv2.VideoWriter(save_path, cv2.VideoWriter_fourcc(*'mp4v'), fps, (w, h)) |
|
vid_writer.write(im0) |
|
|
|
if save_txt or save_img: |
|
s = f"\n{len(list(save_dir.glob('labels/*.txt')))} labels saved to {save_dir / 'labels'}" if save_txt else '' |
|
|
|
|
|
print(f'Done. ({time.time() - t0:.3f}s)') |
|
|
|
|
|
|