256 lines
12 KiB
Python
256 lines
12 KiB
Python
import argparse
|
||
import time
|
||
from pathlib import Path
|
||
|
||
import cv2
|
||
import torch
|
||
import torch.backends.cudnn as cudnn
|
||
import numpy as np
|
||
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, save_one_box, xywh2xyxy
|
||
from utils.plots import colors, plot_one_box
|
||
from utils.torch_utils import select_device, load_classifier, time_synchronized
|
||
|
||
|
||
def detect(opt):
|
||
source1, source2, weights, view_img, save_txt, imgsz = opt.source1, opt.source2, opt.weights, opt.view_img, opt.save_txt, opt.img_size
|
||
|
||
save_img = opt.save_img # #not opt.nosave and not source1.endswith('.txt') # save inference images
|
||
webcam = source1.isnumeric() or source1.endswith('.txt') or source1.lower().startswith(
|
||
('rtsp://', 'rtmp://', 'http://', 'https://'))
|
||
|
||
# Directories
|
||
save_dir = increment_path(Path(opt.project) / opt.name, exist_ok=opt.exist_ok) # increment run
|
||
(save_dir / 'labels' if save_txt else save_dir).mkdir(parents=True, exist_ok=True) # make dir
|
||
|
||
# Initialize
|
||
set_logging()
|
||
device = select_device(opt.device)
|
||
half = device.type != 'cpu' # half precision only supported on CUDA
|
||
|
||
# Load model
|
||
model = attempt_load(weights, map_location=device) # load FP32 model
|
||
stride = int(model.stride.max()) # model stride
|
||
imgsz = check_img_size(imgsz, s=stride) # check img_size
|
||
names = model.module.names if hasattr(model, 'module') else model.names # get class names
|
||
if half:
|
||
model.half() # to FP16
|
||
|
||
# Second-stage classifier
|
||
classify = False
|
||
if classify:
|
||
modelc = load_classifier(name='resnet101', n=2) # initialize
|
||
modelc.load_state_dict(torch.load('weights/resnet101.pt', map_location=device)['model']).to(device).eval()
|
||
|
||
# Set Dataloader
|
||
vid_path, vid_writer = None, None
|
||
if webcam:
|
||
view_img = check_imshow()
|
||
cudnn.benchmark = True # set True to speed up constant image size inference
|
||
dataset = LoadStreams(source1, img_size=imgsz, stride=stride)
|
||
else:
|
||
dataset = LoadImages(source1, img_size=imgsz, stride=stride)
|
||
dataset2 = LoadImages(source2, img_size=imgsz, stride=stride)
|
||
|
||
# # Run inference
|
||
# if device.type != 'cpu':
|
||
# model(torch.zeros(1, 3, imgsz, imgsz).to(device).type_as(next(model.parameters()))) # run once
|
||
|
||
t0 = time.time()
|
||
img_num = 0
|
||
fps_sum = 0
|
||
for (path, img, im0s, vid_cap), (path_, img2, im0s_, vid_cap_) in zip(dataset, dataset2):
|
||
# print(path)
|
||
# print(path_)
|
||
img = torch.from_numpy(img).to(device)
|
||
img2 = torch.from_numpy(img2).to(device)
|
||
|
||
img = img.half() if half else img.float() # uint8 to fp16/32
|
||
img /= 255.0 # 0 - 255 to 0.0 - 1.0
|
||
if img.ndimension() == 3:
|
||
img = img.unsqueeze(0)
|
||
img2 = img2.half() if half else img2.float() # uint8 to fp16/32
|
||
img2 /= 255.0 # 0 - 255 to 0.0 - 1.0
|
||
if img2.ndimension() == 3:
|
||
img2 = img2.unsqueeze(0)
|
||
|
||
# Inference
|
||
t1 = time_synchronized()
|
||
pred = model(img, img2, augment=opt.augment)[0]
|
||
|
||
# Apply NMS
|
||
pred = non_max_suppression(pred, opt.conf_thres, opt.iou_thres, classes=opt.classes, agnostic=opt.agnostic_nms)
|
||
t2 = time_synchronized()
|
||
|
||
# Apply Classifier
|
||
if classify:
|
||
pred = apply_classifier(pred, modelc, img, im0s)
|
||
|
||
# Process detections
|
||
for i, det in enumerate(pred): # detections per image
|
||
|
||
if webcam: # batch_size >= 1
|
||
p, s, im0, frame = path[i], '%g: ' % i, im0s[i].copy(), dataset.count
|
||
else:
|
||
p, s, im0, frame = path, '', im0s.copy(), getattr(dataset, 'frame', 0)
|
||
p, s, im0_, frame = path, '', im0s_.copy(), getattr(dataset2, 'frame', 0)
|
||
|
||
p = Path(p) # to Path
|
||
save_path = str(save_dir / p.name) # img.jpg
|
||
txt_path = str(save_dir / 'labels' / p.stem) + ('' if dataset.mode == 'image' else f'_{frame}') # img.txt
|
||
s += '%gx%g ' % img.shape[2:] # print string
|
||
gn = torch.tensor(im0.shape)[[1, 0, 1, 0]] # normalization gain whwh
|
||
# print(gn)
|
||
|
||
# # ----------------------------------------------------------------------------
|
||
# # 画GT，替换det
|
||
# #
|
||
# # ---------------------------------------------------------------------------
|
||
# annoPath = "/home/fqy/proj/paper/test_result/gt/"
|
||
# annoName = (path_.split("/")[-1]).split(".")[0] + ".txt"
|
||
# annoPath += annoName
|
||
# # print(annoPath)
|
||
# gt = np.loadtxt(annoPath)
|
||
# gt = gt.reshape((-1, 5))
|
||
# ones = np.ones((gt.shape[0], 1))
|
||
# gt = np.hstack((gt, ones))
|
||
# gt[:, [0,1,2,3,4,5]] = gt[:, [1,2,3,4,5,0]]
|
||
# gt = torch.from_numpy(gt).to(device)
|
||
# # print(gt[:, :4])
|
||
# gt[:, :4] = xywh2xyxy(gt[:, :4]) * 640
|
||
#
|
||
# det = gt
|
||
|
||
# print(det)
|
||
if len(det):
|
||
# Rescale boxes from img_size to im0 size
|
||
det[:, :4] = scale_coords(img.shape[2:], det[:, :4], im0.shape).round()
|
||
|
||
# Print results
|
||
for c in det[:, -1].unique():
|
||
n = (det[:, -1] == c).sum() # detections per class
|
||
s += f"{n} {names[int(c)]}{'s' * (n > 1)}, " # add to string
|
||
|
||
# Write results
|
||
for *xyxy, conf, cls in reversed(det):
|
||
if save_txt: # Write to file
|
||
xywh = (xyxy2xywh(torch.tensor(xyxy).view(1, 4)) / gn).view(-1).tolist() # normalized xywh
|
||
line = (cls, *xywh, conf) #if opt.save_conf else (cls, *xywh) # label format
|
||
with open(txt_path + '.txt', 'a') as f:
|
||
f.write(('%g ' * len(line)).rstrip() % line + '\n')
|
||
|
||
if save_img or opt.save_crop or view_img: # Add bbox to image
|
||
c = int(cls) # integer class
|
||
label = None if opt.hide_labels else ( f'{names[c]} {conf:.2f}')
|
||
|
||
plot_one_box(xyxy, im0, label=label, color=colors(c, True), line_thickness=opt.line_thickness)
|
||
plot_one_box(xyxy, im0_, label=label, color=colors(c, True), line_thickness=opt.line_thickness)
|
||
if opt.save_crop:
|
||
save_one_box(xyxy, im0s, file=save_dir / 'crops' / names[c] / f'{p.stem}.jpg', BGR=True)
|
||
|
||
# Print time (inference + NMS)
|
||
print(f'{s}Done. ({t2 - t1:.6f}s, {1/(t2 - t1):.6f}Hz)')
|
||
# add all the fps
|
||
img_num += 1
|
||
fps_sum += 1/(t2 - t1)
|
||
|
||
# Stream results
|
||
if view_img:
|
||
cv2.imshow(str(p), im0)
|
||
cv2.waitKey(1) # 1 millisecond
|
||
|
||
# Save results (image with detections)
|
||
if save_img:
|
||
if dataset.mode == 'image':
|
||
save_path_rgb = save_path.split('.')[0] + '_rgb.' + save_path.split('.')[1]
|
||
save_path_ir = save_path.split('.')[0] + '_ir.' + save_path.split('.')[1]
|
||
print(save_path_rgb)
|
||
cv2.imwrite(save_path_rgb, im0)
|
||
cv2.imwrite(save_path_ir, im0_)
|
||
else: # 'video' or 'stream'
|
||
if vid_path != save_path: # new video
|
||
vid_path = save_path
|
||
if isinstance(vid_writer, cv2.VideoWriter):
|
||
vid_writer.release() # release previous video writer
|
||
if vid_cap: # video
|
||
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: # stream
|
||
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"Results saved to {save_dir}{s}")
|
||
|
||
print(f'Done. ({time.time() - t0:.3f}s)')
|
||
print(f'Average Speed: {fps_sum/img_num:.6f}Hz')
|
||
|
||
# 将yolo格式的txt文件转换为coco格式的json文件
|
||
print("Converting YOLO prediction to COCO format...>")
|
||
from yolo2coco_l import yolo_to_coco
|
||
coco_json = yolo_to_coco(save_dir/'labels')
|
||
import json
|
||
# 保存为JSON文件
|
||
with open(save_dir/'test_pred.json', 'w') as f:
|
||
json.dump(coco_json, f)
|
||
|
||
print("YOLO prediction to COCO format conversion completed.")
|
||
|
||
|
||
if __name__ == '__main__':
|
||
parser = argparse.ArgumentParser()
|
||
parser.add_argument('--weights', nargs='+', type=str, default='best.pt', help='model.pt path(s)')
|
||
parser.add_argument('--data', type=str, default='/data8T/xq/Dataset', help='数据集路径') # file/folder, 0 for webcam
|
||
parser.add_argument('--source1', type=str, help='source') # file/folder, 0 for webcam
|
||
parser.add_argument('--source2', type=str, help='source') # file/folder, 0 for webcam
|
||
parser.add_argument('--img-size', type=int, default=640, help='inference size (pixels)')
|
||
parser.add_argument('--conf-thres', type=float, default=0.3, help='object confidence threshold')
|
||
parser.add_argument('--iou-thres', type=float, default=0.2, help='IOU threshold for NMS')
|
||
parser.add_argument('--device', default='0', help='cuda device, i.e. 0 or 0,1,2,3 or cpu')
|
||
parser.add_argument('--view-img', default=False, action='store_true', help='display results')
|
||
parser.add_argument('--save-txt', default=True, action='store_true', help='save results to *.txt')
|
||
parser.add_argument('--save-img', default=False, 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('--save-crop', action='store_true', help='save cropped prediction boxes')
|
||
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='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('--line-thickness', default=2, type=int, help='bounding box thickness (pixels)')
|
||
parser.add_argument('--hide-labels', default=False, action='store_true', help='hide labels')
|
||
parser.add_argument('--hide-conf', default=False, action='store_true', help='hide confidences')
|
||
opt = parser.parse_args()
|
||
import os
|
||
from data.coco2yolo_test import coco2yolo
|
||
|
||
# convert COCO to YOLO format
|
||
print("Converting COCO to YOLO format...")
|
||
coco2yolo(opt.data) # convert COCO to YOLO format
|
||
print("COCO to YOLO format conversion completed.")
|
||
if opt.data is not None:
|
||
opt.source1 = os.path.join(opt.data, 'sky_data3/images/rgb/test')
|
||
opt.source2 = os.path.join(opt.data, 'sky_data3/images/ir/test')
|
||
print(opt)
|
||
check_requirements(exclude=('pycocotools', 'thop'))
|
||
|
||
with torch.no_grad():
|
||
if opt.update: # update all models (to fix SourceChangeWarning)
|
||
for opt.weights in ['yolov5s.pt', 'yolov5m.pt', 'yolov5l.pt', 'yolov5x.pt']:
|
||
detect(opt=opt)
|
||
strip_optimizer(opt.weights)
|
||
else:
|
||
print("helloxxxxxxxxxxxxxxxxxxxx")
|
||
detect(opt=opt)
|