1.从Detection文件入手，可以单张或批量
import argparse
import os
import sys
from pathlib import Path
import cv2
import torch
import torch.backends.cudnn as cudnn
FILE = Path(__file__).resolve()
ROOT = FILE.parents[0] # YOLOv5 root directory
if str(ROOT) not in sys.path:
sys.path.append(str(ROOT)) # add ROOT to PATH
ROOT = Path(os.path.relpath(ROOT, Path.cwd())) # relative
from models.common import DetectMultiBackend
from utils.datasets import IMG_FORMATS, VID_FORMATS, LoadImages, LoadStreams
from utils.general import (LOGGER, check_file, check_img_size, check_imshow, check_requirements, colorstr,
increment_path, non_max_suppression, print_args, scale_coords, strip_optimizer, xyxy2xywh)
from utils.plots import Annotator, colors, save_one_box
from utils.torch_utils import select_device, time_sync
@torch.no_grad()
def run(weights=ROOT / 'yolov5s.pt', # model.pt path(s)
source=ROOT / 'data/images', # file/dir/URL/glob, 0 for webcam
data=ROOT / 'data/coco128.yaml', # dataset.yaml path
imgsz=(640, 640), # inference size (height, width)
conf_thres=0.25, # confidence threshold
iou_thres=0.45, # NMS IOU threshold
max_det=1000, # maximum detections per image
device='', # cuda device, i.e. 0 or 0,1,2,3 or cpu
view_img=False, # show results
save_txt=False, # save results to *.txt
save_conf=False, # save confidences in --save-txt labels
save_crop=False, # save cropped prediction boxes
nosave=False, # do not save images/videos
classes=None, # filter by class: --class 0, or --class 0 2 3
agnostic_nms=False, # class-agnostic NMS
augment=False, # augmented inference
visualize=False, # visualize features
update=False, # update all models
project=ROOT / 'runs/detect', # save results to project/name
name='exp', # save results to project/name
exist_ok=False, # existing project/name ok, do not increment
line_thickness=3, # bounding box thickness (pixels)
hide_labels=False, # hide labels
hide_conf=False, # hide confidences
half=False, # use FP16 half-precision inference
dnn=False, # use OpenCV DNN for onNX inference
):
source = str(source)
save_img = not nosave and not source.endswith('.txt') # save inference images
is_file = Path(source).suffix[1:] in (IMG_FORMATS + VID_FORMATS)
is_url = source.lower().startswith(('rtsp://', 'rtmp://', 'http://', 'https://'))
webcam = source.isnumeric() or source.endswith('.txt') or (is_url and not is_file)
if is_url and is_file:
source = check_file(source) # download
# Directories
save_dir = increment_path(Path(project) / name, exist_ok=exist_ok) # increment run
(save_dir / 'labels' if save_txt else save_dir).mkdir(parents=True, exist_ok=True) # make dir
# Load model
device = select_device(device)
model = DetectMultiBackend(weights, device=device, dnn=dnn, data=data)
stride, names, pt, jit, onnx, engine = model.stride, model.names, model.pt, model.jit, model.onnx, model.engine
imgsz = check_img_size(imgsz, s=stride) # check image size
# Half
half &= (pt or jit or engine) and device.type != 'cpu' # half precision only supported by PyTorch on CUDA
if pt or jit:
model.model.half() if half else model.model.float()
# Dataloader
if webcam:
view_img = check_imshow()
cudnn.benchmark = True # set True to speed up constant image size inference
dataset = LoadStreams(source, img_size=imgsz, stride=stride, auto=pt)
bs = len(dataset) # batch_size
else:
dataset = LoadImages(source, img_size=imgsz, stride=stride, auto=pt)
bs = 1 # batch_size
vid_path, vid_writer = [None] * bs, [None] * bs
# Run inference
model.warmup(imgsz=(1, 3, *imgsz), half=half) # warmup
dt, seen = [0.0, 0.0, 0.0], 0
for path, im, im0s, vid_cap, s in dataset:
t1 = time_sync()
im = torch.from_numpy(im).to(device)
im = im.half() if half else im.float() # uint8 to fp16/32
im /= 255 # 0 - 255 to 0.0 - 1.0
if len(im.shape) == 3:
im = im[None] # expand for batch dim
t2 = time_sync()
dt[0] += t2 - t1
# Inference
visualize = increment_path(save_dir / Path(path).stem, mkdir=True) if visualize else False
# pred = model(im, augment=augment, visualize=visualize)
model_ = model.model.model
print(len(model_))
pred =im
for i in range(len(model_)):
pred = model_[i](pred)
if i == 2:
ReLu_out = pred
t3 = time_sync()
dt[1] += t3 - t2
# NMS
pred = non_max_suppression(pred, conf_thres, iou_thres, classes, agnostic_nms, max_det=max_det)
dt[2] += time_sync() - t3
# Second-stage classifier (optional)
# pred = utils.general.apply_classifier(pred, classifier_model, im, im0s)
# Process predictions
for i, det in enumerate(pred): # per image
seen += 1
if webcam: # batch_size >= 1
p, im0, frame = path[i], im0s[i].copy(), dataset.count
s += f'{i}: '
else:
p, im0, frame = path, im0s.copy(), getattr(dataset, 'frame', 0)
p = Path(p) # to Path
save_path = str(save_dir / p.name) # im.jpg
txt_path = str(save_dir / 'labels' / p.stem) + ('' if dataset.mode == 'image' else f'_{frame}') # im.txt
s += '%gx%g ' % im.shape[2:] # print string
gn = torch.tensor(im0.shape)[[1, 0, 1, 0]] # normalization gain whwh
imc = im0.copy() if save_crop else im0 # for save_crop
annotator = Annotator(im0, line_width=line_thickness, example=str(names))
if len(det):
# Rescale boxes from img_size to im0 size
det[:, :4] = scale_coords(im.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 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 save_crop or view_img: # Add bbox to image
c = int(cls) # integer class
label = None if hide_labels else (names[c] if hide_conf else f'{names[c]} {conf:.2f}')
annotator.box_label(xyxy, label, color=colors(c, True))
if save_crop:
save_one_box(xyxy, imc, file=save_dir / 'crops' / names[c] / f'{p.stem}.jpg', BGR=True)
# Print time (inference-only)
LOGGER.info(f'{s}Done. ({t3 - t2:.3f}s)')
# Stream results
im0 = annotator.result()
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':
cv2.imwrite(save_path, im0)
else: # 'video' or 'stream'
if vid_path[i] != save_path: # new video
vid_path[i] = save_path
if isinstance(vid_writer[i], cv2.VideoWriter):
vid_writer[i].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[i] = cv2.VideoWriter(save_path, cv2.VideoWriter_fourcc(*'mp4v'), fps, (w, h))
vid_writer[i].write(im0)
# Print results
t = tuple(x / seen * 1E3 for x in dt) # speeds per image
LOGGER.info(f'Speed: %.1fms pre-process, %.1fms inference, %.1fms NMS per image at shape {(1, 3, *imgsz)}' % t)
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 ''
LOGGER.info(f"Results saved to {colorstr('bold', save_dir)}{s}")
if update:
strip_optimizer(weights) # update model (to fix SourceChangeWarning)
def parse_opt():
parser = argparse.ArgumentParser()
parser.add_argument('--weights', nargs='+', type=str, default='runs/train/exp29/weights/best.pt', help='model path(s)')
parser.add_argument('--source', type=str, default=ROOT / 'data/images', help='file/dir/URL/glob, 0 for webcam')
parser.add_argument('--data', type=str, default=ROOT / 'data/coco.yaml', help='(optional) dataset.yaml path')
parser.add_argument('--imgsz', '--img', '--img-size', nargs='+', type=int, default=[640, 640], help='inference size h,w')
parser.add_argument('--conf-thres', type=float, default=0.25, help='confidence threshold')
parser.add_argument('--iou-thres', type=float, default=0.45, help='NMS IoU threshold')
parser.add_argument('--max-det', type=int, default=1000, help='maximum detections per image')
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='show 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('--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: --classes 0, or --classes 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('--visualize', action='store_true', help='visualize features')
parser.add_argument('--update', action='store_true', help='update all models')
parser.add_argument('--project', default=ROOT / '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('--line-thickness', default=3, 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')
parser.add_argument('--half', action='store_true', help='use FP16 half-precision inference')
parser.add_argument('--dnn', action='store_true', help='use OpenCV DNN for onNX inference')
opt = parser.parse_args()
opt.imgsz *= 2 if len(opt.imgsz) == 1 else 1 # expand
print_args(FILE.stem, opt)
return opt
def main(opt):
check_requirements(exclude=('tensorboard', 'thop'))
run(**vars(opt))
if __name__ == "__main__":
opt = parse_opt()
main(opt)
2.找到pred这个预测结果
pred = model(im, augment=augment, visualize=visualize)
3.由于U版的yolo都是基于yaml文件集成的，所以需要把模型抽取出来
model_ = model.model.model
先看一下v5的模型图和Sequential序列
假设要看看SPP结构的作用，在热力图上展示
在 Sequential序列中是(9): SPPF
Sequential(
(0): Conv(
(conv): Conv2d(3, 8, kernel_size=(6, 6), stride=(2, 2), padding=(2, 2))
(act): SiLU(inplace=True)
)
(1): Conv(
(conv): Conv2d(8, 16, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1))
(act): SiLU(inplace=True)
)
(2): C3(
(cv1): Conv(
(conv): Conv2d(16, 8, kernel_size=(1, 1), stride=(1, 1))
(act): SiLU(inplace=True)
)
(cv2): Conv(
(conv): Conv2d(16, 8, kernel_size=(1, 1), stride=(1, 1))
(act): SiLU(inplace=True)
)
(cv3): Conv(
(conv): Conv2d(16, 16, kernel_size=(1, 1), stride=(1, 1))
(act): SiLU(inplace=True)
)
(m): Sequential(
(0): Bottleneck(
(cv1): Conv(
(conv): Conv2d(8, 8, kernel_size=(1, 1), stride=(1, 1))
(act): SiLU(inplace=True)
)
(cv2): Conv(
(conv): Conv2d(8, 8, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(act): SiLU(inplace=True)
)
)
)
)
(3): Conv(
(conv): Conv2d(16, 32, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1))
(act): SiLU(inplace=True)
)
(4): C3(
(cv1): Conv(
(conv): Conv2d(32, 16, kernel_size=(1, 1), stride=(1, 1))
(act): SiLU(inplace=True)
)
(cv2): Conv(
(conv): Conv2d(32, 16, kernel_size=(1, 1), stride=(1, 1))
(act): SiLU(inplace=True)
)
(cv3): Conv(
(conv): Conv2d(32, 32, kernel_size=(1, 1), stride=(1, 1))
(act): SiLU(inplace=True)
)
(m): Sequential(
(0): Bottleneck(
(cv1): Conv(
(conv): Conv2d(16, 16, kernel_size=(1, 1), stride=(1, 1))
(act): SiLU(inplace=True)
)
(cv2): Conv(
(conv): Conv2d(16, 16, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(act): SiLU(inplace=True)
)
)
)
)
(5): Conv(
(conv): Conv2d(32, 56, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1))
(act): SiLU(inplace=True)
)
(6): C3(
(cv1): Conv(
(conv): Conv2d(56, 28, kernel_size=(1, 1), stride=(1, 1))
(act): SiLU(inplace=True)
)
(cv2): Conv(
(conv): Conv2d(56, 28, kernel_size=(1, 1), stride=(1, 1))
(act): SiLU(inplace=True)
)
(cv3): Conv(
(conv): Conv2d(56, 56, kernel_size=(1, 1), stride=(1, 1))
(act): SiLU(inplace=True)
)
(m): Sequential(
(0): Bottleneck(
(cv1): Conv(
(conv): Conv2d(28, 28, kernel_size=(1, 1), stride=(1, 1))
(act): SiLU(inplace=True)
)
(cv2): Conv(
(conv): Conv2d(28, 28, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(act): SiLU(inplace=True)
)
)
)
)
(7): Conv(
(conv): Conv2d(56, 104, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1))
(act): SiLU(inplace=True)
)
(8): C3(
(cv1): Conv(
(conv): Conv2d(104, 52, kernel_size=(1, 1), stride=(1, 1))
(act): SiLU(inplace=True)
)
(cv2): Conv(
(conv): Conv2d(104, 52, kernel_size=(1, 1), stride=(1, 1))
(act): SiLU(inplace=True)
)
(cv3): Conv(
(conv): Conv2d(104, 104, kernel_size=(1, 1), stride=(1, 1))
(act): SiLU(inplace=True)
)
(m): Sequential(
(0): Bottleneck(
(cv1): Conv(
(conv): Conv2d(52, 52, kernel_size=(1, 1), stride=(1, 1))
(act): SiLU(inplace=True)
)
(cv2): Conv(
(conv): Conv2d(52, 52, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(act): SiLU(inplace=True)
)
)
)
)
(9): SPPF(
(cv1): Conv(
(conv): Conv2d(104, 52, kernel_size=(1, 1), stride=(1, 1))
(act): SiLU(inplace=True)
)
(cv2): Conv(
(conv): Conv2d(208, 104, kernel_size=(1, 1), stride=(1, 1))
(act): SiLU(inplace=True)
)
(m): MaxPool2d(kernel_size=5, stride=1, padding=2, dilation=1, ceil_mode=False)
)
(10): Conv(
(conv): Conv2d(104, 56, kernel_size=(1, 1), stride=(1, 1))
(act): SiLU(inplace=True)
)
(11): Upsample(scale_factor=2.0, mode=nearest)
(12): Concat()
(13): C3(
(cv1): Conv(
(conv): Conv2d(112, 28, kernel_size=(1, 1), stride=(1, 1))
(act): SiLU(inplace=True)
)
(cv2): Conv(
(conv): Conv2d(112, 28, kernel_size=(1, 1), stride=(1, 1))
(act): SiLU(inplace=True)
)
(cv3): Conv(
(conv): Conv2d(56, 56, kernel_size=(1, 1), stride=(1, 1))
(act): SiLU(inplace=True)
)
(m): Sequential(
(0): Bottleneck(
(cv1): Conv(
(conv): Conv2d(28, 28, kernel_size=(1, 1), stride=(1, 1))
(act): SiLU(inplace=True)
)
(cv2): Conv(
(conv): Conv2d(28, 28, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(act): SiLU(inplace=True)
)
)
)
)
(14): Conv(
(conv): Conv2d(56, 32, kernel_size=(1, 1), stride=(1, 1))
(act): SiLU(inplace=True)
)
(15): Upsample(scale_factor=2.0, mode=nearest)
(16): Concat()
(17): C3(
(cv1): Conv(
(conv): Conv2d(64, 16, kernel_size=(1, 1), stride=(1, 1))
(act): SiLU(inplace=True)
)
(cv2): Conv(
(conv): Conv2d(64, 16, kernel_size=(1, 1), stride=(1, 1))
(act): SiLU(inplace=True)
)
(cv3): Conv(
(conv): Conv2d(32, 32, kernel_size=(1, 1), stride=(1, 1))
(act): SiLU(inplace=True)
)
(m): Sequential(
(0): Bottleneck(
(cv1): Conv(
(conv): Conv2d(16, 16, kernel_size=(1, 1), stride=(1, 1))
(act): SiLU(inplace=True)
)
(cv2): Conv(
(conv): Conv2d(16, 16, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(act): SiLU(inplace=True)
)
)
)
)
(18): Conv(
(conv): Conv2d(32, 32, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1))
(act): SiLU(inplace=True)
)
(19): Concat()
(20): C3(
(cv1): Conv(
(conv): Conv2d(64, 28, kernel_size=(1, 1), stride=(1, 1))
(act): SiLU(inplace=True)
)
(cv2): Conv(
(conv): Conv2d(64, 28, kernel_size=(1, 1), stride=(1, 1))
(act): SiLU(inplace=True)
)
(cv3): Conv(
(conv): Conv2d(56, 56, kernel_size=(1, 1), stride=(1, 1))
(act): SiLU(inplace=True)
)
(m): Sequential(
(0): Bottleneck(
(cv1): Conv(
(conv): Conv2d(28, 28, kernel_size=(1, 1), stride=(1, 1))
(act): SiLU(inplace=True)
)
(cv2): Conv(
(conv): Conv2d(28, 28, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(act): SiLU(inplace=True)
)
)
)
)
(21): Conv(
(conv): Conv2d(56, 56, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1))
(act): SiLU(inplace=True)
)
(22): Concat()
(23): C3(
(cv1): Conv(
(conv): Conv2d(112, 52, kernel_size=(1, 1), stride=(1, 1))
(act): SiLU(inplace=True)
)
(cv2): Conv(
(conv): Conv2d(112, 52, kernel_size=(1, 1), stride=(1, 1))
(act): SiLU(inplace=True)
)
(cv3): Conv(
(conv): Conv2d(104, 104, kernel_size=(1, 1), stride=(1, 1))
(act): SiLU(inplace=True)
)
(m): Sequential(
(0): Bottleneck(
(cv1): Conv(
(conv): Conv2d(52, 52, kernel_size=(1, 1), stride=(1, 1))
(act): SiLU(inplace=True)
)
(cv2): Conv(
(conv): Conv2d(52, 52, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(act): SiLU(inplace=True)
)
)
)
)
(24): Detect(
(m): ModuleList(
(0): Conv2d(32, 117, kernel_size=(1, 1), stride=(1, 1))
(1): Conv2d(56, 117, kernel_size=(1, 1), stride=(1, 1))
(2): Conv2d(104, 117, kernel_size=(1, 1), stride=(1, 1))
)
)
)
4.对于nn.Sequential结构，要想获取中间网络层输出，可以使用循环遍历的方式得到
layer_9 = 0
print(len(model_))#层数
pred =im #im是输入图像
for i in range(len(model_)):
pred = model_[i](pred) #不断迭代pred
if i == 9:
layer_9 = pred #获得第二层的中间结果
欢迎分享，转载请注明来源：内存溢出
微信扫一扫
支付宝扫一扫
评论列表（0条）