yolov7 姿态识别-人体骨架-实时检测+实例分割_人脸识别、人体骨架识别、手势识别、手势骨架、目标检测 (ssd、yolov7)

(15条消息) YOLOv7实例分割_迷途小书童的Note的博客-CSDN博客https://blog.csdn.net/djstavaV/article/details/126357677
(15条消息) yolov7 姿态识别-人体骨架-实时检测_ASURIUS的博客-CSDN博客https://blog.csdn.net/ASURIUS/article/details/127513826

import time
import matplotlib
matplotlib.use('TkAgg')
import matplotlib.pyplot as plt
import torch
import cv2
from torchvision import transforms
import numpy as np
from utils.datasets import letterbox
from utils.general import non_max_suppression_kpt
from utils.plots import output_to_keypoint, plot_skeleton_kpts
 
device =  torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
weigths = torch.load('yolov7-w6-pose.pt')
model = weigths['model']
model = model.half().to(device) if device.type != "cpu" else model.float().to(device)
_ = model.eval()
 
 
 
 
# 读取摄像头画面
print(device)
url = 0
cap = cv2.VideoCapture(url)
while (cap.isOpened()):
    ret, image = cap.read()
    # image = cv2.imread('xiaolu.jpg')
    image = letterbox(image, 960, stride=64, auto=True)[0]
    image_ = image.copy()
    image = transforms.ToTensor()(image)
    image = torch.tensor(np.array([image.numpy()]))
    image = image.to(device)
    image = image.half() if device.type != "cpu" else image.float()
 
    # 姿势识别
    t1 = time.time()
    with torch.no_grad():
        output, _ = model(image)
        output = non_max_suppression_kpt(output, 0.25, 0.65, nc=model.yaml['nc'], nkpt=model.yaml['nkpt'],
                                         kpt_label=True)
        output = output_to_keypoint(output)
    nimg = image[0].permute(1, 2, 0) * 255
    nimg = nimg.cpu().numpy().astype(np.uint8)
    nimg = cv2.cvtColor(nimg, cv2.COLOR_RGB2BGR)
    for idx in range(output.shape[0]):
        plot_skeleton_kpts(nimg, output[idx, 7:].T, 3)
 
    # 打开摄像头
    cv2.namedWindow("ning", cv2.WINDOW_NORMAL)
    cv2.imshow("ning", nimg)
    t2 = time.time()
    print(f'Done. ({(1E3 * (t2 - t1)):.1f}ms) Inference')
    if cv2.waitKey(1) & 0xFF == ord('q'):
        break
cap.release()
cv2.destroyAllWindows()
 
 
 
# image = cv2.imread('bus.jpg')
# image = letterbox(image, 960, stride=64, auto=True)[0]
# image_ = image.copy()
# image = transforms.ToTensor()(image)
# image = torch.tensor(np.array([image.numpy()]))
# image = image.to(device)
# image = image.half()
#
# output, _ = model(image)
#
# output = non_max_suppression_kpt(output, 0.25, 0.65, nc=model.yaml['nc'], nkpt=model.yaml['nkpt'], kpt_label=True)
# with torch.no_grad():
#     output = output_to_keypoint(output)
# nimg = image[0].permute(1, 2, 0) * 255
# nimg = nimg.cpu().numpy().astype(np.uint8)
# nimg = cv2.cvtColor(nimg, cv2.COLOR_RGB2BGR)
# for idx in range(output.shape[0]):
#     plot_skeleton_kpts(nimg, output[idx, 7:].T, 3)
 
# plt.figure(figsize=(8, 8))
# plt.axis('off')
# plt.imshow(nimg)
# plt.show()
# cv2.imshow('nimg',nimg)
# cv2.waitKey(100000)
 

分割的部分依赖于 facebook 的 detectron2，而 detectron2 要求 torch 版本大于 1.8，由于之前我一直用的都是 1.7.1，因此这里需要创建一个新的环境

# 创建新的虚拟环境
conda create -n pytorch1.8 python=3.8
conda activate pytorch1.8
 
# 安装 torch 1.8.2
pip install torch==1.8.2 torchvision==0.9.2 torchaudio===0.8.2 --extra-index-url https://download.pytorch.org/whl/lts/1.8/cu111
 
# 修改requirements.txt，将其中的torch和torchvision注释掉
pip install -r requirements.txt
 
# 安装detectron2
git clone https://github.com/facebookresearch/detectron2
cd detectron2
python setup.py install
cd ..

然后去下载实例分割的模型 https://github.com/WongKinYiu/yolov7/releases/download/v0.1/yolov7-mask.pt，将模型放入源码目录中

分割的示例代码在 tools/instance.ipynb，可以在 jupyter notebook 中直接运行

如果需要将 ipynb 文件转成 python 文件，就执行

jupyter nbconvert --to python tools/instance.ipynb

将生成的 tools/instance.py 拷贝到源码根目录下，然后修改文件的最后显示部分为保存结果图片

import matplotlib.pyplot as plt
import torch
import cv2
import yaml
from torchvision import transforms
import numpy as np
 
from utils.datasets import letterbox
from utils.general import non_max_suppression_mask_conf
 
from detectron2.modeling.poolers import ROIPooler
from detectron2.structures import Boxes
from detectron2.utils.memory import retry_if_cuda_oom
from detectron2.layers import paste_masks_in_image
 
device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
with open('data/hyp.scratch.mask.yaml') as f:
    hyp = yaml.load(f, Loader=yaml.FullLoader)
weigths = torch.load('yolov7-mask.pt')
model = weigths['model']
model = model.half().to(device)
_ = model.eval()
 
image = cv2.imread('inference/images/horses.jpg')  # 504x378 image
image = letterbox(image, 640, stride=64, auto=True)[0]
image_ = image.copy()
image = transforms.ToTensor()(image)
image = torch.tensor(np.array([image.numpy()]))
image = image.to(device)
image = image.half()
 
output = model(image)
 
inf_out, train_out, attn, mask_iou, bases, sem_output = output['test'], output['bbox_and_cls'], output['attn'], output['mask_iou'], output['bases'], output['sem']
 
bases = torch.cat([bases, sem_output], dim=1)
nb, _, height, width = image.shape
names = model.names
pooler_scale = model.pooler_scale
pooler = ROIPooler(output_size=hyp['mask_resolution'], scales=(pooler_scale,), sampling_ratio=1, pooler_type='ROIAlignV2', canonical_level=2)
 
output, output_mask, output_mask_score, output_ac, output_ab = non_max_suppression_mask_conf(inf_out, attn, bases, pooler, hyp, conf_thres=0.25, iou_thres=0.65, merge=False, mask_iou=None)
 
pred, pred_masks = output[0], output_mask[0]
base = bases[0]
bboxes = Boxes(pred[:, :4])
original_pred_masks = pred_masks.view(-1, hyp['mask_resolution'], hyp['mask_resolution'])
pred_masks = retry_if_cuda_oom(paste_masks_in_image)( original_pred_masks, bboxes, (height, width), threshold=0.5)
pred_masks_np = pred_masks.detach().cpu().numpy()
pred_cls = pred[:, 5].detach().cpu().numpy()
pred_conf = pred[:, 4].detach().cpu().numpy()
nimg = image[0].permute(1, 2, 0) * 255
nimg = nimg.cpu().numpy().astype(np.uint8)
nimg = cv2.cvtColor(nimg, cv2.COLOR_RGB2BGR)
nbboxes = bboxes.tensor.detach().cpu().numpy().astype(np.int)
pnimg = nimg.copy()
 
for one_mask, bbox, cls, conf in zip(pred_masks_np, nbboxes, pred_cls, pred_conf):
    if conf < 0.25:
        continue
    color = [np.random.randint(255), np.random.randint(255), np.random.randint(255)]
 
 
    pnimg[one_mask] = pnimg[one_mask] * 0.5 + np.array(color, dtype=np.uint8) * 0.5
    pnimg = cv2.rectangle(pnimg, (bbox[0], bbox[1]), (bbox[2], bbox[3]), color, 2)
    #label = '%s %.3f' % (names[int(cls)], conf)
    #t_size = cv2.getTextSize(label, 0, fontScale=0.5, thickness=1)[0]
    #c2 = bbox[0] + t_size[0], bbox[1] - t_size[1] - 3
    #pnimg = cv2.rectangle(pnimg, (bbox[0], bbox[1]), c2, color, -1, cv2.LINE_AA)  # filled
    #pnimg = cv2.putText(pnimg, label, (bbox[0], bbox[1] - 2), 0, 0.5, [255, 255, 255], thickness=1, lineType=cv2.LINE_AA)
 
cv2.imwrite("instance_result.jpg", pnimg)

同样的，这里也提供一份视频文件或摄像头检测的代码

import torch
import cv2
import yaml
from torchvision import transforms
import numpy as np
 
from utils.datasets import letterbox
from utils.general import non_max_suppression_mask_conf
 
from detectron2.modeling.poolers import ROIPooler
from detectron2.structures import Boxes
from detectron2.utils.memory import retry_if_cuda_oom
from detectron2.layers import paste_masks_in_image
 
 
device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
with open('data/hyp.scratch.mask.yaml') as f:
    hyp = yaml.load(f, Loader=yaml.FullLoader)
weigths = torch.load('yolov7-mask.pt')
model = weigths['model']
model = model.half().to(device)
_ = model.eval()
 
cap = cv2.VideoCapture('vehicle_test.mp4')
if (cap.isOpened() == False):
    print('open failed.')
    exit(-1)
 
# 分辨率
frame_width = int(cap.get(3))
frame_height = int(cap.get(4))
 
# 图片缩放
vid_write_image = letterbox(cap.read()[1], (frame_width), stride=64, auto=True)[0]
resize_height, resize_width = vid_write_image.shape[:2]
 
# 保存结果视频
out = cv2.VideoWriter("result_instance.mp4",
                      cv2.VideoWriter_fourcc(*'mp4v'), 30,
                      (resize_width, resize_height))
 
while(cap.isOpened):
    flag, image = cap.read()
    if flag:
        image = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)
        image = letterbox(image, frame_width, stride=64, auto=True)[0]
        image_ = image.copy()
        image = transforms.ToTensor()(image)
        image = torch.tensor(np.array([image.numpy()]))
        image = image.to(device)
        image = image.half()
 
        with torch.no_grad():
            output = model(image)
        
        inf_out, train_out, attn, mask_iou, bases, sem_output = output['test'], output['bbox_and_cls'], output['attn'], output['mask_iou'], output['bases'], output['sem']
    
        bases = torch.cat([bases, sem_output], dim=1)
        nb, _, height, width = image.shape
        names = model.names
        pooler_scale = model.pooler_scale
        pooler = ROIPooler(output_size=hyp['mask_resolution'], scales=(pooler_scale,), sampling_ratio=1, pooler_type='ROIAlignV2', canonical_level=2)
 
        output, output_mask, output_mask_score, output_ac, output_ab = non_max_suppression_mask_conf(inf_out, attn, bases, pooler, hyp, conf_thres=0.25, iou_thres=0.65, merge=False, mask_iou=None)
 
        pred, pred_masks = output[0], output_mask[0]
        base = bases[0]
        bboxes = Boxes(pred[:, :4])
        original_pred_masks = pred_masks.view(-1, hyp['mask_resolution'], hyp['mask_resolution'])
        pred_masks = retry_if_cuda_oom(paste_masks_in_image)( original_pred_masks, bboxes, (height, width), threshold=0.5)
        pred_masks_np = pred_masks.detach().cpu().numpy()
        pred_cls = pred[:, 5].detach().cpu().numpy()
        pred_conf = pred[:, 4].detach().cpu().numpy()
        nimg = image[0].permute(1, 2, 0) * 255
        nimg = nimg.cpu().numpy().astype(np.uint8)
        nimg = cv2.cvtColor(nimg, cv2.COLOR_RGB2BGR)
        nbboxes = bboxes.tensor.detach().cpu().numpy().astype(np.int)
        pnimg = nimg.copy()
 
        for one_mask, bbox, cls, conf in zip(pred_masks_np, nbboxes, pred_cls, pred_conf):
            if conf < 0.25:
                continue
            
            color = [np.random.randint(255), np.random.randint(255), np.random.randint(255)]
 
            pnimg[one_mask] = pnimg[one_mask] * 0.5 + np.array(color, dtype=np.uint8) * 0.5
            pnimg = cv2.rectangle(pnimg, (bbox[0], bbox[1]), (bbox[2], bbox[3]), color, 2)
 
        cv2.imshow('YOLOv7 mask', pnimg)
        out.write(pnimg)
 
        if cv2.waitKey(1) & 0xFF == ord('q'):
            break
 
    else:
        break
    
 
cap.release()
cv2.destroyAllWindows()