366 lines
15 KiB
Python
366 lines
15 KiB
Python
|
||
#!/usr/bin/env python
|
||
# -*- coding: UTF-8 -*-
|
||
'''
|
||
@Project -> File ：yolov8_segment.py
|
||
@IDE ：PyCharm
|
||
@Author ：hjw
|
||
@Version : 1.0.0
|
||
@Date ：2024/8/20 9:25
|
||
@Function ：
|
||
'''
|
||
|
||
# yolov8 pt模型，实例分割推理
|
||
import cv2
|
||
import time
|
||
import numpy as np
|
||
import torch, torchvision
|
||
import torch.nn.functional as F
|
||
|
||
|
||
|
||
def load_model(model_path, device):
|
||
model = torch.load(model_path, map_location=device)
|
||
category_list = model.get('CLASSES', model.get('model').names)
|
||
model = (model.get('ema') or model['model']).float() # FP32 model
|
||
model.__setattr__('CLASSES', category_list)
|
||
model.fuse().eval()
|
||
#model = model.cuda()
|
||
return model
|
||
|
||
|
||
def data_preprocess(model, img, img_scale, device):
|
||
stride, auto = 32, True
|
||
stride = max(int(model.stride.max()), 32)
|
||
img = letterbox(img, new_shape=img_scale, stride=stride, auto=auto)[0] # padded resize
|
||
img = np.ascontiguousarray(img.transpose((2, 0, 1))[::-1]) # HWC to CHW, BGR to RGB,contiguous
|
||
#img = torch.from_numpy(img) # ndarray to tensor
|
||
img = torch.from_numpy(img).to(device)
|
||
#img = torch.from_numpy(img)
|
||
img = img.float() # uint8 to fp32
|
||
img /= 255 # 0 - 255 to 0.0 - 1.0
|
||
if len(img.shape) == 3:
|
||
img = img[None] # expand for batch dim
|
||
return img
|
||
|
||
|
||
def letterbox(im, new_shape=(640, 640), color=(114, 114, 114), auto=True, scaleFill=False, scaleup=True, stride=32):
|
||
# Resize and pad image while meeting stride-multiple constraints
|
||
shape = im.shape[:2] # current shape [height, width]
|
||
if isinstance(new_shape, int):
|
||
new_shape = (new_shape, new_shape)
|
||
|
||
# Scale ratio (new / old)
|
||
r = min(new_shape[0] / shape[0], new_shape[1] / shape[1])
|
||
if not scaleup: # only scale down, do not scale up (for better val mAP)
|
||
r = min(r, 1.0)
|
||
|
||
# Compute padding
|
||
ratio = r, r # width, height ratios
|
||
new_unpad = int(round(shape[1] * r)), int(round(shape[0] * r))
|
||
dw, dh = new_shape[1] - new_unpad[0], new_shape[0] - new_unpad[1] # wh padding
|
||
if auto: # minimum rectangle
|
||
dw, dh = np.mod(dw, stride), np.mod(dh, stride) # wh padding
|
||
elif scaleFill: # stretch
|
||
dw, dh = 0.0, 0.0
|
||
new_unpad = (new_shape[1], new_shape[0])
|
||
ratio = new_shape[1] / shape[1], new_shape[0] / shape[0] # width, height ratios
|
||
|
||
dw /= 2 # divide padding into 2 sides
|
||
dh /= 2
|
||
|
||
if shape[::-1] != new_unpad: # resize
|
||
im = cv2.resize(im, new_unpad, interpolation=cv2.INTER_LINEAR)
|
||
top, bottom = int(round(dh - 0.1)), int(round(dh + 0.1))
|
||
left, right = int(round(dw - 0.1)), int(round(dw + 0.1))
|
||
im = cv2.copyMakeBorder(im, top, bottom, left, right, cv2.BORDER_CONSTANT, value=color) # add border
|
||
return im, ratio, (dw, dh)
|
||
|
||
|
||
def non_max_suppression(prediction, conf_thres=0.25, iou_thres=0.45, classes=None, agnostic=False, multi_label=False,
|
||
labels=(), max_det=300, nc=0, max_time_img=0.05, max_nms=30000, max_wh=7680, ):
|
||
# Checks
|
||
assert 0 <= conf_thres <= 1, f'Invalid Confidence threshold {conf_thres}, valid values are between 0.0 and 1.0'
|
||
assert 0 <= iou_thres <= 1, f'Invalid IoU {iou_thres}, valid values are between 0.0 and 1.0'
|
||
if isinstance(prediction, (list, tuple)): # YOLOv8 model in validation model, output = (inference_out, loss_out)
|
||
prediction = prediction[0] # select only inference output
|
||
|
||
device = prediction.device
|
||
mps = 'mps' in device.type # Apple MPS
|
||
if mps: # MPS not fully supported yet, convert tensors to CPU before NMS
|
||
prediction = prediction.cpu()
|
||
bs = prediction.shape[0] # batch size
|
||
nc = nc or (prediction.shape[1] - 4) # number of classes
|
||
nm = prediction.shape[1] - nc - 4
|
||
mi = 4 + nc # mask start index
|
||
xc = prediction[:, 4:mi].amax(1) > conf_thres # candidates
|
||
|
||
# Settings
|
||
# min_wh = 2 # (pixels) minimum box width and height
|
||
time_limit = 0.5 + max_time_img * bs # seconds to quit after
|
||
multi_label &= nc > 1 # multiple labels per box (adds 0.5ms/img)
|
||
|
||
prediction = prediction.transpose(-1, -2) # shape(1,84,6300) to shape(1,6300,84)
|
||
prediction[..., :4] = xywh2xyxy(prediction[..., :4]) # xywh to xyxy
|
||
|
||
t = time.time()
|
||
output = [torch.zeros((0, 6 + nm), device=prediction.device)] * bs
|
||
for xi, x in enumerate(prediction): # image index, image inference
|
||
# Apply constraints
|
||
# x[((x[:, 2:4] < min_wh) | (x[:, 2:4] > max_wh)).any(1), 4] = 0 # width-height
|
||
x = x[xc[xi]] # confidence
|
||
|
||
# Cat apriori labels if autolabelling
|
||
if labels and len(labels[xi]):
|
||
lb = labels[xi]
|
||
v = torch.zeros((len(lb), nc + nm + 4), device=x.device)
|
||
v[:, :4] = xywh2xyxy(lb[:, 1:5]) # box
|
||
v[range(len(lb)), lb[:, 0].long() + 4] = 1.0 # cls
|
||
x = torch.cat((x, v), 0)
|
||
|
||
# If none remain process next image
|
||
if not x.shape[0]:
|
||
continue
|
||
|
||
# Detections matrix nx6 (xyxy, conf, cls)
|
||
box, cls, mask = x.split((4, nc, nm), 1)
|
||
|
||
if multi_label:
|
||
i, j = torch.where(cls > conf_thres)
|
||
x = torch.cat((box[i], x[i, 4 + j, None], j[:, None].float(), mask[i]), 1)
|
||
else: # best class only
|
||
conf, j = cls.max(1, keepdim=True)
|
||
x = torch.cat((box, conf, j.float(), mask), 1)[conf.view(-1) > conf_thres]
|
||
|
||
# Filter by class
|
||
if classes is not None:
|
||
x = x[(x[:, 5:6] == torch.tensor(classes, device=x.device)).any(1)]
|
||
|
||
# Check shape
|
||
n = x.shape[0] # number of boxes
|
||
if not n: # no boxes
|
||
continue
|
||
if n > max_nms: # excess boxes
|
||
x = x[x[:, 4].argsort(descending=True)[:max_nms]] # sort by confidence and remove excess boxes
|
||
|
||
# Batched NMS
|
||
c = x[:, 5:6] * (0 if agnostic else max_wh) # classes
|
||
boxes, scores = x[:, :4] + c, x[:, 4] # boxes (offset by class), scores
|
||
i = torchvision.ops.nms(boxes, scores, iou_thres) # NMS
|
||
i = i[:max_det] # limit detections
|
||
|
||
output[xi] = x[i]
|
||
if mps:
|
||
output[xi] = output[xi].to(device)
|
||
if (time.time() - t) > time_limit:
|
||
print(f'WARNING ⚠️ NMS time limit {time_limit:.3f}s exceeded')
|
||
break # time limit exceeded
|
||
return output
|
||
|
||
|
||
def xywh2xyxy(x):
|
||
"""
|
||
Convert bounding box coordinates from (x, y, width, height) format to (x1, y1, x2, y2) format where (x1, y1) is the
|
||
top-left corner and (x2, y2) is the bottom-right corner.
|
||
Args:
|
||
x (np.ndarray | torch.Tensor): The input bounding box coordinates in (x, y, width, height) format.
|
||
Returns:
|
||
y (np.ndarray | torch.Tensor): The bounding box coordinates in (x1, y1, x2, y2) format.
|
||
"""
|
||
assert x.shape[-1] == 4, f'input shape last dimension expected 4 but input shape is {x.shape}'
|
||
y = torch.empty_like(x) if isinstance(x, torch.Tensor) else np.empty_like(x) # faster than clone/copy
|
||
dw = x[..., 2] / 2 # half-width
|
||
dh = x[..., 3] / 2 # half-height
|
||
y[..., 0] = x[..., 0] - dw # top left x
|
||
y[..., 1] = x[..., 1] - dh # top left y
|
||
y[..., 2] = x[..., 0] + dw # bottom right x
|
||
y[..., 3] = x[..., 1] + dh # bottom right y
|
||
return y
|
||
|
||
|
||
def scale_boxes(img1_shape, boxes, img0_shape, ratio_pad=None, padding=True):
|
||
"""
|
||
Rescales bounding boxes (in the format of xyxy) from the shape of the image they were originally specified in
|
||
(img1_shape) to the shape of a different image (img0_shape).
|
||
Args:
|
||
img1_shape (tuple): The shape of the image that the bounding boxes are for, in the format of (height, width).
|
||
boxes (torch.Tensor): the bounding boxes of the objects in the image, in the format of (x1, y1, x2, y2)
|
||
img0_shape (tuple): the shape of the target image, in the format of (height, width).
|
||
ratio_pad (tuple): a tuple of (ratio, pad) for scaling the boxes. If not provided, the ratio and pad will be
|
||
calculated based on the size difference between the two images.
|
||
padding (bool): If True, assuming the boxes is based on image augmented by yolo style. If False then do regular
|
||
rescaling.
|
||
Returns:
|
||
boxes (torch.Tensor): The scaled bounding boxes, in the format of (x1, y1, x2, y2)
|
||
"""
|
||
if ratio_pad is None: # calculate from img0_shape
|
||
gain = min(img1_shape[0] / img0_shape[0], img1_shape[1] / img0_shape[1]) # gain = old / new
|
||
pad = round((img1_shape[1] - img0_shape[1] * gain) / 2 - 0.1), round(
|
||
(img1_shape[0] - img0_shape[0] * gain) / 2 - 0.1) # wh padding
|
||
else:
|
||
gain = ratio_pad[0][0]
|
||
pad = ratio_pad[1]
|
||
|
||
if padding:
|
||
boxes[..., [0, 2]] -= pad[0] # x padding
|
||
boxes[..., [1, 3]] -= pad[1] # y padding
|
||
boxes[..., :4] /= gain
|
||
clip_boxes(boxes, img0_shape)
|
||
return boxes
|
||
|
||
|
||
def clip_boxes(boxes, shape):
|
||
"""
|
||
Takes a list of bounding boxes and a shape (height, width) and clips the bounding boxes to the shape.
|
||
|
||
Args:
|
||
boxes (torch.Tensor): the bounding boxes to clip
|
||
shape (tuple): the shape of the image
|
||
"""
|
||
if isinstance(boxes, torch.Tensor): # faster individually
|
||
boxes[..., 0].clamp_(0, shape[1]) # x1
|
||
boxes[..., 1].clamp_(0, shape[0]) # y1
|
||
boxes[..., 2].clamp_(0, shape[1]) # x2
|
||
boxes[..., 3].clamp_(0, shape[0]) # y2
|
||
else: # np.array (faster grouped)
|
||
boxes[..., [0, 2]] = boxes[..., [0, 2]].clip(0, shape[1]) # x1, x2
|
||
boxes[..., [1, 3]] = boxes[..., [1, 3]].clip(0, shape[0]) # y1, y2
|
||
|
||
|
||
def process_mask(protos, masks_in, bboxes, shape, ori_shape):
|
||
"""
|
||
Crop after upsample.
|
||
proto_out: [mask_dim, mask_h, mask_w]
|
||
out_masks: [n, mask_dim], n is number of masks after nms
|
||
bboxes: [n, 4], n is number of masks after nms
|
||
shape:input_image_size, (h, w)
|
||
|
||
return: h, w, n
|
||
"""
|
||
# mask转换成自定义尺寸
|
||
c, mh, mw = protos.shape # CHW
|
||
masks = (masks_in @ protos.float().view(c, -1)).sigmoid().view(-1, mh, mw)
|
||
masks = F.interpolate(masks[None], shape, mode='bilinear', align_corners=False)[0] # CHW
|
||
# mask转换成原图尺寸
|
||
gain = min(shape[0] / ori_shape[0], shape[1] / ori_shape[1]) # gain = old / new
|
||
pad = (shape[1] - ori_shape[1] * gain) / 2, (shape[0] - ori_shape[0] * gain) / 2 # wh padding
|
||
top, left = int(pad[1]), int(pad[0]) # y, x
|
||
bottom, right = int(shape[0] - pad[1]), int(shape[1] - pad[0])
|
||
if len(masks.shape) < 2:
|
||
raise ValueError(f'"len of masks shape" should be 2 or 3, but got {len(masks.shape)}')
|
||
masks = masks[:, top:bottom, left:right]
|
||
masks = F.interpolate(masks[None], ori_shape, mode='bilinear', align_corners=False)[0] # CHW
|
||
# 裁去box以外的图像
|
||
crop_masks = []
|
||
for i, mask in enumerate(masks):
|
||
mask = mask[int(bboxes[i][1]):int(bboxes[i][3]), int(bboxes[i][0]):int(bboxes[i][2])]
|
||
crop_masks.append(mask.gt_(0.5))
|
||
return crop_masks
|
||
|
||
|
||
def plot_result(det_cpu, dst_img, masks, category_names):
|
||
circle_max_contour = []
|
||
concrete_max_contour = []
|
||
for i, item in enumerate(det_cpu):
|
||
# rand_color = (random.randint(0, 255), random.randint(0, 255), random.randint(0, 255))
|
||
# 画box
|
||
box_x1, box_y1, box_x2, box_y2 = item[0:4].astype(np.int32)
|
||
label = category_names[int(item[5])]
|
||
rand_color = (0, 255, 255)
|
||
#cv2.rectangle(dst_img, (box_x1, box_y1), (box_x2, box_y2), color=rand_color, thickness=2)
|
||
score = item[4]
|
||
org = (int((box_x1+box_x2)/2), int((box_y1+box_y2)/2))
|
||
text = '{}|{:.2f}'.format(label, score)
|
||
cv2.putText(dst_img, text, org=org, fontFace=cv2.FONT_HERSHEY_SIMPLEX, fontScale=0.8, color=rand_color, thickness=2)
|
||
# 画mask
|
||
#mask = masks[i].cpu().numpy().astype(int)
|
||
mask = masks[i].cpu().data.numpy().astype(int)
|
||
#mask = masks[i].numpy().astype(int)
|
||
bbox_image = dst_img[box_y1:box_y2, box_x1:box_x2]
|
||
h, w = box_y2 - box_y1, box_x2 - box_x1
|
||
mask_colored = np.zeros((h, w, 3), dtype=np.uint8)
|
||
mask_colored[np.where(mask)] = rand_color
|
||
##################################
|
||
imgray = cv2.cvtColor(mask_colored, cv2.COLOR_BGR2GRAY)
|
||
# cv2.imshow('mask',imgray)
|
||
# cv2.waitKey(1)
|
||
# 2、二进制图像
|
||
ret, binary = cv2.threshold(imgray, 10, 255, 0)
|
||
# 阈值 二进制图像
|
||
# cv2.imshow('bin',binary)
|
||
# cv2.waitKey(1)
|
||
contours, hierarchy = cv2.findContours(binary, cv2.RETR_TREE, cv2.CHAIN_APPROX_NONE)
|
||
max_contour = None
|
||
max_perimeter = 0
|
||
for contour in contours:
|
||
perimeter = cv2.arcLength(contour, True)
|
||
if perimeter > max_perimeter:
|
||
max_perimeter = perimeter
|
||
max_contour = contour
|
||
rect = cv2.minAreaRect(max_contour)
|
||
# cv2.boxPoints可以将轮廓点转换为四个角点坐标
|
||
box = cv2.boxPoints(rect)
|
||
# 这一步不影响后面的画图，但是可以保证四个角点坐标为顺时针
|
||
startidx = box.sum(axis=1).argmin()
|
||
box = np.roll(box, 4 - startidx, 0)
|
||
# 在原图上画出预测的外接矩形
|
||
box = box.reshape((-1, 1, 2)).astype(np.int32)
|
||
box = box + [[[box_x1, box_y1]], [[box_x1, box_y1]], [[box_x1, box_y1]], [[box_x1, box_y1]]]
|
||
cv2.polylines(dst_img, [box], True, (0, 255, 0), 2)
|
||
|
||
return dst_img
|
||
# cv2.imwrite('rs.jpg', dst_img)
|
||
|
||
|
||
class yolov8_segment():
|
||
def __init__(self):
|
||
super(yolov8_segment, self).__init__()
|
||
|
||
|
||
def load_model(self, model_path, device):
|
||
self.model = load_model(model_path, device)
|
||
self.device = device
|
||
|
||
def model_inference(self, frame, upd_arr):
|
||
img = data_preprocess(self.model, frame, [640, 640], self.device)
|
||
|
||
# 推理
|
||
ori_img = frame.copy()
|
||
result = self.model(img, augment=False)
|
||
preds = result[0]
|
||
proto = result[1][-1]
|
||
# NMS
|
||
det = non_max_suppression(preds, conf_thres=0.25, iou_thres=0.3, nc=len(self.model.CLASSES))[0]
|
||
if det.shape[0] != 0:
|
||
# bbox还原至原图尺寸
|
||
det[:, :4] = scale_boxes(img.shape[2:], det[:, :4], ori_img.shape)
|
||
# mask转换成原图尺寸并做裁剪
|
||
masks = process_mask(proto[0], det[:, 6:], det[:, :4], img.shape[2:], ori_img.shape[0:2])
|
||
category_names = self.model.CLASSES
|
||
# 画图
|
||
# result_frame = plot_result(det.cpu().data.numpy(), ori_img, masks, category_names)
|
||
return 1 , det.cpu().data.numpy(), ori_img, masks, category_names
|
||
else:
|
||
return 0 , None, None, None, None
|
||
|
||
def clear(self):
|
||
del self.model
|
||
|
||
# model = yolov8_segment()
|
||
# model.load_model('./pt_model/yolov8n-seg.pt','cpu')
|
||
# cap = cv2.VideoCapture(1)
|
||
# while True:
|
||
# # count_file = len(os.listdir('E:\\A_panckg\\cv_sdk_discharge\\video_save')) # 数量
|
||
# ret, frame = cap.read()
|
||
# if ret:
|
||
# frame_save_count = 1000
|
||
# frame = cv2.resize(frame, (1280, 720))
|
||
# img = model.model_inference(frame, 0)
|
||
# cv2.imshow("imgrr", img)
|
||
# cv2.waitKey(1)
|
||
# #videoWriter(img)
|
||
|
||
|
||
|
||
|