免费建网站样板手机版,兰州全面解封最新消息,广西旅游网站建设,门户网站的基本特征a信息与服务文章目录 一、目标检测介绍二、YOLOv8介绍三、源码获取四、环境搭建4.1 环境检测 五、数据集准备六、 模型训练6.1 方式一6.2 方式二6.3 针对其他任务 七、模型验证八、模型测试九、模型转换9.1 转onnx9.1.1 方式一 9.2 转tensorRT9.2.1 trtexec9.2.2 代码转换9.2.3 推理代码 一… 文章目录 一、目标检测介绍二、YOLOv8介绍三、源码获取四、环境搭建4.1 环境检测 五、数据集准备六、 模型训练6.1 方式一6.2 方式二6.3 针对其他任务 七、模型验证八、模型测试九、模型转换9.1 转onnx9.1.1 方式一 9.2 转tensorRT9.2.1 trtexec9.2.2 代码转换9.2.3 推理代码 一、目标检测介绍
目标检测Object Detection是计算机视觉领域的一项重要技术旨在识别图像或视频中的特定目标并确定其位置。通过训练深度学习模型如卷积神经网络CNN可以实现对各种目标的精确检测。常见的目标检测任务包括人脸检测、行人检测、车辆检测等。目标检测在安防监控、自动驾驶、智能零售等领域具有广泛应用前景。
二、YOLOv8介绍
YOLOv8 是 Ultralytics 公司在 2023 年 1月 10 号开源的 YOLOv5 的下一个重大更新版本目前支持图像分类、物体检测和实例分割任务在还没有开源时就收到了用户的广泛关注。YOLOv8 抛弃了前几代模型的 Anchor-Base提供了一个全新的 SOTA 模型包括 P5 640 和 P6 1280 分辨率的目标检测网络和基于 YOLACT 的实例分割模型。和 YOLOv5 一样基于缩放系数也提供了 N/S/M/L/X 尺度的不同大小模型用于处理不同大小的输入图像 。
三、源码获取
https://github.com/ultralytics/ultralytics
四、环境搭建
CPU环境安装
conda create -n YOLOv8 python3.8.1
pip install ultralytics -i https://pypi.tuna.tsinghua.edu.cn/simpleGPU环境安装 参考这个链接点击
# 安装CUDA、CUDNN、Python、Pytorch、Torchvision 这里每个版本要相互对应
pip install ultralytics -i https://pypi.tuna.tsinghua.edu.cn/simple4.1 环境检测
下载yolov8n.pt和bus.jpg 然后命令行输入
yolo predict modelyolov8n.pt sourceultralytics/data/images/bus.jpg然后就会看到这个图片
五、数据集准备
这时候说明环境是没问题的了我们可以准备数据集了数据集的格式就是TXT标签加原图片可参考YOLOv5这个博客点击
六、 模型训练
6.1 方式一
YOLO(“yolov8n.pt”) 表示用预训练模型 YOLO(“yolov8n.yaml”)表示正常训练
from ultralytics import YOLO# Load a model
# model YOLO(yolov8n.yaml) # build a new model from scratch
model YOLO(yolov8n.pt) # load a pretrained model (recommended for training)# Use the model
model.train(dataultralytics/cfg/mask.yaml, epochs3) # train the model
metrics model.val() # evaluate model performance on the validation set
results model(ultralytics/data/images/bus.jpg) # predict on an image
path model.export(formatonnx) # export the model to ONNX format6.2 方式二
yolo taskdetect modetrain modelyolov8n.pt dataultralytics/cfg/mask.yaml epochs3 batch166.3 针对其他任务
包括四种detect 、segment、classify 、pose 通过修改YOLO()导入正确任务的yaml配置文件以及通过data来指定需要载入的对应任务的数据集即可。 这里的数据集我都是按照TXT标签和原图来进行划分的具体格式如下
from ultralytics import YOLO# Load a model
model YOLO(ultralytics/cfg/models/v8/yolov8-seg.yaml) # build a new model from scratch# Use the model
model.train(dataultralytics/cfg/custom_seg.yaml, epochs3) # train the model
metrics model.val() # evaluate model performance on the validation set
results model(ultralytics/data/images/bus.jpg) # predict on an image
path model.export(formatonnx) # export the model to ONNX format针对实例分割任务也成功运行。
七、模型验证
yolo taskdetect modeval modelruns/detect/train/weights/best.pt dataultralytics/cfg/mask.yaml devicecpu八、模型测试
yolo taskdetect modepredict modelruns/detect/train/weights/best.pt sourceultralytics/data/images devicecpu九、模型转换
9.1 转onnx
9.1.1 方式一
根据YOLOv8官网所给代码来实现
yolo export modelyolov8s.pt formatonnx opset12其次可以通过ultralytics API导出onnx模型并同时将bbox解码器和NMS等后处理添加到onnx模型中。YOLOv8-TensorRT
python export-det.py \
--weights yolov8s.pt \
--iou-thres 0.65 \
--conf-thres 0.25 \
--topk 100 \
--opset 11 \
--sim \
--input-shape 1 3 640 640 \
--device cuda:09.2 转tensorRT
9.2.1 trtexec
最简单的方式是使用TensorRT的bin文件夹下的trtexec.exe可执行文件
trtexec.exe --onnxbest.onnx --saveEnginebest.engine --fp169.2.2 代码转换
代码链接YOLOv8-TensorRT
python3 build.py \
--weights yolov8s.onnx \
--iou-thres 0.65 \
--conf-thres 0.25 \
--topk 100 \
--fp16 \
--device cuda:09.2.3 推理代码
参考博客点击 An example that uses TensorRTs Python api to make inferences.import ctypes
import os
import shutil
import random
import sys
import threading
import time
import cv2
import numpy as np
import pycuda.autoinit
import pycuda.driver as cuda
import tensorrt as trtCONF_THRESH 0.5
IOU_THRESHOLD 0.45
LEN_ALL_RESULT 705600##42000 ##(20*2040*4080*80)*(num_cls4) 一个batch长度
NUM_CLASSES 80 ##1
OBJ_THRESH 0.4def get_img_path_batches(batch_size, img_dir):ret []batch []for root, dirs, files in os.walk(img_dir):for name in files:if len(batch) batch_size:ret.append(batch)batch []batch.append(os.path.join(root, name))if len(batch) 0:ret.append(batch)return retdef plot_one_box(x, img, colorNone, labelNone, line_thicknessNone):description: Plots one bounding box on image img,this function comes from YoLov5 project.param:x: a box likes [x1,y1,x2,y2]img: a opencv image objectcolor: color to draw rectangle, such as (0,255,0)label: strline_thickness: intreturn:no returntl (line_thickness or round(0.002 * (img.shape[0] img.shape[1]) / 2) 1) # line/font thicknesscolor color or [random.randint(0, 255) for _ in range(3)]c1, c2 (int(x[0]), int(x[1])), (int(x[2]), int(x[3]))cv2.rectangle(img, c1, c2, color, thicknesstl, lineTypecv2.LINE_AA)if label:tf max(tl - 1, 1) # font thicknesst_size cv2.getTextSize(label, 0, fontScaletl / 3, thicknesstf)[0]c2 c1[0] t_size[0], c1[1] - t_size[1] - 3cv2.rectangle(img, c1, c2, color, -1, cv2.LINE_AA) # filledcv2.putText(img,label,(c1[0], c1[1] - 2),0,tl / 3,[225, 255, 255],thicknesstf,lineTypecv2.LINE_AA,)class YoLov8TRT(object):description: A YOLOv5 class that warps TensorRT ops, preprocess and postprocess ops.def __init__(self, engine_file_path):# Create a Context on this device,self.ctx cuda.Device(0).make_context()stream cuda.Stream()TRT_LOGGER trt.Logger(trt.Logger.INFO)runtime trt.Runtime(TRT_LOGGER)# Deserialize the engine from filewith open(engine_file_path, rb) as f:engine runtime.deserialize_cuda_engine(f.read())context engine.create_execution_context()host_inputs []cuda_inputs []host_outputs []cuda_outputs []bindings []for binding in engine:print(bingding:, binding, engine.get_tensor_shape(binding))size trt.volume(engine.get_tensor_shape(binding)) * engine.max_batch_sizedtype trt.nptype(engine.get_tensor_dtype(binding))# Allocate host and device buffershost_mem cuda.pagelocked_empty(size, dtype)cuda_mem cuda.mem_alloc(host_mem.nbytes)# Append the device buffer to device bindings.bindings.append(int(cuda_mem))# Append to the appropriate list.if engine.binding_is_input(binding):self.input_w engine.get_tensor_shape(binding)[-1]self.input_h engine.get_tensor_shape(binding)[-2]host_inputs.append(host_mem)cuda_inputs.append(cuda_mem)else:host_outputs.append(host_mem)cuda_outputs.append(cuda_mem)# Storeself.stream streamself.context contextself.engine engineself.host_inputs host_inputsself.cuda_inputs cuda_inputsself.host_outputs host_outputsself.cuda_outputs cuda_outputsself.bindings bindingsself.batch_size engine.max_batch_sizedef infer(self, raw_image_generator):threading.Thread.__init__(self)# Make self the active context, pushing it on top of the context stack.self.ctx.push()# Restorestream self.streamcontext self.contextengine self.enginehost_inputs self.host_inputscuda_inputs self.cuda_inputshost_outputs self.host_outputscuda_outputs self.cuda_outputsbindings self.bindings# Do image preprocessbatch_image_raw []batch_origin_h []batch_origin_w []batch_input_image np.empty(shape[self.batch_size, 3, self.input_h, self.input_w])for i, image_raw in enumerate(raw_image_generator):input_image, image_raw, origin_h, origin_w self.preprocess_image(image_raw)batch_image_raw.append(image_raw)batch_origin_h.append(origin_h)batch_origin_w.append(origin_w)np.copyto(batch_input_image[i], input_image)batch_input_image np.ascontiguousarray(batch_input_image)# Copy input image to host buffernp.copyto(host_inputs[0], batch_input_image.ravel())start time.time()# Transfer input data to the GPU.cuda.memcpy_htod_async(cuda_inputs[0], host_inputs[0], stream)# Run inference.context.execute_async_v2(bindingsbindings, stream_handlestream.handle)# context.execute_async(batch_sizeself.batch_size, bindingsbindings, stream_handlestream.handle)# Transfer predictions back from the GPU.cuda.memcpy_dtoh_async(host_outputs[0], cuda_outputs[0], stream)# Synchronize the streamstream.synchronize()end time.time()# Remove any context from the top of the context stack, deactivating it.self.ctx.pop()# Here we use the first row of output in that batch_size 1output host_outputs[0]# Do postprocessfor i in range(self.batch_size):result_boxes, result_scores, result_classid self.post_process_new(output[i * LEN_ALL_RESULT: (i 1) * LEN_ALL_RESULT], batch_origin_h[i], batch_origin_w[i],batch_input_image[i])if result_boxes is None:continue# Draw rectangles and labels on the original imagefor j in range(len(result_boxes)):box result_boxes[j]plot_one_box(box,batch_image_raw[i],label{}:{:.2f}.format(categories[int(result_classid[j])], result_scores[j]),)return batch_image_raw, end - startdef destroy(self):# Remove any context from the top of the context stack, deactivating it.self.ctx.pop()def get_raw_image(self, image_path_batch):description: Read an image from image pathfor img_path in image_path_batch:yield cv2.imread(img_path)def get_raw_image_zeros(self, image_path_batchNone):description: Ready data for warmupfor _ in range(self.batch_size):yield np.zeros([self.input_h, self.input_w, 3], dtypenp.uint8)def preprocess_image(self, raw_bgr_image):description: Convert BGR image to RGB,resize and pad it to target size, normalize to [0,1],transform to NCHW format.param:input_image_path: str, image pathreturn:image: the processed imageimage_raw: the original imageh: original heightw: original widthimage_raw raw_bgr_imageh, w, c image_raw.shapeimage cv2.cvtColor(image_raw, cv2.COLOR_BGR2RGB)# Calculate widht and height and paddingsr_w self.input_w / wr_h self.input_h / hif r_h r_w:tw self.input_wth int(r_w * h)tx1 tx2 0ty1 int((self.input_h - th) / 2)ty2 self.input_h - th - ty1else:tw int(r_h * w)th self.input_htx1 int((self.input_w - tw) / 2)tx2 self.input_w - tw - tx1ty1 ty2 0# Resize the image with long side while maintaining ratioimage cv2.resize(image, (tw, th))# Pad the short side with (128,128,128)image cv2.copyMakeBorder(image, ty1, ty2, tx1, tx2, cv2.BORDER_CONSTANT, None, (128, 128, 128))image image.astype(np.float32)# Normalize to [0,1]image / 255.0# HWC to CHW format:image np.transpose(image, [2, 0, 1])# CHW to NCHW formatimage np.expand_dims(image, axis0)# Convert the image to row-major order, also known as C order:image np.ascontiguousarray(image)return image, image_raw, h, wdef xywh2xyxy(self, origin_h, origin_w, x):description: Convert nx4 boxes from [x, y, w, h] to [x1, y1, x2, y2] where xy1top-left, xy2bottom-rightparam:origin_h: height of original imageorigin_w: width of original imagex: A boxes numpy, each row is a box [center_x, center_y, w, h]return:y: A boxes numpy, each row is a box [x1, y1, x2, y2]y np.zeros_like(x)r_w self.input_w / origin_wr_h self.input_h / origin_hif r_h r_w:y[:, 0] x[:, 0] - x[:, 2] / 2y[:, 2] x[:, 0] x[:, 2] / 2y[:, 1] x[:, 1] - x[:, 3] / 2 - (self.input_h - r_w * origin_h) / 2y[:, 3] x[:, 1] x[:, 3] / 2 - (self.input_h - r_w * origin_h) / 2y / r_welse:y[:, 0] x[:, 0] - x[:, 2] / 2 - (self.input_w - r_h * origin_w) / 2y[:, 2] x[:, 0] x[:, 2] / 2 - (self.input_w - r_h * origin_w) / 2y[:, 1] x[:, 1] - x[:, 3] / 2y[:, 3] x[:, 1] x[:, 3] / 2y / r_hreturn ydef post_process_new(self, output, origin_h, origin_w, img_pad):# Reshape to a two dimentional ndarrayc, h, w img_pad.shaperatio_w w / origin_wratio_h h / origin_hnum_anchors int(((h / 32) * (w / 32) (h / 16) * (w / 16) (h / 8) * (w / 8)))pred np.reshape(output, (num_anchors, 4 NUM_CLASSES))results []for detection in pred:score detection[4:]classid np.argmax(score)confidence score[classid]if confidence CONF_THRESH:if ratio_h ratio_w:center_x int(detection[0] / ratio_w)center_y int((detection[1] - (h - ratio_w * origin_h) / 2) / ratio_w)width int(detection[2] / ratio_w)height int(detection[3] / ratio_w)x1 int(center_x - width / 2)y1 int(center_y - height / 2)x2 int(center_x width / 2)y2 int(center_y height / 2)else:center_x int((detection[0] - (w - ratio_h * origin_w) / 2) / ratio_h)center_y int(detection[1] / ratio_h)width int(detection[2] / ratio_h)height int(detection[3] / ratio_h)x1 int(center_x - width / 2)y1 int(center_y - height / 2)x2 int(center_x width / 2)y2 int(center_y height / 2)results.append([x1, y1, x2, y2, confidence, classid])results np.array(results)if len(results) 0:return None, None, None# Do nmsboxes self.non_max_suppression(results, origin_h, origin_w, conf_thresCONF_THRESH, nms_thresIOU_THRESHOLD)result_boxes boxes[:, :4] if len(boxes) else np.array([])result_scores boxes[:, 4] if len(boxes) else np.array([])result_classid boxes[:, 5] if len(boxes) else np.array([])return result_boxes, result_scores, result_classiddef bbox_iou(self, box1, box2, x1y1x2y2True):description: compute the IoU of two bounding boxesparam:box1: A box coordinate (can be (x1, y1, x2, y2) or (x, y, w, h))box2: A box coordinate (can be (x1, y1, x2, y2) or (x, y, w, h))x1y1x2y2: select the coordinate formatreturn:iou: computed iouif not x1y1x2y2:# Transform from center and width to exact coordinatesb1_x1, b1_x2 box1[:, 0] - box1[:, 2] / 2, box1[:, 0] box1[:, 2] / 2b1_y1, b1_y2 box1[:, 1] - box1[:, 3] / 2, box1[:, 1] box1[:, 3] / 2b2_x1, b2_x2 box2[:, 0] - box2[:, 2] / 2, box2[:, 0] box2[:, 2] / 2b2_y1, b2_y2 box2[:, 1] - box2[:, 3] / 2, box2[:, 1] box2[:, 3] / 2else:# Get the coordinates of bounding boxesb1_x1, b1_y1, b1_x2, b1_y2 box1[:, 0], box1[:, 1], box1[:, 2], box1[:, 3]b2_x1, b2_y1, b2_x2, b2_y2 box2[:, 0], box2[:, 1], box2[:, 2], box2[:, 3]# Get the coordinates of the intersection rectangleinter_rect_x1 np.maximum(b1_x1, b2_x1)inter_rect_y1 np.maximum(b1_y1, b2_y1)inter_rect_x2 np.minimum(b1_x2, b2_x2)inter_rect_y2 np.minimum(b1_y2, b2_y2)# Intersection areainter_area np.clip(inter_rect_x2 - inter_rect_x1 1, 0, None) * \np.clip(inter_rect_y2 - inter_rect_y1 1, 0, None)# Union Areab1_area (b1_x2 - b1_x1 1) * (b1_y2 - b1_y1 1)b2_area (b2_x2 - b2_x1 1) * (b2_y2 - b2_y1 1)iou inter_area / (b1_area b2_area - inter_area 1e-16)return ioudef non_max_suppression(self, prediction, origin_h, origin_w, conf_thres0.5, nms_thres0.4):description: Removes detections with lower object confidence score than conf_thres and performsNon-Maximum Suppression to further filter detections.param:prediction: detections, (x1, y1,x2, y2, conf, cls_id)origin_h: original image heightorigin_w: original image widthconf_thres: a confidence threshold to filter detectionsnms_thres: a iou threshold to filter detectionsreturn:boxes: output after nms with the shape (x1, y1, x2, y2, conf, cls_id)# Get the boxes that score CONF_THRESHboxes prediction[prediction[:, 4] conf_thres]# Trandform bbox from [center_x, center_y, w, h] to [x1, y1, x2, y2]# boxes[:, :4] self.xywh2xyxy(origin_h, origin_w, boxes[:, :4])# clip the coordinatesboxes[:, 0] np.clip(boxes[:, 0], 0, origin_w)boxes[:, 2] np.clip(boxes[:, 2], 0, origin_w)boxes[:, 1] np.clip(boxes[:, 1], 0, origin_h)boxes[:, 3] np.clip(boxes[:, 3], 0, origin_h)# Object confidenceconfs boxes[:, 4]# Sort by the confsboxes boxes[np.argsort(-confs)]# Perform non-maximum suppressionkeep_boxes []while boxes.shape[0]:large_overlap self.bbox_iou(np.expand_dims(boxes[0, :4], 0), boxes[:, :4]) nms_threslabel_match boxes[0, -1] boxes[:, -1]# Indices of boxes with lower confidence scores, large IOUs and matching labelsinvalid large_overlap label_matchkeep_boxes [boxes[0]]boxes boxes[~invalid]boxes np.stack(keep_boxes, 0) if len(keep_boxes) else np.array([])return boxesdef img_infer(yolov5_wrapper, image_path_batch):batch_image_raw, use_time yolov5_wrapper.infer(yolov5_wrapper.get_raw_image(image_path_batch))for i, img_path in enumerate(image_path_batch):parent, filename os.path.split(img_path)save_name os.path.join(output, filename)# Save imagecv2.imwrite(save_name, batch_image_raw[i])print(input-{}, time-{:.2f}ms, saving into output/.format(image_path_batch, use_time * 1000))def warmup(yolov5_wrapper):batch_image_raw, use_time yolov5_wrapper.infer(yolov5_wrapper.get_raw_image_zeros())print(warm_up-{}, time-{:.2f}ms.format(batch_image_raw[0].shape, use_time * 1000))if __name__ __main__:engine_file_path rD:\personal\workplace\python_code\ultralytics-main\yolov8s_p.engine# load coco labelscategories [person, bicycle, car, motorcycle, airplane, bus, train, truck, boat, traffic light, fire hydrant, stop sign, parking meter, bench, bird, cat, dog, horse, sheep, cow, elephant, bear, zebra, giraffe, backpack, umbrella, handbag, tie, suitcase, frisbee, skis, snowboard, sports ball, kite, baseball bat, baseball glove, skateboard, surfboard, tennis racket, bottle, wine glass, cup, fork, knife, spoon, bowl, banana, apple, sandwich, orange, broccoli, carrot, hot dog, pizza, donut, cake, chair, couch, potted plant, bed, dining table, toilet, tv, laptop, mouse, remote, keyboard, cell phone, microwave, oven, toaster, sink, refrigerator, book, clock, vase, scissors, teddy bear, hair drier, toothbrush ]# engine_file_path rC:\Users\caobin\Desktop\model_version\yolov8\20230602\best.engine# categories [man]if os.path.exists(output/):shutil.rmtree(output/)os.makedirs(output/)# a YoLov5TRT instanceyolov8_wrapper YoLov8TRT(engine_file_path)try:print(batch size is, yolov8_wrapper.batch_size)image_dir rD:\personal\workplace\python_code\yolov5-6.0\data\imagesimage_path_batches get_img_path_batches(yolov8_wrapper.batch_size, image_dir)for i in range(10):warmup(yolov8_wrapper)for batch in image_path_batches:img_infer(yolov8_wrapper, batch)finally:yolov8_wrapper.destroy()
