EADST

YOLOv5: Infer the Image with ONNX

YOLOv5: Infer the Image with ONNX

Convert to the onnx model from our well-trained pt model

python export.py --weights ./runs/train/exp/best.pt --include onnx

Infer the image with the onnx model

import os
import cv2
import numpy as np
import onnxruntime
import time

CLASSES=["b", "t"]

class YOLOV5(): def init(self,onnxpath): self.onnx_session=onnxruntime.InferenceSession(onnxpath) self.input_name=self.get_input_name() self.output_name=self.get_output_name()

def get_input_name(self):
    input_name=[]
    for node in self.onnx_session.get_inputs():
        input_name.append(node.name)
    return input_name

def get_output_name(self):
    output_name=[]
    for node in self.onnx_session.get_outputs():
        output_name.append(node.name)
    return output_name

def get_input_feed(self,img_tensor):
    input_feed={}
    for name in self.input_name:
        input_feed[name]=img_tensor
    return input_feed

def inference(self,img_path):
    img=cv2.imread(img_path)
    or_img=cv2.resize(img,(640,640))
    img=or_img[:,:,::-1].transpose(2,0,1)  #BGR2RGB and HWC2CHW
    img=img.astype(dtype=np.float32)
    img/=255.0
    img=np.expand_dims(img,axis=0)
    input_feed=self.get_input_feed(img)
    pred=self.onnx_session.run(None,input_feed)[0]
    return pred,or_img

def nms(dets, thresh): x1 = dets[:, 0] y1 = dets[:, 1] x2 = dets[:, 2] y2 = dets[:, 3]

areas = (y2 - y1 + 1) * (x2 - x1 + 1)
scores = dets[:, 4]
keep = []
index = scores.argsort()[::-1]

while index.size > 0:
    i = index[0]
    keep.append(i)

    x11 = np.maximum(x1[i], x1[index[1:]]) 
    y11 = np.maximum(y1[i], y1[index[1:]])
    x22 = np.minimum(x2[i], x2[index[1:]])
    y22 = np.minimum(y2[i], y2[index[1:]])

    w = np.maximum(0, x22 - x11 + 1)                              
    h = np.maximum(0, y22 - y11 + 1)

    overlaps = w * h

    ious = overlaps / (areas[i] + areas[index[1:]] - overlaps)
    idx = np.where(ious <= thresh)[0]
    index = index[idx + 1]
return keep

def xywh2xyxy(x): # [x, y, w, h] to [x1, y1, x2, y2] y = np.copy(x) y[:, 0] = x[:, 0] - x[:, 2] / 2 y[:, 1] = x[:, 1] - x[:, 3] / 2 y[:, 2] = x[:, 0] + x[:, 2] / 2 y[:, 3] = x[:, 1] + x[:, 3] / 2 return y

def filter_box(org_box,conf_thres,iou_thres): org_box=np.squeeze(org_box) conf = org_box[..., 4] > conf_thres box = org_box[conf == True]

cls_cinf = box[..., 5:]
cls = []
for i in range(len(cls_cinf)):
    cls.append(int(np.argmax(cls_cinf[i])))
all_cls = list(set(cls))

output = []
for i in range(len(all_cls)):
    curr_cls = all_cls[i]
    curr_cls_box = []
    curr_out_box = []
    for j in range(len(cls)):
        if cls[j] == curr_cls:
            box[j][5] = curr_cls
            curr_cls_box.append(box[j][:6])
    curr_cls_box = np.array(curr_cls_box)
    # curr_cls_box_old = np.copy(curr_cls_box)
    curr_cls_box = xywh2xyxy(curr_cls_box)
    curr_out_box = nms(curr_cls_box,iou_thres)
    for k in curr_out_box:
        output.append(curr_cls_box[k])
output = np.array(output)
return output

def draw(image,box_data):

boxes=box_data[...,:4].astype(np.int32) 
scores=box_data[...,4]
classes=box_data[...,5].astype(np.int32)

for box, score, cl in zip(boxes, scores, classes):
    top, left, right, bottom = box
    print('class: {}, score: {}'.format(CLASSES[cl], score))
    print('box left,top,right,down: [{}, {}, {}, {}]'.format(top, left, right, bottom))

    text_left = left
    text_top = top         
    color = (255, 0, 0)
    if CLASSES[cl] == "b":
        text_left += 50
        text_top -= 20     
        color = (0, 0, 255)
    cv2.rectangle(image, (top, left), (right, bottom), color, 2)
    cv2.putText(image, CLASSES[cl],
                (text_top, text_left),
                cv2.FONT_HERSHEY_SIMPLEX,
                0.6, color, 2)

if name=="main": onnx_path = "best.onnx" model = YOLOV5(onnx_path) img_path = "0_0.jpg" output, img = model.inference(img_path) outbox = filter_box(output,0.5,0.5) draw(img, outbox) cv2.imwrite(img_path[:-4]+"_res.jpg", img)

Reference:

YOLOV5模型转onnx并推理

相关标签
About Me
XD
Goals determine what you are going to be.
Category
标签云
llama.cpp Baidu Tracking Anaconda EXCEL GGML PyCharm ChatGPT Image2Text Food Sklearn Numpy Attention Mixtral 搞笑 算法题 Python Docker FP16 Tiktoken 域名 ResNet-50 公式 个人博客 COCO Qwen RGB Proxy Augmentation Use Logo JSON Plotly logger IndexTTS2 Linux 报税 LoRA LLM Nginx torchinfo 飞书 强化学习 云服务器 Translation Bipartite News Shortcut C++ Video Land FastAPI LaTeX Paddle DeepStream HuggingFace LLAMA Data v0.dev Interview AI Domain Ptyhon Paper transformers scipy git SQLite PDF Disk Claude Google 论文速读 Pillow YOLO TensorRT CC TSV 论文 RAR git-lfs Heatmap Rebuttal ms-swift tar Qwen2.5 Clash Miniforge OCR Search Markdown Input Gemma Conda 长期记忆 mmap CUDA GPT4 Cloudreve Dataset VSCode GPTQ BeautifulSoup NameSilo BF16 GIT Diagram Jetson Safetensors 图标 hf Streamlit CAM ModelScope Firewall 腾讯云 顶会 递归学习法 API网关 uwsgi InvalidArgumentError FlashAttention NLTK Michelin DeepSeek WebCrawler Pandas Pickle Git Password Magnet Animate tqdm CTC 自我改进 Zip Algorithm PDB Base64 PIP Quantization HaggingFace VGG-16 WAN Agent uWSGI Pytorch QWEN Template Color Distillation Web Crawler Plate Excel icon CEIR FP64 Qwen2 Quantize NLP FP8 BTC Django diffusers UI Freesound 财报 Card Bin Hungarian Tensor VPN MD5 Llama Transformers Bitcoin SVR 音频 阿里云 证件照 Vim 关于博主 多线程 SPIE 继承 签证 TensorFlow RL CSV GoogLeNet Vmess Datetime ONNX Statistics PyTorch v2ray Bert Breakpoint Review CLAP 第一性原理 Website XML 多进程 CV SQL Jev printf XGBoost 版权 FP32 API Harness Jupyter 净利润 Math Permission SAM Ubuntu Github Windows Random Knowledge LeetCode UNIX Hilton OpenCV TTS Hotel 图形思考法 OpenAI
站点统计

本站现有博文340篇,共被浏览1017859次

本站已经建立2718天!

热门文章
文章归档
回到顶部