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

本站现有博文340篇,共被浏览1012485次

本站已经建立2716天!

热门文章
文章归档
回到顶部