官方预训练模型转换

1. 下载yolov5-v6.0分支源码解压到本地，并配置基础运行环境。
2. 下载官方预训练模型

• yolov5n.pt
• yolov5s.pt
• yolov5m.pt
• …

3. 进入yolov5-6.0目录下，新建文件夹weights，并将步骤2中下载的权重文件放进去。
4. 修改models/yolo.py文件

    def forward(self, x):z = []  # inference outputfor i in range(self.nl):x[i] = self.m[i](x[i]).sigmoid()  # conv#     bs, _, ny, nx = x[i].shape  # x(bs,255,20,20) to x(bs,3,20,20,85)#     x[i] = x[i].view(bs, self.na, self.no, ny, nx).permute(0, 1, 3, 4, 2).contiguous()#     if not self.training:  # inference#         if self.grid[i].shape[2:4] != x[i].shape[2:4] or self.onnx_dynamic:#             self.grid[i], self.anchor_grid[i] = self._make_grid(nx, ny, i)#         y = x[i].sigmoid()#         if self.inplace:#             y[..., 0:2] = (y[..., 0:2] * 2. - 0.5 + self.grid[i]) * self.stride[i]  # xy#             y[..., 2:4] = (y[..., 2:4] * 2) ** 2 * self.anchor_grid[i]  # wh#         else:  # for YOLOv5 on AWS Inferentia https://github.com/ultralytics/yolov5/pull/2953#             xy = (y[..., 0:2] * 2. - 0.5 + self.grid[i]) * self.stride[i]  # xy#             wh = (y[..., 2:4] * 2) ** 2 * self.anchor_grid[i]  # wh#             y = torch.cat((xy, wh, y[..., 4:]), -1)#         z.append(y.view(bs, -1, self.no))# return x if self.training else (torch.cat(z, 1), x)return x[0], x[1], x[2]

5. 新建export_rknn.py文件

import os
import torch
import onnx
from onnxsim import simplify
import onnxoptimizer
import argparse
from models.yolo import Detect, Modelif __name__ == '__main__':parser = argparse.ArgumentParser()parser.add_argument('--weights', type=str, default='./weights/yolov5n.pt', help='initial weights path') #================================================================opt = parser.parse_args()print(opt)#Save Only weightsckpt = torch.load(opt.weights, map_location=torch.device('cpu'))torch.save(ckpt['model'].state_dict(), opt.weights.replace(".pt", "-model.pt"))#Load model without postprocessingnew_model = Model("./models/{}.yaml".format(os.path.basename(opt.weights).strip(".pt")))new_model.load_state_dict(torch.load(opt.weights.replace(".pt", "-model.pt"), map_location=torch.device('cpu')), False)new_model.eval()#save to JIT scriptexample = torch.rand(1, 3, 640, 640)traced_script_module = torch.jit.trace(new_model, example)traced_script_module.save(opt.weights.replace(".pt", "-jit.pt"))#save to onnxf = opt.weights.replace(".pt", ".onnx")torch.onnx.export(new_model, example, f, verbose=False, opset_version=12,training=torch.onnx.TrainingMode.EVAL,do_constant_folding=True,input_names=['data'],output_names=['out0','out1','out2'])#onnxsimmodel_simp, check = simplify(f)assert check, "Simplified ONNX model could not be validated"onnx.save(model_simp, opt.weights.replace(".pt", "-sim.onnx"))#optimize onnxpasses = ["extract_constant_to_initializer", "eliminate_unused_initializer"]optimized_model = onnxoptimizer.optimize(model_simp, passes)onnx.checker.check_model(optimized_model)onnx.save(optimized_model, opt.weights.replace(".pt", "-op.onnx"))print('finished exporting onnx')

6. 命令行执行python3 export_rknn.py脚本(默认为yolov5n.pt, 加–weights参数可指定权重)，转换成功会输出一下信息, 转换后的模型存于权重同级目录(*-op.onnx后缀模型)

Namespace(weights='./weights/yolov5n.pt')
finished exporting onnx

RKNN开发板植入-模型转换篇

前期准备

• RKNN开发环境（python）
• rknn-toolkits2

详细流程

1. 进入rknn-toolkits2/examples/onnx/yolov5示例目录下
2. 修改test.py内容（按需修改ONNX_MODEL、RKNN_MODEL、IMG_PATH、DATASET等等超参数）

def sigmoid(x):# return 1 / (1 + np.exp(-x))return x

3. 命令行执行python3 test.py即可获取推理结果
   

RKNN开发板植入-NPU加载推理篇(C++)

后续放出代码