rk1808 转化pytorch案例

1环境准备

numpy 1.19.2
tensorflow 1.15.0
tensorflow-gpu 1.15.0
rknn 1.6.0
torch 1.3.1

2转换模型

首先转化resent18的网络，具体案例也可以在rknn1.6的案例包中

#import numpy as np
#import cv2
from rknn.api import RKNN
import torchvision.models as models
import torch
net = models.resnet18(pretrained=True)
net.eval()
trace_model = torch.jit.trace(net, torch.Tensor(1,3,224,224))
trace_model.save('./resnet18.pt')

转换resnet-18

打开rk1808可视化转化界面

python3 -m rknn.bin.visualization

生成成功