[{"createTime":1735734952000,"id":1,"img":"hwy_ms_500_252.jpeg","link":"https://activity.huaweicloud.com/cps.html?fromacct=261f35b6-af54-4511-a2ca-910fa15905d1&utm_source=V1g3MDY4NTY=&utm_medium=cps&utm_campaign=201905","name":"华为云秒杀","status":9,"txt":"华为云38元秒杀","type":1,"updateTime":1735747411000,"userId":3},{"createTime":1736173885000,"id":2,"img":"txy_480_300.png","link":"https://cloud.tencent.com/act/cps/redirect?redirect=1077&cps_key=edb15096bfff75effaaa8c8bb66138bd&from=console","name":"腾讯云秒杀","status":9,"txt":"腾讯云限量秒杀","type":1,"updateTime":1736173885000,"userId":3},{"createTime":1736177492000,"id":3,"img":"aly_251_140.png","link":"https://www.aliyun.com/minisite/goods?userCode=pwp8kmv3","memo":"","name":"阿里云","status":9,"txt":"阿里云2折起","type":1,"updateTime":1736177492000,"userId":3},{"createTime":1735660800000,"id":4,"img":"vultr_560_300.png","link":"https://www.vultr.com/?ref=9603742-8H","name":"Vultr","status":9,"txt":"Vultr送$100","type":1,"updateTime":1735660800000,"userId":3},{"createTime":1735660800000,"id":5,"img":"jdy_663_320.jpg","link":"https://3.cn/2ay1-e5t","name":"京东云","status":9,"txt":"京东云特惠专区","type":1,"updateTime":1735660800000,"userId":3},{"createTime":1735660800000,"id":6,"img":"new_ads.png","link":"https://www.iodraw.com/ads","name":"发布广告","status":9,"txt":"发布广告","type":1,"updateTime":1735660800000,"userId":3},{"createTime":1735660800000,"id":7,"img":"yun_910_50.png","link":"https://activity.huaweicloud.com/discount_area_v5/index.html?fromacct=261f35b6-af54-4511-a2ca-910fa15905d1&utm_source=aXhpYW95YW5nOA===&utm_medium=cps&utm_campaign=201905","name":"底部","status":9,"txt":"高性能云服务器2折起","type":2,"updateTime":1735660800000,"userId":3}]
<>模型的加载
import torchvision.models as models resnet34 = models.resnet34() resnet34.
load_state_dict(torch.load('latest.pth')['model'])
<>要解决的疑问
* load_state_dict torch.load作用
网络结构有了 这部分是在加载参数
* dummy input作用
给网络一个输入
* 如果dynamic_axes 后面输入可以更改指定的维度
* binding inputname outputname作用
binding 每个engine有且只有两个binding，对应输入输出
name可以理解为指针，在转onnx时候就指定根据这个指针拿到输入输出的内容 dummy_input=torch.randn(BATCH_SIZE, 3,
224, 224) import torch.onnx torch.onnx.export(resnet34, dummy_input,
"rp_rec.onnx", verbose=False)
<>注意
torchvision和mmcls的Resnet模型不一样
resnet34 = models.resnet34() resnet34.load_state_dict(torch.load('latest.pth')[
'model'])
模型必须和参数对应起来
不能用torchvision的模型加载mmcls的参数
<>Pytorch转TensorRT方法总结
采用mmclassification框架，根据网络推理时的输入指定网络输入dummy_input，看推理代码，如果网络允许某个维度有变化，那么可以设定dynamic_axes（某个维度定死了，就不要dynamic_axes），采用verify参数，对比模型的输出是否一致
步骤：在服务器上完成trt到onnx转换（configs等等不好往板卡放）
然后将deployment复制到板卡上，执行转trt代码
