Wentao Chao

Motivation: Verify the effect of the bottom-up model(such as higherhrnet) on the AIC dataset. I have tried it, but the result is not good. mAP only 0.2. So please help...

将strict的值设为False即可 ``` def _resnet(arch, block, layers, pretrained, progress, **kwargs): model = ResNet(block, layers, **kwargs)#自己定义的model if pretrained: state_dict = load_state_dict_from_url(model_urls[arch], progress=progress)#预训练的model model.load_state_dict(state_dict, strict=False) """如果是加载本地下载好的预训练模型，就用torch.load()，再把strict设为False model.load_state_dict(torch.load("./resnet50-19c8e357.pth"),strict=False) """ return model ```

@sysuzgg @tfederico hello, I also meet the same question. Please tell me your solution. Thank you very much. =_=

@sysuzgg 谢谢啊，我的显卡是2080ti，直接使用conda安装的cuda，cudnn。 ``` conda install pytorch==1.7.1 torchvision==0.8.2 torchaudio==0.7.2 cudatoolkit=10.1 -c pytorch ``` 按照上述命令进行安装的，不知道为啥就报错了……

@sysuzgg 你说的有道理，那个机器上面没安装cuda，我直接用conda安装的cuda，然后就出现了这个问题。可能我需要先安装好cuda和cudnn，然后再使用pip安装。

> It requires python2.7 but pickle needs python3!!! > This does work > dd = pickle.load(f, encoding="latin-1") > => dd = pickle.load(f) > > File "/usr/lib/python2.7/runpy.py", line 174, in _run_module_as_main...

> I'm talking to the company about whether it's okay to release a pre-trained model. > Please wait a little. Sorry. I train the model in my own dataset. The...

Thanks a lot. I am your students from cs231n camp. Thanks again.

I reconfigured the environment again, the result is still the original problem. I guess it may be a problem with the windows system, then I will try it under the...