Lida Li

> Hello, your work is very good. How to solve this problem? Do you need to add this function trilinear_func.py? Can you update this function to your code in the...

> Could you provide the weights saved along with the architecture? I am trying to convert the model file to tensorflow but cant without the architecture saved along with the...

> When I installed the roi and rod.I met some error.Just like this. > `error: command 'D:\\application\\visual_studio\\VC\\Tools\\MSVC\\14.10.25017\\bin\\HostX64\\x64\\cl.exe' failed with exit status 2` > > Did anybody met this problem?Thank u...

> I run test with both PyTorch 1.2 and PyTorch 0.4.1 version, some top1 cropping results are different > > For examples > image number: 220865 > PyTorch 0.4.1: >...

> @HuiZeng > > When run `demo_eval.py`, is `nn.Dataparallel` necessary? > I commented out some code as fellows: > > ```python > if args.cuda: > # net = torch.nn.DataParallel(net, device_ids=[0])...

> I am unable to use mobilenetv2_0.5 mobilenetv2_0.75 and mobilentv2_1.0 pretrained weights.....I get an error in demo_eval.py in line 63 i.e. in load_state_dict Well noted. I'll check and reply you...

Sorry for my late reply. Could you please share more details when you failed to load the pretrained weights? Did you specify the right path? Many thanks!

> @lld533 ask for help！！ > I cannot use the demo_eval.py to make some test Thanks for your question. There are a few things that I'm not sure. 1/ It...

> > > @lld533 ask for help！！ > > > I cannot use the demo_eval.py to make some test > > > Thanks for your question. > > > There...

@duchengyao I'm new to linux and I'm facing the same problem. How did you change the symbolic links? Could you please add some details? Much thanks.