lih
lih
线性回归的例子也出现了这个问题，在第三张Tensor画图部分 ```python if ii%50 ==0: # 画图 display.clear_output(wait=True) x = t.arange(0, 6).view(-1, 1) # 此处我改为 x = t.arange(0, 6).view(-1, 1).float() y = x.mm(w) + b.expand_as(x) plt.plot(x.cpu().numpy(), y.cpu().numpy()) # predicted x2,...
> Following the naming format of **deeplab_davis_12_0.pth**, I pre-trained deeplabv3 only on davis16 dataset.(with batch_size=8, learning_rate=0.001, maxEpoches=120, weight_decay=0.0005) And I got J=72.05% on davis16 test set. Then I initialized the...
> em... Hi @smallcorgi > I have been confused about a question. > In your code，you didn't use the constrains:There are at least one 3D points in the four border...
@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]) cudnn.benchmark = True net = net.cuda() ``` Then...
@HuiZeng @lld533 Helllo, I just use CPU for inference:), because the pre-trained model is perfect. I am designing an intelligent cropping project based on your model and method. The purpose...