EnQing626

Results 4 comments of EnQing626

> 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...

> Hi, > > can you try changing the line for the true_1_hot, and adding a cast to int64. > > Like this > > `true_1_hot = torch.eye(num_classes)[true.squeeze(1).to(torch.int64)]` It works...

Just as the @SJWang2015 said, it works for me by his solution. You don't need to modify the "STATICLAPACKLDFLAGS". This variable is used for "deepmatching-static" but not "deepmatching", you need...

Got the same error. Did you solve the problem?