senlin-ali

大佬好、请教下 你写的flask web界面代码方便分享一下吗，我只看到了soutu这个、好像跟你使用的这个特征不太一样、这个使用的界面代码方便分享一下吗

e-packages/ttach/functional.py", line 7, in rot90 return torch.rot90(x, k, (2, 3)) RuntimeError: Rotation dim0 out of range, dim0 = 2

TypeError: buffer is too small for requested array

4

Layer of type maxpool not supported, skipping ONNX node generation. Layer of type maxpool not supported, skipping ONNX node generation. Layer of type maxpool not supported, skipping ONNX node generation....

hi, i have a question about the code

4

hi, i see the test.ipynb ,the cls model is no use in the ipynb; and i do not know if it is just train GAN model first(use outlier data and...

can you share your training code？thanku very much

How can i use Generative frame interpolation demo

1

Great work! i want to know if we can use Generative frame interpolation demo

why the training loss is nan?

3

hi , i have a question about training. when i train my own data, the loss begins 1.0 to 0.8... and then the loss is nan, how can i solve...

raise AttributeError("'{}' object has no attribute '{}'".format( AttributeError: 'Block' object has no attribute 'drop_path'

2

raise AttributeError("'{}' object has no attribute '{}'".format( AttributeError: 'Block' object has no attribute 'drop_path'