Light--

same question here. how to simplfy the code to avoid manually compute the arcface gradient (grad and x_grad) in partial_fc.py ？@anxiangsir

also meet this problem, how to solve this? Does cuda 10.1 + boost 1.66 not ok?

same problem. ang solution?

> does your model output a list? i also meet this problem and yes, my model output a list could you help me? @szagoruyko ``` class Backbone(Module): def __init__(self, num_layers,...

@chesharma > vis_graph = make_dot((y[0], y[1], y[2]), params=dict(list(self.model.named_parameters()) )) Genius bro! 👍 👍 👍 How did you notice this problem and figure it out ? ``` # the output of...

you can refer to [this](https://github.com/deepinsight/insightface/blob/3ed11eb2bcf253d46accde1a56739a4f54624e8f/recognition/image_iter.py#L43)

> 然后深拷贝的话，可以试下 `copy.deepcopy` copy.deepcopy不行。。拷贝不了