Graviton

Dropout

1

if we set `self.dropout=True`, the probability of an element to be zeroed is one. then all elements of output tenor is zero. I get confused about it ```python class GAT(nn.Module):...

imformation about malignancy

1

Hi juliandewit.After runing "step3_predict_nodules.py",I get nothing about malignancy.In my generated .csv file,there is only coord_x,coord_y,diameter,nodule_chance and diameter_mm.but I notice that These few lines of code in your model: out_class =...

data exchangeably

2

@yromano In conformal prediction, the regression algorithm must treat the data exchangeably. I want to know whether CQR must treat the data exchangeably.

cannot import name 'VariableSaver'

10

@NiuChH @korepwx @TsingHuasuya @haowen-xu 我下载了stable版本的tfsnippet，但是在运行如下代码时， ```python from tfsnippet.scaffold import VariableSaver ``` 报错 > from tfsnippet.scaffold import VariableSaver ImportError: cannot import name 'VariableSaver'

the value of loss is negtive

1

I found the value of loss became negtive when training the model in my dataset.I hope you can give me a help

损失问题

1

大佬，您好我将您的模型用于voc数据集训练时，发现后两个损失值一直在上升，即detectior_cls和detectior_regr,最近做毕设用到这个模型，希望您能百忙之中尽快回复 1/2000 [..............................] - ETA: 11:45:41 - rpn_cls: 0.9137 - rpn_regr: 2.7919 - detector_cls: 0.1544 - detector_regr: 0.2115 2/2000 [..............................] - ETA: 7:20:18 - rpn_cls: 1.0191 - rpn_regr: 2.2316 -...