guixianjin97

Hi! Recently, I try to adapt this code for Clothing1M dataset and I carefully check its data augmentation. It seems that if you use official pytorch augmentation function, these lines...

I'm confusing with 'Best accu'. Assuming we have a validation set and a separate test data set, does 'Best accu' not mean the accuracy in test data set of the...

Hi! @tc64 @rosefun @giorgiop I think it may be because y_pred shape is N(batch_size) * C(class_num). That is y_pred = [f(x1)^T;f(x2)^T;...] where f(x1) ( a column vector) is the classifier's...

> 这个问题主要是因为core文件中不能用list 方式创建layer，你将其改为字典，而且字典的key必须为字符串 修改deepctr/layers/core.py self.activation_layers={} for i in range(len(self.hidden_units)): self.activation_layers[str(i)]=activation_layer(self.activation) # self.activation_layers = [activation_layer(self.activation) for _ in range(len(self.hidden_units))] # print("activation num:", len(self.activation_layers)) if self.output_activation: # self.activation_layers[-1] = activation_layer(self.output_activation) self.activation_layers[str(len(self.hidden_units)-1)] =...