摘要:
PyTorch provides 2 kinds of Softmax class. The one is applying softmax along a certain dimension. The other is do softmax on a spatial matrix sized in 阅读全文
摘要:
1. requires_grad = False Set all parameters in the current model frozen: Filter some specific layers by name to be frozen: 2. Filter out unfrozen para 阅读全文
摘要:
Sigmoid Sigmoids saturate and kill gradients. Sigmoid outputs are not zero-centered. Exponential function is a little computational expensive. Tanh Ki 阅读全文
摘要:
Linear Classifier and Hing Loss (or Multiclass SVM Loss) Linear Mapping (Score function) Linear Classifier Hinge Loss Regularization Softmax Classifie 阅读全文