fmscole
fmscole
我还是认为, pooling.py的79行,应该对self.index有一个清零的步骤,self.index = np.zeros(self.input_shape) 即: forward(self, x): out = np.zeros([x.shape[0], x.shape[1] / self.stride, x.shape[2] / self.stride, self.output_channels]) self.index = np.zeros(self.input_shape) for b in range(x.shape[0]): ............................ 供讨论
policy.py第110行: for name, thing in locals().items(): 应该改为: for name, thing in list(locals().items()): 否则会出现异常RuntimeError: dictionary changed size during iteration
test,but can't convergence to target: --- when: y_list = [-0.8333333333, 0.33333, 0.166666667, -0.8] result: iter 9999: y_pred = [-0.76083, -0.00007, -0.00007, -0.79996], loss: 1.442e-01 ## I add a linare layer...
version 0.33 code : ``` using System; using System.IO; using System.Security.Cryptography; using System.Text; using SharpCompress.Archives; using SharpCompress.Archives.Rar; using SharpCompress.Factories; using SharpCompress.Readers; namespace RarMD5Calculator { class Program { static void Main(string[]...
尽管不涉及错误,也不影响什么, 双重循环看起来还是很不舒服,毕竟0(1)的问题变成了0(n^2)的问题了,做如下修改比较好: def click1(self, event): #click1 because keyword repetition size = self.board.width current_player = self.board.get_current_player() if current_player == 1: # for i in range(size): # for j in range(size): i=(event.x)//30...
I want to open a word document and copy to another document,how to do it?