EmperorOfChina comments

Results 8 comments of


                                            EmperorOfChina

Check failed: registry.count(type) == 0 (1 vs. 0) Layer type Convolution already registered

how do you fix it buddy, could you please help me?

TypeError: Expected int32, got list containing Tensors of type '_Message' instead

@gemengsoftware @zhr1201 Please change "SENN.py" line110 from `targets = tf.concat( [tf.reshape(0, speech_f[i][self.N_IN - 1][0:self.NEFF], [1, self.NEFF]) for i in range(0, self.batch_size, 1)])` to `targets = tf.concat( [tf.reshape( speech_f[i][self.N_IN - 1][0:self.NEFF],...

about the training code

@zuie21 1.MatConvNet 2.Refer to DnCNN TrainingCodes 3.Using less layers is not related to overfitting I think. 4.Read the papper 5.feature descriptor? here? are you a 医生吗

inconsistent tensor sizes in"dout8_out7 = torch.cat([dout8, out7], 1)"

Using torch 0.3.1 ![image](https://user-images.githubusercontent.com/5409816/44707596-81f7ee80-aad7-11e8-9e95-e8f833cb3e5e.png)

inconsistent tensor sizes in"dout8_out7 = torch.cat([dout8, out7], 1)"

It seems that input image size must be less than 512??

Layer type Convolution already registered.

解决了吗老哥

TypeError: 'map' object is not subscriptable

I have the same issue,

TypeError: 'map' object is not subscriptable

@YangBain already do that, but it didn't work