Jason

RuntimeError: set_storage is not allowed on a Tensor created from .data or .detach().

4

```python weight_hh_data = torch.eye(self.hidden_size) weight_hh_data = weight_hh_data.repeat(1, 3) self.weight_hh.data.set_(weight_hh_data) alpha_weight_hh_data = torch.eye(self.hidden_size) alpha_weight_hh_data = alpha_weight_hh_data.repeat(1, 1) self.alpha_weight_hh.data.set_(alpha_weight_hh_data) ``` > model\latticelstm.py", line 107, in reset_parameters > self.weight_hh.data.set_(weight_hh_data) > RuntimeError: set_storage is...

```python i, o, g = torch.split(wh_b + wi, split_size_or_sections=self.hidden_size, dim=1) i = torch.sigmoid(i) g = torch.tanh(g) o = torch.sigmoid(o) c_num = len(c_input) if c_num == 0: f = 1 -...

难度列DD可以把红黄绿颜色表示在Title列的文本上，F列希望有开关可以关闭（大多人没有力扣vip），这样可以节省屏幕空间。 

你好，有没有考虑加入自定义快捷键的功能，在系统设置里自己修改那种

Tutorial1 - BiLSTMPOSTagger，don't have pack pad？

3

For varying-length sequences，Why don't have pack pad？ ```python def forward(self, text): embedded = self.dropout(self.embedding(text)) outputs, (hidden, cell) = self.lstm(embedded) predictions = self.fc(self.dropout(outputs)) return predictions ```

Tutorial 4: Decoder - the calculation of prediction

2

Why use `torch.cat((output, weighted, embedded), dim=1)`？ Usually，Isn't just using the `output` enough？ ```python embedded = embedded.squeeze(0) output = output.squeeze(0) weighted = weighted.squeeze(0) prediction = self.fc_out(torch.cat((output, weighted, embedded), dim=1)) ```

ModuleNotFoundError: No module named 'pyexpat'

3

vse_windows_GPU.7z

Why add `torch.log` here？ https://github.com/jadore801120/attention-is-all-you-need-pytorch/blob/132907dd272e2cc92e3c10e6c4e783a87ff8893d/transformer/Translator.py#L53

刷新之后各种设定和输入都消失了

such as, shortcuts for "Add file"