ParkBook

Vertex Shader: ``` cpp "uniform mat4 transform;" "uniform vec2 uv_offset;" "uniform vec2 uv_scale;" "uniform bool octant_mask[8];" "attribute vec3 position;" "attribute float octant;" "attribute vec2 texcoords;" "varying vec2 v_texcoords;" "void main()...

https://github.com/HsiaoYetGun/ESIM/blob/master/Model.py#L169 ``` python attentionSoft_b = tf.nn.softmax(tf.transpose(attentionWeights)) ``` 这里对attentionWeights进行transpose后，生成的张量的形状为 ( seq_length, seq_length, batch_size ) 然后在对上一步的结果进行softmax，tf.nn.softmax默认在最后一个维度作softmax， 那岂不是在batch上作softmax ？求相互指教。

### 帮助页面的链接（Help page URL） [https://help.mirrors.cernet.edu.cn/anaconda/](url) ### 原文 (Text) ``` yaml channels: - defaults show_channel_urls: true default_channels: - https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/main - https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/r - https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/msys2 custom_channels: conda-forge: https://mirrors.tuna.tsinghua.edu.cn/anaconda/cloud pytorch: https://mirrors.tuna.tsinghua.edu.cn/anaconda/cloud ``` ### 反馈和修正...