deep_learning
deep_learning copied to clipboard
nosuggest
基础的深度学习实验研究结果汇总笔记
Bumps [requests](https://github.com/psf/requests) from 2.22.0 to 2.31.0. Release notes Sourced from requests's releases. v2.31.0 2.31.0 (2023-05-22) Security Versions of Requests between v2.3.0 and v2.30.0 are vulnerable to potential forwarding of Proxy-Authorization...
![dependabot[bot] avatar](https://avatars.githubusercontent.com/in/29110?v=4 "dependabot[bot] avatar"){kind=avatar}
Bumps [tensorflow](https://github.com/tensorflow/tensorflow) from 1.14.0 to 2.11.1. Release notes Sourced from tensorflow's releases. TensorFlow 2.11.1 Release 2.11.1 Note: TensorFlow 2.10 was the last TensorFlow release that supported GPU on native-Windows. Starting...
Bumps [numpy](https://github.com/numpy/numpy) from 1.17.3 to 1.22.0. Release notes Sourced from numpy's releases. v1.22.0 NumPy 1.22.0 Release Notes NumPy 1.22.0 is a big release featuring the work of 153 contributors spread...
hi,dear 大佬 这是我的一些浅显的问题， 请指点下，多谢 1.能不能提供下[数据集](https://github.com/sladesha/deep_learning/blob/master/YoutubeNetwork/normal_version/data_make/map_item_idx.py#L4)？ 2.[这里面](https://github.com/sladesha/deep_learning/blob/master/YoutubeNetwork/normal_version/data_make/map_item_idx.py#L6)的 `data.columns = ['UId', 'ItemId', 'BrandId', 'MiddlesortId', 'ClickTime', 'Date']` middlesortId是啥？Date呢？ 3.[负采样](https://github.com/sladesha/deep_learning/blob/master/YoutubeNetwork/normal_version/model/model.py#L24)是怎么做的啊？ `self.sub_sample = tf.placeholder(tf.int32, [None, None]) # soft layer (pos_clict,neg_list)[B,sub_size]` 4.y是什么呢？怎么是2维的呢？是one-hot之前的吧？[link](https://github.com/sladesha/deep_learning/blob/master/YoutubeNetwork/normal_version/model/model.py#L25) `self.y = tf.placeholder(tf.float32, [None,...
https://github.com/sladesha/deep_learning/blob/master/YoutubeNetwork/normal_version/model/model.py self.loss = tf.reduce_mean(-self.y * tf.log(self.yhat + 1e-24)) 这边 y 的值好像是 1/0 ,这个loss是不是有问题
how to explain your rnn code, why use alpha? i think there dosnot need alpha operation, use lstm->cnn direct
