克里斯汀娜

hi, I am using this script to generate albert saved model which is capativble with `tf serving` since i genrated model , the input is { "instances":[ {"inputs": ["你好么"]} ]...

I think

2

use `pyspark` to write these alg should be meaningful

has error when using webo

2

check fail: file open pretext file /familia/model/webo/lda.conf

TCNN

1

实际上 Text-cnn在训练的时候 卷积层可以使用 多个 不同尺寸的卷积核 最后拼接到一个中间层上 然后输入多个 dense 可以尝试如下操作 ``` python # 第一卷积层 conv_4_layer = Convolution1D(200, 4, activation='tanh')(embedding) # 第一池化层 max_pool_4_layer = MaxPooling1D(4)(conv_4_layer) # 第一扁平层 flat_4_layer = Flatten()(max_pool_4_layer) # 第二卷积层...

## advise we need to calc steps_per_epoch and specific this value ```python def fit(self, log=False, **kwargs): """kwargs: keyword arguments passed to `model.fit`""" if log: callbacks = [keras.callbacks.TensorBoard( log_dir='./log', histogram_freq=0, write_graph=True,...

为什么没有subsample

2

我记得GBDT里有shrinkage和subsample的过程啊 代码里只有列采样

why ‘我是傻逼’ and '你是傻逼' is postive

3

### this need think sentence length has imapct on classify of sentiment. ### report ``` Using TensorFlow backend. D:\Program Files (x86)\Python\lib\site-packages\gensim\utils.py:862: UserWarning: detected Windows; aliasing chunkize to chunkize_serial warnings.warn("detected Windows;...

**Describe the bug** 获取新文章时没有发送通知 **To Reproduce** Steps to reproduce the behavior: 1. 任意一个 rss，开启自动更新抓取，当有新文章时没有系统级的通知 **Expected behavior** 有系统通知 **Platform (please complete the following information):** - OS: mac os sonoma

i am using this within a flask backend and it works well , but i get base64 encode face image quiet slow. Theres is at least 2s delay. ``` def...

mingGEPhp

2

拳打laravel 脚踢symfony 一把登顶php界第一的宝座，回头一看，thinkphp竟然抄自己 顺手一把黑将其从世界上抹去