Littlely

when I write down math, it can not export math correctly .I write$$\sum_{i=1}^n$$, it shows "Σi=1nΣi=1n" in PDF, but it work well in HTML. @dbelyaev

I write this `$$\sum_{i=1}^{n}=t$$`, but it doesn't work, what should I do? Thanks.

you mean this $$\sum\_{i=1}^n$$, right? it doesn't work, it shows "Σi=1nΣi=1n" in PDF. @snnn .( I add a backlash, it doesn't show here.)

> Would be easier to address if you could post a runnable code snippet. Would you be able to post such snippet? ``` conf = SparkConf().setAppName("test") spark = SparkSession.builder.config(conf=conf).enableHiveSupport().getOrCreate() spark.conf.set(SparkDatasetConverter.PARENT_CACHE_DIR_URL_CONF,...

吴老师，在9.1.6节HTTP身份验证的地方，我输入代码但是出现Basic authentication cancelled.并没有预想的页面出现，我又用qq空间试了一下，最后出来的只是qq空间进入页面的源代码，这是怎么回事。

我的做法和书上的一样，只是url改成了我登录的qq界面，userpwd改成了我的qq账号和密码。 @coderLMN

谢谢，我会试一试的

@sgwhat Code: ``` def model_creator(config): deep_cross = DeepCross(user_num=config["uid_num"], item_num=config["item_num"], user_item_dim=16, sparse_num=config["sparse_num"], feature_embed_dim=16, embed_norm=0.001, dnn_hidden_units=[int(e) for e in [128, 64, 32]], dnn_activation="relu", dnn_dropout=0.2, cross_num=4) loss = tf.keras.losses.BinaryCrossentropy() optimizer = tf.keras.optimizers.Adam() deep_cross.compile(optimizer=optimizer,...

the DeepCross model is a user defined subclassed model, in tf2, it cannot save as h5 file.

> > the DeepCross model is a user defined subclassed model, in tf2, it cannot save as h5 file. > > Does there any arguments in `__init__` of `DeepCross`？ Yes,...