Liu Zhihui

我有点不太明白你说的啥意思。你说的single task是指self.adv=False时的情况吗？

I pad sentences to fixed length manually. Of course you can use tf.data API to automaticlly pad zeros.

i ignored the two dataset because of encoding problem. i thought the data was broken.

` pad_id = -1` and `word_embed[pad_id] = np.zeros([word_dim])` is unnecessary. `PAD_WORD` is in `vocab` and not in `pretrain_words2id`, its vector will be random initialized ``` for w in vocab: if...

@marvelousgirl cnn just encode a sentence to a vector. you can try to use lstm.

@marvelousgirl 我在`read_tfrecord`里用的是`dataset.make_one_shot_iterator`，只能使用一次，如果想要测试多次的话，就要使用`dataset.repeat`；`dataset.repeat`不是复制，只是个循环次数。

@marvelousgirl 1. 可以去掉 2. 你可以对卷积核正则化看看效果，是否加正则化是调参调出来的

@marvelousgirl 你测一下结果对不对不就行了

the classification loss is decreased but the adv loss is increased

`java -jar SparrowRecSys-1.0-SNAPSHOT-jar-with-dependencies.jar ` log4j:WARN No appenders could be found for logger (org.eclipse.jetty.util.log). log4j:WARN Please initialize the log4j system properly. log4j:WARN See http://logging.apache.org/log4j/1.2/faq.html#noconfig for more info. webRootLocation: jar:file:/mnt/e/work/SparrowRecSys/target/SparrowRecSys-1.0-SNAPSHOT-jar-with-dependencies.jar!/webroot/ Web Root...