paulxin

请问文中代码用的tensorflow版本号是多少呢？

matchzoo.contrib.models.ESIM(), model.save, raise ValueError: substring not found

1

### Describe the bug when I run tutorials.wikiqa.esim.ipynb, in the last run model.save(SAVE_PATH), raise ValueError: substring not found File "D:\ProgramData\Anaconda3\envs\Matchzoo\lib\site-packages\tensorflow_core\python\ops\variables.py", line 1150, in _shared_name return self.name[:self.name.index(":")]

def rssError() 函数说明部分的returns不应该是ws，应该是((yArr - yHatArr)**2).sum()。

Update，W1层的参数时，input = np.sum(batch, axis=0)/batch_size的维度时（3,），这导致input*np.transpose(sig1)的维度是[1,3]而不是[3,3]。更新参数的时候不是按公式来更新。

为什么要用tf训练一个emb？直接用gensim，然后增量训练有什么不同呢？

Why parakeet (transducer model) can't support hotwords?

9

Why parakeet can't support hotwords? I check code in offline-recognizer-transducer-nemo-impl.h `class OfflineRecognizerTransducerNeMoImpl : public OfflineRecognizerImpl { public: explicit OfflineRecognizerTransducerNeMoImpl( const OfflineRecognizerConfig &config) : OfflineRecognizerImpl(config), config_(config), symbol_table_(config_.model_config.tokens), model_(std::make_unique( config_.model_config)) { if...