search

brightmart / text_classification

all kinds of text classification models and more with deep learning
MIT License
7.83k stars 2.57k forks source link

Questions about hierarchical attention network #72

Closed yangdelu855 closed 6 years ago

yangdelu855 commented 6 years ago

In your previous test function, given 10 samples with same content(all zeros) but different labels in a batch, we train the model for several times, the acc can arrive 100%. I just wonder, how the model tells the docs with all zeros from each other, and predict different labels for them?Is there anything wrong? ca14c201-2aca-45be-9db8-dcb7ac95b022 b2f59929-5885-4b8f-9d0f-3878553b87ed

brightmart commented 6 years ago

hi. for the same input(x), the label(y) should be same. so you've better come up a new toy task if you like.