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?
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?
![b2f59929-5885-4b8f-9d0f-3878553b87ed](https://user-images.githubusercontent.com/34619524/42922973-c2e67e8a-8b55-11e8-8983-2a7afa9ef774.png)