search

yu4u / age-gender-estimation

Keras implementation of a CNN network for age and gender estimation
MIT License
1.46k stars 502 forks source link

why dot ages arange(0, 101) rather than max in predict #146

Open qiujunhan opened 2 years ago

qiujunhan commented 2 years ago

ages = np.arange(0, 101).reshape(101, 1) predicted_ages = results[1].dot(ages).flatten()

why 100 age have more big weights to calculate,hope to get answers,think you.

yu4u commented 2 years ago

By definition of expected value