kevinzakka / recurrent-visual-attention

A PyTorch Implementation of "Recurrent Models of Visual Attention"
MIT License
468 stars 123 forks source link

accuracy calculation bit confusing #38

Open chatgptcoderhere opened 3 years ago

chatgptcoderhere commented 3 years ago

How do you calculate the final accuracy? If you have 8 steps with one glimpse, do you only consider last step as final prediction for accuracy calculations or do you average predictions from all steps given each step can have different predictions?

lizhenstat commented 3 years ago

@DeccanKing1 Hi, In section 3.1, the reward is defined as follows: In the case of object recognition, for example, rT = 1 if the object is classified correctly after T steps and 0 otherwise.