Wrong calculation in pooling layer. < pooling3x3s2_max >

[Alan-Turing-Ko]

Function: pooling3x3s2_max ( arm/impl/pooling_arm_impl.cpp ) Layer Definition: layer { name: "Pooling1" type: "Pooling" bottom: "Convolution3" top: "Pooling1" pooling_param { pool: MAX kernel_size: 3 stride: 2 } } Input dim: 1, 64, 61, 61 Output dim: 1, 64, 30, 30 Input Values: <0, 0>:0.072792 ... <1, 57>: 0.021526 <1, 58>: 0.021526 <1, 59>: 0.021526 <1, 60>: 0.041485

Output Values: <0, 27>:0.021526 <0, 28>:0.021526 <0, 29>:0.021526 <1, 0>: 0.072792

I think Output<0, 29> must be 0.041485. Please check and fix bug asap.

[xyoungli]

thanks for your issues, we will check it soon