Hi, I've found that # of stride in 5th MBconv block layer of the backbone (efficient net) is set to 2 ('r3_k5_s22_e6_i80_o112_se0.25'), which are different from the official Tensorflow implementation. ('r3_k5_s11_e6_i80_o112_se0.25') This might affect halving the resolution of the output of that layer, but seems should be kept to the same (paper, Table 1). Is it intended behavior?
Hi, I've found that # of stride in 5th MBconv block layer of the backbone (efficient net) is set to 2 ('r3_k5_s22_e6_i80_o112_se0.25'), which are different from the official Tensorflow implementation. ('r3_k5_s11_e6_i80_o112_se0.25') This might affect halving the resolution of the output of that layer, but seems should be kept to the same (paper, Table 1). Is it intended behavior?