[Retracted] DTFA-Net: Dynamic and Texture Features Fusion Attention Network for Face Antispoofing

Table 4

The structure of FC2-3 in Figure 5.

Layer	Input size	Output size
FC2_1	256  6  6	256  3  3
FC2_2	256  3  3	256  2  2
FC3_1	256  6	256  3
FC3_2	256  3	256
FC3_3	256	2