Research Article
Analysis of Behavioral Image Recognition of Pan-Entertainment of Contemporary College Students’ Network
Table 1
Improved network structure based on R(2 + 1)D-34/R(2 + 1)D-50.
| Number of layers | Output size | R (2 + 1) D-34 | R (2 + 1) D-50 |
| Conv1_x | λ × 14 × 14 | × 6 | × 6 | Conv2_x | λ/2 × 7 × 7 | × 3 | × 3 | | 1 × 1 × 1 | Spatiotemporal pooling, fc layer with softmax |
|
|