Research Article
Exploiting the Relationship between Pruning Ratio and Compression Effect for Neural Network Model Based on TensorFlow
Table 7
Descriptions of parameters of the pruning effect in the fourth scene.
| ā | Original number of parameters | Threshold value | Valid parameter number |
| w_conv1 | 800 | 0.0 | 800 | w_conv2 | 51,200 | 0.0 | 51,200 | w_fc1 | 3,211,264 | 0.09749276 | 963,379 | w_fc2 | 10,240 | 0.10360378 | 3,071 |
|
|