Open alexrakowski opened 5 years ago
I am confused with how many reduction (pooling?) layers a micro model should have. Figure 4 in the paper shows 1 reduction layer per 1 convolutional block, whereas in the code:
MicroChild.__init__(): ... pool_distance = self.num_layers // 3 self.pool_layers = [pool_distance, 2 * pool_distance + 1]
MicroChild.__init__():
...
pool_distance = self.num_layers // 3
self.pool_layers = [pool_distance, 2 * pool_distance + 1]
which would indicate there are always only two such layers. Is that correct? @melodyguan @hyhieu
I am confused with how many reduction (pooling?) layers a micro model should have. Figure 4 in the paper shows 1 reduction layer per 1 convolutional block, whereas in the code:
MicroChild.__init__():...pool_distance = self.num_layers // 3self.pool_layers = [pool_distance, 2 * pool_distance + 1]which would indicate there are always only two such layers. Is that correct? @melodyguan @hyhieu