Model blending using only 1_F is better than using all three networks in level1.

[mariolew]

trafficstars

When I test level1, I found that using 1_F only is better than using 1_F + 1_EN + 1_NM. By the way, the loss of 1_EN and 1_NM is also pretty low. If I use 1_F only for the first level, I got reasonable good result from level3... I just can't understand why 1_F only would be better than blending of three networks.

[luoyetx]

Yes, I found this problem too :(

So, I didn't train model 1_EN and 1_NM. Maybe the processing part of 1_EN or 1_NM are not good or still need some training trick to train these two model well.