lucasoskorep/tensordex
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Updates to all parts of model building - moving to frozen transfer learning followed by slowed learning rate fine tuning using EfficientNets for final model.

Browse Source
This commit is contained in:
Lucas
2022-06-03 13:44:34 -04:00
parent 755fcde3a9
commit d111cdae69
13 changed files with 156 additions and 79 deletions
Download Patch File Download Diff File Expand all files Collapse all files
all_model_output.csv
+3
View File
@@ -0,0 +1,3 @@
model,test_acc,test_loss,single_acc,single_loss
./models/keras\pt-fl-fbn-efficientnet_v2b0-d1024-do0.5-l11.e-04-l21.e-04-5224-second_stage.hdf5,0.6720150708068079,1.7423864365349095,0.9893048128342246,0.4364729183409372
./models/keras\pt-fl-fbn-efficientnet_v2b0-d1024-do0.5-l11.e-04-l21.e-04-5224.hdf5,0.410029881772119,3.346152696366266,0.986096256684492,0.3234976000776315
1 model test_acc test_loss single_acc single_loss
2 ./models/keras\pt-fl-fbn-efficientnet_v2b0-d1024-do0.5-l11.e-04-l21.e-04-5224-second_stage.hdf5 0.6720150708068079 1.7423864365349095 0.9893048128342246 0.4364729183409372
3 ./models/keras\pt-fl-fbn-efficientnet_v2b0-d1024-do0.5-l11.e-04-l21.e-04-5224.hdf5 0.410029881772119 3.346152696366266 0.986096256684492 0.3234976000776315