Closed YuaCC closed 3 years ago
I run the code with python train.py --train-data cub --test-data cub --backbone conv4 --num-shots 1 --train-tasks 50000 --semantic-type class_attributes --num-workers 0 --download
python train.py --train-data cub --test-data cub --backbone conv4 --num-shots 1 --train-tasks 50000 --semantic-type class_attributes --num-workers 0 --download
and get the results:
./cub_cub_protonet_agam_conv4_2021-02-24-00-09-46 test_acc,71.08; 0.28 best_i_task,48000 best_train_acc,0.8233333826065063 best_train_loss,1.2430473566055298 best_val_acc,0.6532889052232107 best_val_loss,1.770083642800649
It differs from the result from paper 75.87;0.29 Would it be useful to run it multiple times?
@YuaCC I think running it multiple times does help. The random seed is quite important in few-shot learning experiments as it also determines the sampling training and testing episodes.
I run the code with
python train.py --train-data cub --test-data cub --backbone conv4 --num-shots 1 --train-tasks 50000 --semantic-type class_attributes --num-workers 0 --download
and get the results:
It differs from the result from paper 75.87;0.29 Would it be useful to run it multiple times?