5way 5shot experiment of miniImageNet

[sadbb]

Hello, your work is really good. But as i try a 5way 5shot experiment in miniImageNet(transductive method), the result of my experiment could not achieve 76.37% as you reported. I did this experiment just with the code 'python3 trainer.py --dataset mini --num_ways 5 --num_shots 5 --trainsductive True' in readme. Since i don't have a file named 'trainer.py', so i changed 'trainer.py' to 'train.py'. Were you having some other adjustments when doing experiments? Thank you very much!

[jmkim0309]

Hi, I'm so sorry, there were some typos in README file. trainer.py --> train.py trainsductive --> transductive Because of the second typo, 'transductive' argument is just set with default value 'False', ignoring your command '--trainsductive True'. Therefore, the obtained result is actually the non-transductive result. I have just fixed them, so please try again with the command in updated README. 'python3 train.py --dataset mini --num_ways 5 --num_shots 5 --transductive True' should work.