mmfewshot
mmfewshot copied to clipboard
test query set would have some samples from test support set
I reload your model from metafile.yml and want to test the performance of MMfewshot in my dataset. I found that when I input dataset with different numbers of images like 50, 100 ,200 ,400 , the more images I input , the less acc I got. And I found that datawraper would load same images into support set and query set . The less images I input ,the higher acc is. There is my result.
model=meta-baseline | ||||||||
---|---|---|---|---|---|---|---|---|
800 eposide | ||||||||
num querys 15 | ||||||||
5 way 5shot | 5 way 10shot | 5 way 15shot | 5 way 20shot | |||||
input_pics | acc | acc std | acc | acc std | acc | acc std | acc | acc std |
50 | 69.7 | 0.46 | 75.91 | 0.43 | 78.05 | 0.4 | 79.6 | 0.36 |
100 | 63.77 | 0.47 | 69.33 | 0.41 | 71.22 | 0.38 | 72.4 | 0.36 |
200 | 60.63 | 0.43 | 66.48 | 0.41 | 68.59 | 0.4 | 70.24 | 0.4 |
400 | 59.76 | 0.43 | 65.44 | 0.4 | 67.5 | 0.38 | 68.93 | 0.38 |
The model will replace the classifier head and finetune it with N-way K-shot setting while testing. 1 eposide = 5way*(5support+15querys)=100pictures for your setting 5shot/10shot/15shot/20shot, the number of picture is not enough