baidu-research/dt-ram

dt-ram's Issues

Question on Table 8 and Table 9

Hi, thanks for your great paper on dynamic inference, especially plenty of experiments.
I have one question on Table 8 and Table 9
the second row of Table 8(w. C.L.) and Table9(w. I.S.)
have the same error for each step
Is this because both curriculum learning and intermediate supervision has similar function?
Did you combine these two method together and test the result
under the similar experiment setting?

Thanks in advance

FGVC accuracy

请问在FGVC Aircraft数据集上可以达到多高的准确率呢?

Issue about the paper on arxiv

Sorry, I found that it is the Browser Error.

Resnet50 CUB 2011 performance

Hi,
I am looking for the best performance on CUB 2011 and i find that you've got the 84.5% accuracy with resnet50. You mentioned that you've done fine-tuning very carefully and got this result.

I also try to reproduce this performance with resnet50 on Pytorch framework. but doesn't work.

Here is my setting and let me know what kind of setting did you use. there is large difference you've got.
Training argumentation:
Image rescale size: 448 (keep aspect ratio)
image random crop(448 size)
random Hflip
normalization

batch size 16
initial lr: 1e-3
lr decay(*0.1) at 30, 60 epoch

Test argumentation
Image rescale size: 448 (keep aspect ratio)
image center crop(448 size)
normalization

I employ pretrained resnet50 from imagenet that provided by Pytorch community.
So far, i got about 83% accuracy on resnet152. with resnet50, still less than 80%