Closed avijit9 closed 5 years ago
Hi @avijit9, One issue I can see is that the schedule should be STEP_SIZES: [40000, 8000] (following linear scaling rule https://arxiv.org/pdf/1706.02677.pdf)
@chaoyuaw Thanks for your prompt reply. I am going to run this experiment now with your suggestion and let you know the outcome.
Btw, thanks for this amazing repo. :)
Of course :) Let me know how it goes. Closing this now, but please feel free to reopen if you see other issues. Thanks!
It worked like charm! Thanks again for your help.
I am a bit confused. What is the difference between I3D and 3D CNN in table 4 of the LFB paper? Both are using R50-I3D-NL. Does 3D CNN represent your implementation while the other one is from the paper you cited?
Glad to hear that it worked!
Yes, the term "3D CNN" describes the "meta-architecture", and it refers to the the design in Figure 3(a). It can use different "backbones".
In Table 4, "3D CNN with R50-I3D-NL" is a "3D CNN" design (Figure 3(a)) using "R50-I3D-NL" as backbone.
You're right that the only difference between "3D CNN" and "I3D-NL" in Table 4 is implementation detail of backbone (See Appendix for details of ours), but nothing fundamentally different. Sorry for the confusion!
Thanks a lot :)
Hi,
I am trying to replicate the
Resnet-50-baseline
experiment on the Charades dataset. I'm using the following config -As you can see, I am using 4 GPUs. So, I have reduced the batch size and learning rate by half. But the highest mAP I am getting is ~ 36.0. But if I do the test using your pre-trained model, I can get ~38 mAP. Can you please check my config file and suggest some changes necessary?