Closed abhishekaich27 closed 4 years ago
Yes, only L168 needs to be changed. Batchsize, the num of GPUs and the version of pytorch may impact the results. In general, 1% error is reasonable. In addition, running test-all.py is necessary, because the process of test in train.py only uses 4 frames per video.
Hi Xinqian,
To replicate only I3D results, do we need to change anything else except
AP3D.APP3DC ---> AP3D.I3D
inL168
ofResNet.py
? If I only do this change, I get 3% mAP difference according to Table 1.