<Thumos experiment>the python/tuple in train.prototxt was [2,4,6,8,10,12,14,16,18,20,22,24,26,28,30,32,34,36,38,40,42,44,46,48,50,52,54,56],which is different from [2,4,5,6,8,9,10,12,14,16] in your paper of R-C3D

VisionLearningGroup / R-C3D

code for R-C3D

MIT License

254 stars 94 forks source link

<Thumos experiment>the python/tuple in train.prototxt was [2,4,6,8,10,12,14,16,18,20,22,24,26,28,30,32,34,36,38,40,42,44,46,48,50,52,54,56],which is different from [2,4,5,6,8,9,10,12,14,16] in your paper of R-C3D #64

Open fanxx17 opened 3 years ago

fanxx17 commented 3 years ago

the python/tuple in train.prototxt was [2,4,6,8,10,12,14,16,18,20,22,24,26,28,30,32,34,36,38,40,42,44,46,48,50,52,54,56],which is different from [2,4,5,6,8,9,10,12,14,16] in your paper of R-C3D。 And my question is "which tuple do you use when you train your paper's caffemodel ",thank you so much