Closed Guocode closed 5 years ago
From my experience you have no chance to train it straight on ucf101,HMDB51 or other small datasets, you have to pretrain on kinetics
Hi @Guocode ,
Load the kinetics pre-trained model is the best solution, since the UCF101/HMDB51 is too small for 3D ConvNets.
Below are some tricks to try if you really do not want to load Kinetics pre-trained model:
Thanks for trying our code, and sorry for the late reply.
Deep Networks with Stochastic Depth mixup: Beyond Empirical Risk Minimization
Thanks for reply.
Do you have any training tricks on ucf101,when I train MFNET on ucf101,it turns out to overfitting easily. Is a pretraining on large dataset like kinetics necessary and what's your key tricks to improve accuracy?