search

swathikirans / GSM

Gate-Shift Networks for Video Action Recognition - CVPR 2020
Other
151 stars 17 forks source link

Difference in Result #6

Open NaeemKhan333 opened 4 years ago

NaeemKhan333 commented 4 years ago

Thanks for nice work . I have trained a model on my own dataset which have three classes and every class have 20 videos each . I have formated the dataset in the somehting-something-v1 format and start the training. Durning training I have got testing accuracy as follow

ss1

After completing the training, I have tested the model on the same data, it giving me as follow

Screenshot from 2020-03-02 19-41-05

Class Accuracy 36.67% Overall Prec@1 36.67% Prec@5 100.00%

can you explain the result ,is it ok or something wrong ?

swathikirans commented 4 years ago

Please make sure you are using the right model during inference. It looks like you are loading the something-v1 trained model during inference.

NaeemKhan333 commented 4 years ago

Yes this is my model,which is trained using the something-something-v1 dataset format, Althought model name is ""something-v1_BNInception_avg_segment8_checkpoint.pth.tar"" but actually it is the model which is trained my me on my own data set.