sumeetssaurav
sumeetssaurav
@Katou2 Could you please share the details of your config file which you used for fine-tuning using resnext-100 and resnext-101-64f version of the models on UCF-101. I want to know...
There is another issue in the code. Once you generate the val.json, the file contains prediction results of 1 video less than what contained in the val list of videos....
@Katou2 Thanks for the quick reply. Still wondering where I have to put the loop suggested by you. Could you please highlight it in the test.py code.
You could try using --resnet_shortcut B for model depth other than 18 and 34. Thank You
Hi, I'm trying to reproduce the results reported in the paper (and this repository) with the I3D model trained with only RGB on UCF-101 (split 1) . When I run...
Sorry the error is coming in the line featmap_2d = keras.layers.Reshape((28,28,256), name='clstm_reshape')(clstm2d_2) By the way, I do not think this is version related issue. Could you please check it once...
Modified the code for the new version of Keras-2.2.4 with tensorflow 1.10.1. Things are working properly now. Thanks @GuangmingZhu