Number of frames for test

[ir0nt0ad]

I3D_Finetune/finetune.py

Line 63 in c32d90f

clip_holder, label_holder = tf.py_func(

It appears that we always call process_video with is_training=True, and therefore each sample of test_dataset has _CLIP_SIZE, not _EACH_VIDEO_TEST_SIZE frames as we would like to have it.

@Rhythmblue @AlexHu123