wangzhe

for j in range(i+1, self.hparams.field_nums): vi_fj = tf.nn.embedding_lookup(embedding[j], df_i[:,i]) # None * embedding_size vj_fi = tf.nn.embedding_lookup(embedding[i], df_i[:,j]) # None * embedding_size 这个embedding[j]为什么对应df[:,i]？

Who can explain the meaning of format in './data/LSVRC2015/ImageSets/VID_train_15frames.txt' and'./data/LSVRC2015/ImageSets/VID_val_videos.txt'

4

In 'VID_train_15frames.txt': It looks like: 'train/ILSVRC2015_VID_train_0000/ILSVRC2015_train_00000000 1 10 300' In 'VID_val_videos.txt': It looks like: 'val/ILSVRC2015_val_00000000 1 0 464' What's thr meaning of the last three numbers?

fps?

8

Have you test the fps in your computer? when I run the eval.py, it is only 2.17samples/sec, this is too slow for light head? is it?