xmzhuxm

ckpt = tf.train. get_checkpoint_state('./models') if ckpt and ckpt.model_checkpoint_path: saver.restore(sess, ckpt.model_checkpoint_path) print("Model Loading Done!")

@Mohamad73 @SiDinhThoi @laura-wang @Ai-is-light @BestJuly ，THe results @hx173149 obtained were tested on ucf-101 test split 1,and where your guys trained ,you then split dataset again,so your test.list must have many...

i also meet this error,have you sloved the matter?

where i need to modify,i train from scratch and get a very low accuracy,maybe i modify error location,can you help me,thank you very much! i stacked here for many days....

> > > i also got ~30% and i don't know what to do... where i need to modify,i train from scratch and get a very low accuracy,maybe i modify...