Open jianzhelin opened 6 years ago
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!")
@malege when I tried to run the code you gave I got this error
Traceback (most recent call last):
File "<stdin>", line 2, in <module>
NameError: name 'saver' is not defined
can you help me to solve this? Thanks
I have trained the model by training part, but how to use this trained model in prediction part?
have you finished this problem? i meet the same problem
i solve this problem,when you use the predict_c3d_ucf101.py ,you can use .data.... as model
I have trained the model by training part, but how to use this trained model in prediction part?