junkyungkim
junkyungkim
@chen1005 I also curious about that! Could you share your modified code? At first, I can do 'make' on cmd with installing Gnuwin32. but i stopped with 'make' command with...
oh, I already adapt that correction in code.  This is my output from above method. It is quite different from #3. In my case, 3D skeleton is also wrongly...
@timctho Can you share your weight and model files?? I don't think there is no problem with your codes.
@yukaliu07 @lavage Thank you so much!! It perfectly solved my problem. :D
@Robinchacko At step 3 on your method, i guess you should fix the location of model file in demo_tf.py
I changed code line 173-181 in **vnect_tf.py** ``` if __name__ == '__main__': model_file = 'vnect.pkl' model = VNect(368) with tf.Session() as sess: saver = tf.train.Saver() model.load_weights(sess, model_file) save_path = saver.save(sess,...