Wang

遇到了同样的问题，训练了一个异构图，模型无法收敛，且最终embbedding的余弦距离非常接近，请问如何解决呢

Hi, I have solved this problem by using the following instructions: `$ ./server.py --time 15 --batch 7 $ ./view_generative_model.py --name transition --time 15 --batch 7` You can have a try.

@yangyuekai Hi, I didn't change the code from github. I guess your problem from this command( line 87 ) `imgs = sess.run([G_out], feed_dict={O: outs.reshape((-1, z_dim)), K.learning_phase(): 1})[0]` The shape of...