1. 环境：macbook10.12.6 (16G29)，python2.7，virtualenv.
2. 描述：下载了老师的train.py跑，到Epoch 9, 第 22 步, 生成器的损失: 1.945, 判别器的损失: 1.434之后报错如下，google不到原因，程序也推出了。
3. 错误内容：

WARNING:tensorflow:This model was compiled with a Keras optimizer (<tensorflow.python.keras.optimizers.Adam object at 0x1310a1350>) but is being saved in TensorFlow format withsave_weights. The model's weights will be saved, but unlike with TensorFlow optimizers in the TensorFlow format the optimizer's state will not be saved.

Consider using a TensorFlow optimizer fromtf.train. 2018-10-16 12:50:29.019043: W tensorflow/core/framework/op_kernel.cc:1273] OP_REQUIRES failed at save_restore_v2_ops.cc:109 : Not found: ; No such file or directory Traceback (most recent call last): File "train.py", line 92, in <module> train() File "train.py", line 87, in train g.save_weights("generator_weight1016", True) File "/Users/hahaxixi2017/PycharmProjects/tensorflow/lib/python2.7/site-packages/tensorflow/python/keras/engine/network.py", line 1458, in save_weights self._checkpointable_saver.save(filepath, session=session) File "/Users/hahaxixi2017/PycharmProjects/tensorflow/lib/python2.7/site-packages/tensorflow/python/training/checkpointable/util.py", line 1309, in save global_step=checkpoint_number) File "/Users/hahaxixi2017/PycharmProjects/tensorflow/lib/python2.7/site-packages/tensorflow/python/training/saver.py", line 1450, in save raise exc ValueError: Parent directory of generator_weight doesn't exist, can't save.