Caused by op 'model/mean_squared_error/SquaredDifference', defined at:
File "code2seq_lkf.py", line 40, in <module>
model.train()
File "/mnt/lkf_u/code2seq/model_lkf.py", line 89, in train
self.build_training_graph(self.queue_thread.get_output(), rewards)
File "/mnt/lkf_u/code2seq/model_lkf.py", line 538, in build_training_graph
critic_loss = tf.losses.mean_squared_error(labels=rewards, predictions=critic_outputs, weights=critic_weights) # 形狀不與label相同，是一個標量
File "/home/lkf/lkf_u/anaconda3/envs/tf1.12/lib/python3.6/site-packages/tensorflow/python/ops/losses/losses_impl.py", line 671, in mean_squared_error
losses = math_ops.squared_difference(predictions, labels)
File "/home/lkf/lkf_u/anaconda3/envs/tf1.12/lib/python3.6/site-packages/tensorflow/python/ops/gen_math_ops.py", line 8258, in squared_difference
"SquaredDifference", x=x, y=y, name=name)
File "/home/lkf/lkf_u/anaconda3/envs/tf1.12/lib/python3.6/site-packages/tensorflow/python/framework/op_def_library.py", line 787, in _apply_op_helper
op_def=op_def)
File "/home/lkf/lkf_u/anaconda3/envs/tf1.12/lib/python3.6/site-packages/tensorflow/python/util/deprecation.py", line 488, in new_func
return func(*args, **kwargs)
File "/home/lkf/lkf_u/anaconda3/envs/tf1.12/lib/python3.6/site-packages/tensorflow/python/framework/ops.py", line 3274, in create_op
op_def=op_def)
File "/home/lkf/lkf_u/anaconda3/envs/tf1.12/lib/python3.6/site-packages/tensorflow/python/framework/ops.py", line 1770, in __init__
self._traceback = tf_stack.extract_stack()
InvalidArgumentError (see above for traceback): Incompatible shapes: [6,7] vs. [256,7]
[[node model/mean_squared_error/SquaredDifference (defined at /mnt/lkf_u/code2seq/model_lkf.py:538) = SquaredDifference[T=DT_FLOAT, _device="/job:localhost/replica:0/task:0/device:GPU:0"](model/Squeeze, model/transpose)]]
[[{{node model/mean_squared_error/num_present/broadcast_weights/assert_broadcastable/AssertGuard/Assert/Switch_1/_527}} = _Recv[client_terminated=false, recv_device="/job:localhost/replica:0/task:0/device:CPU:0", send_device="/job:localhost/replica:0/task:0/device:GPU:0", send_device_incarnation=1, tensor_name="edge_2333_...t/Switch_1", tensor_type=DT_INT32, _device="/job:localhost/replica:0/task:0/device:CPU:0"]()]]
我使用了tf.placeholder，沒有指定batch_size的大小，但是我在feed進去之前查看了資料shape，跟batch_size大小一樣，結果卻出現了下面這個錯，我在傳進去之后對它進行的唯一操作是tf.transpose，請問是什么原因
uj5u.com熱心網友回復：
檢查一下矩陣維度，模型每一步都列印一下shape轉載請註明出處，本文鏈接：https://www.uj5u.com/qita/75072.html
標籤：人工智能技術
上一篇：求容器中最大值