train_PNet.py的error:Tensor("Cast_2:0", shape=(384,), dtype=int32) must be from the same graph as Tensor("mul:0", shape=(384,), dtype=int32).

[m29110938]

在执行train_PNet.py的档案时，出现这个问题请问要怎么解决 Traceback (most recent call last):

File "", line 29, in train_PNet(base_dir, prefix, end_epoch, display, lr)

File "", line 15, in train_PNet train(net_factory,prefix, end_epoch, base_dir, display=display, base_lr=lr)

File "D:\test\mtcnn_test\MTCNN-Tensorflow-master\train_models\train.py", line 163, in train cls_loss_op,bbox_loss_op,landmark_loss_op,L2_loss_op,accuracy_op = net_factory(input_image, label, bbox_target,landmark_target,training=True)

File "D:\test\mtcnn_test\MTCNN-Tensorflow-master\train_models\mtcnn_model.py", line 237, in P_Net cls_loss = cls_ohem(cls_prob,label)

File "D:\test\mtcnn_test\MTCNN-Tensorflow-master\train_models\mtcnn_model.py", line 42, in cls_ohem indices_ = row + label_int

File "C:\Users\User\Anaconda3\envs\gpu\lib\site-packages\tensorflow\python\ops\math_ops.py", line 860, in binary_op_wrapper with ops.name_scope(None, op_name, [x, y]) as name:

File "C:\Users\User\Anaconda3\envs\gpu\lib\site-packages\tensorflow\python\framework\ops.py", line 6035, in enter g = _get_graph_from_inputs(self._values)

File "C:\Users\User\Anaconda3\envs\gpu\lib\site-packages\tensorflow\python\framework\ops.py", line 5661, in _get_graph_from_inputs _assert_same_graph(original_graph_element, graph_element)

File "C:\Users\User\Anaconda3\envs\gpu\lib\site-packages\tensorflow\python\framework\ops.py", line 5597, in _assert_same_graph original_item))

@AITTSMD