search

tkipf / relational-gcn

Keras-based implementation of Relational Graph Convolutional Networks
MIT License
793 stars 134 forks source link

TypeError: Expected int32, got <tf.Variable 'graphconvolution_1_W:0' shape=(8285, 16) dtype=float32_ref> of type 'Variable' instead. #25

Open xjy-xing opened 2 years ago

xjy-xing commented 2 years ago

sorry run train.py and this is the error Traceback (most recent call last): File "/home/bfs/NEW_LAB/relational-gcn-master/rgcn/train.py", line 92, in W_regularizer=l2(L2))([X_in] + A_in) File "/home/bfs/miniconda3/envs/py27tf14_rgcn/lib/python2.7/site-packages/keras/engine/topology.py", line 548, in call self.build(input_shapes) File "build/bdist.linux-x86_64/egg/rgcn/layers/graph.py", line 69, in build File "/home/bfs/miniconda3/envs/py27tf14_rgcn/lib/python2.7/site-packages/keras/backend/tensorflow_backend.py", line 1427, in concatenate return tf.concat(axis, [to_dense(x) for x in tensors]) File "/home/bfs/miniconda3/envs/py27tf14_rgcn/lib/python2.7/site-packages/tensorflow/python/ops/array_ops.py", line 1096, in concat dtype=dtypes.int32).get_shape().assert_is_compatible_with( File "/home/bfs/miniconda3/envs/py27tf14_rgcn/lib/python2.7/site-packages/tensorflow/python/framework/ops.py", line 836, in convert_to_tensor as_ref=False) File "/home/bfs/miniconda3/envs/py27tf14_rgcn/lib/python2.7/site-packages/tensorflow/python/framework/ops.py", line 926, in internal_convert_to_tensor ret = conversion_func(value, dtype=dtype, name=name, as_ref=as_ref) File "/home/bfs/miniconda3/envs/py27tf14_rgcn/lib/python2.7/site-packages/tensorflow/python/framework/constant_op.py", line 229, in _constant_tensor_conversion_function return constant(v, dtype=dtype, name=name) File "/home/bfs/miniconda3/envs/py27tf14_rgcn/lib/python2.7/site-packages/tensorflow/python/framework/constant_op.py", line 208, in constant value, dtype=dtype, shape=shape, verify_shape=verify_shape)) File "/home/bfs/miniconda3/envs/py27tf14_rgcn/lib/python2.7/site-packages/tensorflow/python/framework/tensor_util.py", line 383, in make_tensor_proto _AssertCompatible(values, dtype) File "/home/bfs/miniconda3/envs/py27tf14_rgcn/lib/python2.7/site-packages/tensorflow/python/framework/tensor_util.py", line 303, in _AssertCompatible (dtype.name, repr(mismatch), type(mismatch).name)) TypeError: Expected int32, got <tf.Variable 'graphconvolution_1_W:0' shape=(8285, 16) dtype=float32_ref> of type 'Variable' instead.

Process finished with exit code 1

jiujiuxia commented 2 years ago

Hi! have you solved this problem?

xjy-xing commented 2 years ago

yes, thank you so much! sorry to reply so late.

------------------ 原始邮件 ------------------ 发件人: "tkipf/relational-gcn" @.>; 发送时间: 2022年6月9日(星期四) 晚上8:52 @.>; @.**@.>; 主题: Re: [tkipf/relational-gcn] TypeError: Expected int32, got <tf.Variable 'graphconvolution_1_W:0' shape=(8285, 16) dtype=float32_ref> of type 'Variable' instead. (Issue #25)

Hi! have you solved this problem?

— Reply to this email directly, view it on GitHub, or unsubscribe. You are receiving this because you authored the thread.Message ID: @.***>

Changgeww commented 1 year ago

Hello, I have the same problem as you. May I ask how you solved it?