Mmmofan / YOLO_6D

Implement Singleshotpose(Yolo 6d) in TensorFlow
54 stars 9 forks source link

ValueError: Dimension 2 in both shapes must be equal, but are 7 and 6. Shapes are [?,6,7] and [?,6,6]. for 'concat' (op: 'ConcatV2') with input shapes: [?,7,7,64], [?,7,6,64], [?,6,7,64], [?,6,6,64], [] and with computed input tensors: input[4] = <3>. #3

Open phes10529 opened 3 years ago

phes10529 commented 3 years ago

This is my all error message `Traceback (most recent call last): File "D:\Python36\lib\site-packages\tensorflow_core\python\framework\ops.py", line 1619, in _create_c_op c_op = c_api.TF_FinishOperation(op_desc) tensorflow.python.framework.errors_impl.InvalidArgumentError: Dimension 2 in both shapes must be equal, but are 7 and 6. Shapes are [?,6,7] and [?,6,6]. for 'concat' (op: 'ConcatV2') with input shapes: [?,7,7,64], [?,7,6,64], [?,6,7,64], [?,6,6,64], [] and with computed input tensors: input[4] = <3>.

During handling of the above exception, another exception occurred:

Traceback (most recent call last): File "train.py", line 372, in yolo = YOLO6D_net() File "E:\YOLO_6D\yolo_6d_net.py", line 60, in init self.output = self.build_networks(self.input_images) # shape: [batch, cell, cell, 19] File "E:\YOLO_6D\yolo_6d_net.py", line 103, in build_networks net = self.reorg(net) File "E:\YOLO_6D\yolo_6d_net.py", line 210, in reorg output = tf.concat([outputs_1, outputs_2, outputs_3, outputs_4], axis = 3) File "D:\Python36\lib\site-packages\tensorflow_core\python\util\dispatch.py", line 180, in wrapper return target(*args, **kwargs) File "D:\Python36\lib\site-packages\tensorflow_core\python\ops\array_ops.py", line 1517, in concat return gen_array_ops.concat_v2(values=values, axis=axis, name=name) File "D:\Python36\lib\site-packages\tensorflow_core\python\ops\gen_array_ops.py", line 1126, in concat_v2 "ConcatV2", values=values, axis=axis, name=name) File "D:\Python36\lib\site-packages\tensorflow_core\python\framework\op_def_library.py", line 742, in _apply_op_helper attrs=attr_protos, op_def=op_def) File "D:\Python36\lib\site-packages\tensorflow_core\python\framework\ops.py", line 3322, in _create_op_internal op_def=op_def) File "D:\Python36\lib\site-packages\tensorflow_core\python\framework\ops.py", line 1786, in init control_input_ops) File "D:\Python36\lib\site-packages\tensorflow_core\python\framework\ops.py", line 1622, in _create_c_op raise ValueError(str(e)) ValueError: Dimension 2 in both shapes must be equal, but are 7 and 6. Shapes are [?,6,7] and [?,6,6]. for 'concat' (op: 'ConcatV2') with input shapes: [?,7,7,64], [?,7,6,64], [?,6,7,64], [?,6,6,64], [] and with computed input tensors: input[4] = <3>.`