ValueError: Shapes must be equal rank, but are 2 and 1

[RoseLii]

tensorflow.python.framework.errors_impl.InvalidArgumentError: Shapes must be equal rank, but are 2 and 1 From merging shape 0 with other shapes. for 'packed' (op: 'Pack') with input shapes: [?,23436], [3]. please help me ValueError: Shapes must be equal rank, but are 2 and 1 From merging shape 0 with other shapes. for 'packed' (op: 'Pack') with input shapes: [?,23436], [3]. I should how charge the error?

[willSapgreen]

Hello @RoseLii

if you still have this issue,

try the following approach which resolves on my side:

change

final_pred_conf = tf.concat(1, preds_conf)
final_pred_loc = tf.concat(1, preds_loc)

to final_pred_conf = tf.concat(preds_conf, 1) final_pred_loc = tf.concat(preds_loc, 1)

in model.py

My environment: python3 TensorFlow 1.12.0, installed from build.

Good luck!