ValueError: Dimensions must be equal, but are 256 and 384 for 'tower_0/build_pyramid/build_P4/add' (op: 'Add') with input shapes: [1,?,?,256], [1,?,?,384].

I try to training my dataset, and i have reference the three steps in README.md, I use the pretrained weights resnet_v1_50.ckpt, and i modify the $PATH_ROOT/libs/configs/cfgs.py and $PATH_ROOT/libs/label_name_dict/lable_dict.py and $PATH_ROOT/data/io/read_tfrecord.py, the NET_NAME has been alter with "resnet_v1_50", However ,after "python ./tools/multi_gpu_train.py",the error msg:
++--++--++--++--++--++--++--++--++--++--++--++--++--++--++--++--++--++--++--++--
./NAS_FPN_Tensorflow-master
WARNING:tensorflow:From multi_gpu_train.py:123: get_or_create_global_step (from tensorflow.contrib.framework.python.ops.variables) is deprecated and will be removed in a future version.
Instructions for updating:
Please switch to tf.train.get_or_create_global_step
tfrecord path is --> ./NAS_FPN_Tensorflow-master/data/tfrecord/occlusion_recognition_train*
Traceback (most recent call last):
File "./envs/anaconda/lib/python3.6/site-packages/tensorflow/python/framework/ops.py", line 1589, in _create_c_op
c_op = c_api.TF_FinishOperation(op_desc)
tensorflow.python.framework.errors_impl.InvalidArgumentError: Dimensions must be equal, but are 256 and 384 for 'tower_0/build_pyramid/build_P4/add' (op: 'Add') with input shapes: [1,?,?,256], [1,?,?,384].

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File "multi_gpu_train.py", line 352, in
train()
File "multi_gpu_train.py", line 212, in train
gtboxes_batch=gtboxes_and_label)
File "../libs/networks/build_whole_network.py", line 386, in build_whole_detection_network
P_list = self.build_base_network(input_img_batch)
File "../libs/networks/build_whole_network.py", line 35, in build_base_network
return resnet.resnet_base(input_img_batch, scope_name=self.base_network_name, is_training=self.is_training)
File "../libs/networks/resnet.py", line 189, in resnet_base
scope='build_P%d' % level)
File "../libs/networks/resnet.py", line 63, in fusion_two_layer
add_f = 0.5*upsample_p + 0.5*reduce_dim_c
File "./envs/anaconda/lib/python3.6/site-packages/tensorflow/python/ops/math_ops.py", line 847, in binary_op_wrapper
return func(x, y, name=name)
File "./envs/anaconda/lib/python3.6/site-packages/tensorflow/python/ops/gen_math_ops.py", line 297, in add
"Add", x=x, y=y, name=name)
File "./envs/anaconda/lib/python3.6/site-packages/tensorflow/python/framework/op_def_library.py", line 787, in _apply_op_helper
op_def=op_def)
File "./envs/anaconda/lib/python3.6/site-packages/tensorflow/python/framework/ops.py", line 3414, in create_op
op_def=op_def)
File "./anaconda/lib/python3.6/site-packages/tensorflow/python/framework/ops.py", line 1756, in __init__
control_input_ops)
File "./envs/anaconda/lib/python3.6/site-packages/tensorflow/python/framework/ops.py", line 1592, in _create_c_op
raise ValueError(str(e))
ValueError: Dimensions must be equal, but are 256 and 384 for 'tower_0/build_pyramid/build_P4/add' (op: 'Add') with input shapes: [1,?,?,256], [1,?,?,384].

Start with libs/networks/resnet.py, especially fusion_two_layer at line 63, and trace its callers in libs/networks/build_whole_network.py; compare the NET_NAME and pretrained-weight setup in libs/configs/cfgs.py with the tensors reaching build_P4. Re-run python ./tools/multi_gpu_train.py after checking the documented configuration, and consider it done when graph construction no longer raises the reported channel mismatch.

Written by the indexing model from the issue text.