Assign requires shapes of both tensors to match. lhs shape= [1,1,256,3] rhs shape= [1,1,256,2]

[Jacoobr]

Hi, dear @LeslieZhoa , when i try to run test.py to predict the result, the error as bellowed occurred . Can you give me some advices about the error? Bty, the training stage goes well, when the training finished and i try to the test stage by running python test.py, the error occurred unfortunately.
Appreciative for your reply.

2019-11-27 17:20:28.581507: I tensorflow/core/common_runtime/process_util.cc:115] Creating new thread pool with default inter op setting: 2. Tune using inter_op_parallelism_threads for best performance.
model file:=====================>  ./qgymodel/model.ckpt-18
W1127 17:20:28.587627 139825758234368 deprecation.py:323] From /home/zcy/anaconda3/lib/python3.7/site-packages/tensorflow/python/training/saver.py:1276: checkpoint_exists (from tensorflow.python.training.checkpoint_management) is deprecated and will be removed in a future version.
Instructions for updating:
Use standard file APIs to check for files with this prefix.
2019-11-27 17:20:29.224083: W tensorflow/compiler/jit/mark_for_compilation_pass.cc:1412] (One-time warning): Not using XLA:CPU for cluster because envvar TF_XLA_FLAGS=--tf_xla_cpu_global_jit was not set.  If you want XLA:CPU, either set that envvar, or use experimental_jit_scope to enable XLA:CPU.  To confirm that XLA is active, pass --vmodule=xla_compilation_cache=1 (as a proper command-line flag, not via TF_XLA_FLAGS) or set the envvar XLA_FLAGS=--xla_hlo_profile.
Traceback (most recent call last):
  File "/home/zcy/anaconda3/lib/python3.7/site-packages/tensorflow/python/client/session.py", line 1356, in _do_call
    return fn(*args)
  File "/home/zcy/anaconda3/lib/python3.7/site-packages/tensorflow/python/client/session.py", line 1341, in _run_fn
    options, feed_dict, fetch_list, target_list, run_metadata)
  File "/home/zcy/anaconda3/lib/python3.7/site-packages/tensorflow/python/client/session.py", line 1429, in _call_tf_sessionrun
    run_metadata)
tensorflow.python.framework.errors_impl.InvalidArgumentError: Assign requires shapes of both tensors to match. lhs shape= [1,1,256,3] rhs shape= [1,1,256,2]
         [[{{node save/Assign_31}}]]

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
  File "/home/zcy/anaconda3/lib/python3.7/site-packages/tensorflow/python/training/saver.py", line 1286, in restore
    {self.saver_def.filename_tensor_name: save_path})
  File "/home/zcy/anaconda3/lib/python3.7/site-packages/tensorflow/python/client/session.py", line 950, in run
    run_metadata_ptr)
  File "/home/zcy/anaconda3/lib/python3.7/site-packages/tensorflow/python/client/session.py", line 1173, in _run
    feed_dict_tensor, options, run_metadata)
  File "/home/zcy/anaconda3/lib/python3.7/site-packages/tensorflow/python/client/session.py", line 1350, in _do_run
    run_metadata)
  File "/home/zcy/anaconda3/lib/python3.7/site-packages/tensorflow/python/client/session.py", line 1370, in _do_call
    raise type(e)(node_def, op, message)
tensorflow.python.framework.errors_impl.InvalidArgumentError: Assign requires shapes of both tensors to match. lhs shape= [1,1,256,3] rhs shape= [1,1,256,2]
         [[node save/Assign_31 (defined at test.py:37) ]]