RK3399Pro入门教程（9）MNIST RKNN量化教程

2020-04-17 23:23:52.630269: 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.
pyfunc exception: Cannot feed value of shape (1, 28, 28, 1) for Tensor 'x:0', which has shape '(?, 28, 28)'
Traceback (most recent call last):
  File "/home/ol/.local/lib/python3.5/site-packages/rknn/base/acuitylib/converter/pyfunc_builder.py", line 30, in pyfunc_call
    return function_builder(func_str)(self, node, tensor)
  File "<string>", line 9, in r_fc_tensor_dot_rule_get_param_axis_pre_condition
  File "rknn/base/acuitylib/converter/convert_tf.py", line 134, in rknn.base.acuitylib.converter.convert_tf.convert_tf.shape_pick
  File "rknn/base/acuitylib/converter/tensorflowloader.py", line 205, in rknn.base.acuitylib.converter.tensorflowloader.TF_Graph_Preprocess.query_tensors
  File "rknn/base/acuitylib/converter/tf_util.py", line 371, in rknn.base.acuitylib.converter.tf_util.TFProto_Util.query_tensor
  File "rknn/base/acuitylib/converter/tf_util.py", line 374, in rknn.base.acuitylib.converter.tf_util.TFProto_Util.query_tensor
  File "rknn/base/acuitylib/converter/tf_util.py", line 407, in rknn.base.acuitylib.converter.tf_util.TFProto_Util.query_tensor
  File "/home/ol/.local/lib/python3.5/site-packages/tensorflow/python/client/session.py", line 950, in run
    run_metadata_ptr)
  File "/home/ol/.local/lib/python3.5/site-packages/tensorflow/python/client/session.py", line 1149, in _run
    str(subfeed_t.get_shape())))
ValueError: Cannot feed value of shape (1, 28, 28, 1) for Tensor 'x:0', which has shape '(?, 28, 28)'


说我的输入不对？这个怎么解决啊