无效参数：不兼容的形状：[4883,1]与[68,1]

Question

为了优化我的代码，我更改了以下内容：

view1ID_train_data_sparse = load_sample(batch_size_view1, f_view1ID_train_data_sparse)
row_view1ID = range(len(view1ID_train_data_sparse[:,0].astype(int)))
col_view1ID = view1ID_train_data_sparse[:,1]
value_view1ID = view1ID_train_data_sparse[:,2]
view1ID_train_data = coo_matrix( ( value_view1ID, (row_view1ID, col_view1ID.astype(int)) ), shape=( len(row_view1ID), View1Number ) ).toarray()

收件人：

^{pr2}$

但有一个错误：

2018-02-26 17:25:25.665274: W tensorflow/core/framework/op_kernel.cc:1152] Invalid argument: Incompatible shapes: [4883,1] vs. [68,1]
     [[Node: gradients/sub_337_grad/BroadcastGradientArgs = BroadcastGradientArgs[T=DT_INT32, _device="/job:localhost/replica:0/task:0/cpu:0"](gradients/sub_337_grad/Shape, gradients/sub_337_grad/Shape_1)]]
2018-02-26 17:25:25.666627: W tensorflow/core/framework/op_kernel.cc:1152] Invalid argument: Incompatible shapes: [4883,1] vs. [68,1]
     [[Node: gradients/sub_337_grad/BroadcastGradientArgs = BroadcastGradientArgs[T=DT_INT32, _device="/job:localhost/replica:0/task:0/cpu:0"](gradients/sub_337_grad/Shape, gradients/sub_337_grad/Shape_1)]]
Traceback (most recent call last):
  File "/Users/LA_rovski/anaconda/lib/python3.5/site-packages/tensorflow/python/client/session.py", line 1039, in _do_call
    return fn(*args)
  File "/Users/LA_rovski/anaconda/lib/python3.5/site-packages/tensorflow/python/client/session.py", line 1021, in _run_fn
    status, run_metadata)
  File "/Users/LA_rovski/anaconda/lib/python3.5/contextlib.py", line 66, in __exit__
    next(self.gen)
  File "/Users/LA_rovski/anaconda/lib/python3.5/site-packages/tensorflow/python/framework/errors_impl.py", line 466, in raise_exception_on_not_ok_status
    pywrap_tensorflow.TF_GetCode(status))
tensorflow.python.framework.errors_impl.InvalidArgumentError: Incompatible shapes: [4883,1] vs. [68,1]
     [[Node: gradients/sub_337_grad/BroadcastGradientArgs = BroadcastGradientArgs[T=DT_INT32, _device="/job:localhost/replica:0/task:0/cpu:0"](gradients/sub_337_grad/Shape, gradients/sub_337_grad/Shape_1)]]
During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File "Transfer_Model_sparse1.py", line 638, in <module>
Pi: pi})
File "/Users/LA_rovski/anaconda/lib/python3.5/site-packages/tensorflow/python/client/session.py", line 778, in run
run_metadata_ptr)
File "/Users/LA_rovski/anaconda/lib/python3.5/site-packages/tensorflow/python/client/session.py", line 982, in _run
feed_dict_string, options, run_metadata)
File "/Users/LA_rovski/anaconda/lib/python3.5/site-packages/tensorflow/python/client/session.py", line 1032, in _do_run
target_list, options, run_metadata)
File "/Users/LA_rovski/anaconda/lib/python3.5/site-packages/tensorflow/python/client/session.py", line 1052, in _do_call
raise type(e)(node_def, op, message)
tensorflow.python.framework.errors_impl.InvalidArgumentError: Incompatible shapes: [4883,1] vs. [68,1]
 [[Node: gradients/sub_337_grad/BroadcastGradientArgs = BroadcastGradientArgs[T=DT_INT32, _device="/job:localhost/replica:0/task:0/cpu:0"](gradients/sub_337_grad/Shape, gradients/sub_337_grad/Shape_1)]]

Caused by op 'gradients/sub_337_grad/BroadcastGradientArgs', defined at:
File "Transfer_Model_sparse1.py", line 489, in <module>
optimize = optimizer.minimize(objective)
File "/Users/LA_rovski/anaconda/lib/python3.5/site-packages/tensorflow/python/training/optimizer.py", line 315, in minimize
grad_loss=grad_loss)
File "/Users/LA_rovski/anaconda/lib/python3.5/site-packages/tensorflow/python/training/optimizer.py", line 386, in compute_gradients
colocate_gradients_with_ops=colocate_gradients_with_ops)
File "/Users/LA_rovski/anaconda/lib/python3.5/site-packages/tensorflow/python/ops/gradients_impl.py", line 560, in gradients
grad_scope, op, func_call, lambda: grad_fn(op, *out_grads))
File "/Users/LA_rovski/anaconda/lib/python3.5/site-packages/tensorflow/python/ops/gradients_impl.py", line 368, in _MaybeCompile
return grad_fn()  # Exit early
File "/Users/LA_rovski/anaconda/lib/python3.5/site-packages/tensorflow/python/ops/gradients_impl.py", line 560, in <lambda>
grad_scope, op, func_call, lambda: grad_fn(op, *out_grads))
File "/Users/LA_rovski/anaconda/lib/python3.5/site-packages/tensorflow/python/ops/math_grad.py", line 609, in _SubGrad
rx, ry = gen_array_ops._broadcast_gradient_args(sx, sy)
File "/Users/LA_rovski/anaconda/lib/python3.5/site-packages/tensorflow/python/ops/gen_array_ops.py", line 411, in _broadcast_gradient_args
name=name)
File "/Users/LA_rovski/anaconda/lib/python3.5/site-packages/tensorflow/python/framework/op_def_library.py", line 768, in apply_op
op_def=op_def)
File "/Users/LA_rovski/anaconda/lib/python3.5/site-packages/tensorflow/python/framework/ops.py", line 2336, in create_op
original_op=self._default_original_op, op_def=op_def)
File "/Users/LA_rovski/anaconda/lib/python3.5/site-packages/tensorflow/python/framework/ops.py", line 1228, in __init__
self._traceback = _extract_stack()

...which was originally created as op 'sub_337', defined at:
File "Transfer_Model_sparse1.py", line 424, in <module>
sample_log_likelihood_view1 = tf.reduce_sum(log_gaussian(Rating_view1, Y_view1, sigma_prior_y))
File "Transfer_Model_sparse1.py", line 38, in log_gaussian
return -0.5 * np.log(2 * np.pi) - tf.log(tf.abs(sigma)) - tf.square(x - mu) / (2 * tf.square(sigma))
File "/Users/LA_rovski/anaconda/lib/python3.5/site-packages/tensorflow/python/ops/math_ops.py", line 821, in binary_op_wrapper
return func(x, y, name=name)
File "/Users/LA_rovski/anaconda/lib/python3.5/site-packages/tensorflow/python/ops/gen_math_ops.py", line 2627, in _sub
result = _op_def_lib.apply_op("Sub", x=x, y=y, name=name)
File "/Users/LA_rovski/anaconda/lib/python3.5/site-packages/tensorflow/python/framework/op_def_library.py", line 768, in apply_op
op_def=op_def)
File "/Users/LA_rovski/anaconda/lib/python3.5/site-packages/tensorflow/python/framework/ops.py", line 2336, in create_op
original_op=self._default_original_op, op_def=op_def)
File "/Users/LA_rovski/anaconda/lib/python3.5/site-packages/tensorflow/python/framework/ops.py", line 1228, in __init__
self._traceback = _extract_stack()

InvalidArgumentError (see above for traceback): Incompatible shapes: [4883,1] vs. [68,1]
 [[Node: gradients/sub_337_grad/BroadcastGradientArgs = BroadcastGradientArgs[T=DT_INT32, _device="/job:localhost/replica:0/task:0/cpu:0"](gradients/sub_337_grad/Shape, gradients/sub_337_grad/Shape_1)]]

我检查了矩阵的维数很多时间，但没有找到解决办法。这个问题困扰了我很长时间，如果你能帮助我，非常感谢你。在

奇怪的是，如果我将n_批处理（迭代次数）减少到2，bug就会消失。在