TensorFlow回溯（最后一次调用）：TensorFlow.python.framework.errors\u impl.PermissionDeniedError:/tmpp error

我最近刚下载了TensorFlow，它与一个简单的草图配合得很好。但是现在有了一个更大的程序，它给了我一个错误：

Traceback (most recent call last):
  File "/Users/sergei/Documents/neural Network, tensorflow.py", line 4, in <module>
    mnist = input_data.read_data_sets("/tmpp/data/", one_hot=True)
  File "/Library/Frameworks/Python.framework/Versions/3.5/lib/python3.5/site-packages/tensorflow/contrib/learn/python/learn/datasets/mnist.py", line 227, in read_data_sets
    SOURCE_URL + TRAIN_IMAGES)
  File "/Library/Frameworks/Python.framework/Versions/3.5/lib/python3.5/site-packages/tensorflow/contrib/learn/python/learn/datasets/base.py", line 205, in maybe_download
    gfile.MakeDirs(work_directory)
  File "/Library/Frameworks/Python.framework/Versions/3.5/lib/python3.5/site-packages/tensorflow/python/lib/io/file_io.py", line 314, in recursive_create_dir
    pywrap_tensorflow.RecursivelyCreateDir(compat.as_bytes(dirname), status)
  File "/Library/Frameworks/Python.framework/Versions/3.5/lib/python3.5/contextlib.py", line 66, in __exit__
    next(self.gen)
  File "/Library/Frameworks/Python.framework/Versions/3.5/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.PermissionDeniedError: /tmpp

这是我在修复tmp问题和其他一些小问题时遇到的另一个错误

Traceback (most recent call last):
  File "/Library/Frameworks/Python.framework/Versions/3.5/lib/python3.5/site-packages/tensorflow/python/framework/common_shapes.py", line 671, in _call_cpp_shape_fn_impl
    input_tensors_as_shapes, status)
  File "/Library/Frameworks/Python.framework/Versions/3.5/lib/python3.5/contextlib.py", line 66, in __exit__
    next(self.gen)
  File "/Library/Frameworks/Python.framework/Versions/3.5/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: Dimensions must be equal, but are 784 and 500 for 'MatMul_1' (op: 'MatMul') with input shapes: [?,784], [500,500].

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
  File "/Users/sergei/Documents/neural Network, tensorflow.py", line 79, in <module>
    train_neural_network(x)
  File "/Users/sergei/Documents/neural Network, tensorflow.py", line 52, in train_neural_network
    prediction = neural_network_model(x)
  File "/Users/sergei/Documents/neural Network, tensorflow.py", line 39, in neural_network_model
    l2 = tf.add(tf.matmul(data, hidden_2_layer['weights']),  hidden_2_layer['biases'])
  File "/Library/Frameworks/Python.framework/Versions/3.5/lib/python3.5/site-packages/tensorflow/python/ops/math_ops.py", line 1801, in matmul
    a, b, transpose_a=transpose_a, transpose_b=transpose_b, name=name)
  File "/Library/Frameworks/Python.framework/Versions/3.5/lib/python3.5/site-packages/tensorflow/python/ops/gen_math_ops.py", line 1263, in _mat_mul
    transpose_b=transpose_b, name=name)
  File "/Library/Frameworks/Python.framework/Versions/3.5/lib/python3.5/site-packages/tensorflow/python/framework/op_def_library.py", line 768, in apply_op
    op_def=op_def)
  File "/Library/Frameworks/Python.framework/Versions/3.5/lib/python3.5/site-packages/tensorflow/python/framework/ops.py", line 2338, in create_op
    set_shapes_for_outputs(ret)
  File "/Library/Frameworks/Python.framework/Versions/3.5/lib/python3.5/site-packages/tensorflow/python/framework/ops.py", line 1719, in set_shapes_for_outputs
    shapes = shape_func(op)
  File "/Library/Frameworks/Python.framework/Versions/3.5/lib/python3.5/site-packages/tensorflow/python/framework/ops.py", line 1669, in call_with_requiring
    return call_cpp_shape_fn(op, require_shape_fn=True)
  File "/Library/Frameworks/Python.framework/Versions/3.5/lib/python3.5/site-packages/tensorflow/python/framework/common_shapes.py", line 610, in call_cpp_shape_fn
    debug_python_shape_fn, require_shape_fn)
  File "/Library/Frameworks/Python.framework/Versions/3.5/lib/python3.5/site-packages/tensorflow/python/framework/common_shapes.py", line 676, in _call_cpp_shape_fn_impl
    raise ValueError(err.message)
ValueError: Dimensions must be equal, but are 784 and 500 for 'MatMul_1' (op: 'MatMul') with input shapes: [?,784], [500,500].

回溯（最近一次呼叫最后一次）：
文件“/Library/Frameworks/Python.framework/Versions/3.5/lib/python3.5/site-packages/tensorflow/Python/framework/common_-shapes.py”，第671行，在“call\u-cpp\u-shape\u-fn\u-impl”中
输入\张量\作为\形状、状态）
文件“/Library/Frameworks/Python.framework/Versions/3.5/lib/python3.5/contextlib.py”，第66行，在退出时__
下一个（self.gen）
文件“/Library/Frameworks/Python.framework/Versions/3.5/lib/python3.5/site packages/tensorflow/Python/framework/errors\u impl.py”，第466行，处于raise\u exception\u on\u not\u ok\u状态
pywrap_tensorflow.TF_GetCode（状态））
tensorflow.python.framework.errors\u impl.InvalidArgumentError:维度必须相等，但对于输入形状为：[？、784]、[500500]的“MatMul\u 1”（op:“MatMul”）而言，维度为784和500。
在处理上述异常期间，发生了另一个异常：
回溯（最近一次呼叫最后一次）：
文件“/Users/sergei/Documents/neural Network，tensorflow.py”，第79行，中
训练神经网络（x）
文件“/Users/sergei/Documents/neural Network，tensorflow.py”，第52行，训练神经网络
预测=神经网络模型（x）
文件“/Users/sergei/Documents/neural Network，tensorflow.py”，第39行，在神经网络模型中
l2=tf.add（tf.matmul（数据，隐藏层['weights']），隐藏层['biases']））
matmul中的文件“/Library/Frameworks/Python.framework/Versions/3.5/lib/python3.5/site packages/tensorflow/Python/ops/math_ops.py”，第1801行
a、 b，转置a=转置a，转置b=转置b，名称=名称）
文件“/Library/Frameworks/Python.framework/Versions/3.5/lib/python3.5/site packages/tensorflow/Python/ops/gen\u math\u ops.py”，第1263行，在
转置b=转置b，名称=名称）
文件“/Library/Frameworks/Python.framework/Versions/3.5/lib/python3.5/site packages/tensorflow/Python/framework/op_def_Library.py”，第768行，在apply_op
op_def=op_def）
文件“/Library/Frameworks/Python.framework/Versions/3.5/lib/python3.5/site packages/tensorflow/Python/framework/ops.py”，第2338行，在create_op中
为输出设置形状（ret）
文件“/Library/Frameworks/Python.framework/Versions/3.5/lib/python3.5/site packages/tensorflow/Python/framework/ops.py”，第1719行，在集合形状中，用于输出
形状=形状函数（op）
文件“/Library/Frameworks/Python.framework/Versions/3.5/lib/python3.5/site-packages/tensorflow/Python/framework/ops.py”，第1669行，在调用_时使用_
回传呼叫\u cpp\u shape\u fn（op，require\u shape\u fn=True）
文件“/Library/Frameworks/Python.framework/Versions/3.5/lib/python3.5/site packages/tensorflow/Python/framework/common_shapes.py”，第610行，在call_cpp_shape_fn中
调试\u python\u形状\u fn，需要\u形状\u fn）
文件“/Library/Frameworks/Python.framework/Versions/3.5/lib/python3.5/site-packages/tensorflow/Python/framework/common_-shapes.py”，第676行，在“call\u-cpp\u-shape\u-fn\u-impl”中
提升值错误（错误消息）
ValueError:尺寸必须相等，但对于输入形状为：[？、784]、[500500]的“MatMul_1”（op:“MatMul”）而言，尺寸为784和500。

首先，让我们看看错误消息

Traceback (most recent call last):
  File "/Users/sergei/Documents/neural Network, tensorflow.py", line 79, in <module>
    train_neural_network(x)
  File "/Users/sergei/Documents/neural Network, tensorflow.py", line 52, in train_neural_network
    prediction = neural_network_model(x)
  File "/Users/sergei/Documents/neural Network, tensorflow.py", line 39, in neural_network_model
    l2 = tf.add(tf.matmul(data, hidden_2_layer['weights']),  hidden_2_layer['biases'])

到

---

应该是“tmp”而不是“tmpp”很酷，谢谢你修复了一点！我该怎么办？我又犯了一个错误！

Traceback (most recent call last):
  File "/Users/sergei/Documents/neural Network, tensorflow.py", line 79, in <module>
    train_neural_network(x)
  File "/Users/sergei/Documents/neural Network, tensorflow.py", line 52, in train_neural_network
    prediction = neural_network_model(x)
  File "/Users/sergei/Documents/neural Network, tensorflow.py", line 39, in neural_network_model
    l2 = tf.add(tf.matmul(data, hidden_2_layer['weights']),  hidden_2_layer['biases'])

l1 = tf.add(tf.matmul(data, hidden_1_layer['weights']), hidden_1_layer['biases'])
l1 = tf.nn.relu(l1)

# `data` should be l1 
l2 = tf.add(tf.matmul(data, hidden_2_layer['weights']),  hidden_2_layer['biases'])
l2 = tf.nn.relu(l2)

# same error is found here
l3 = tf.add(tf.matmul(data, hidden_3_layer['weights']), hidden_3_layer['biases'])
l3 = tf.nn.relu(l3)

output = tf.matmul(l3, output_layer['weight']) + output_layer['biases']

l1 = tf.add(tf.matmul(data, hidden_1_layer['weights']), hidden_1_layer['biases'])
l1 = tf.nn.relu(l1)

# data --> l1 
l2 = tf.add(tf.matmul(l1, hidden_2_layer['weights']),  hidden_2_layer['biases'])
l2 = tf.nn.relu(l2)

# data --> l2
l3 = tf.add(tf.matmul(l2, hidden_3_layer['weights']), hidden_3_layer['biases'])
l3 = tf.nn.relu(l3)

output = tf.matmul(l3, output_layer['weight']) + output_layer['biases']