希望您身体健康。实际上，我在自己构建的代码中遇到了问题。我是机器学习和神经网络领域的初学者。我建立了自己的神经网络，并尝试在tensorflow的帮助下训练数据集，但损失了很多，并且在打印我的准确性时遇到了一些问题，请查看代码谢谢！
这是我在kaggle上实现的代码：
# This Python 3 environment comes with many helpful analytics libraries installed
# It is defined by the kaggle/python docker image: https://github.com/kaggle/docker-python
# For example, here's several helpful packages to load in
import numpy as np # linear algebra
import pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)
from subprocess import check_output
from tensorflow.examples.tutorials.mnist import input_data
import tensorflow as tf
# Input data files are available in the "../input/" directory.
# For example, running this (by clicking run or pressing Shift+Enter) will list the files in the input directory
import os
print(os.listdir("../input"))
print(check_output(["ls", "../input"]).decode("utf8"))
mnist = input_data.read_data_sets('../input',one_hot=True)
x_train=mnist.train.images
y_train=mnist.train.labels
x_test=mnist.test.images
y_test=mnist.test.labels
# Any results you write to the current directory are saved as output.
layer1_neuron=500
layer2_neuron=500
layer3_neuron=500
number_of_class=10
batch_size=200
x=tf.placeholder('float',[None,784]) #28 * 28 is 784 (shape of the data)
y=tf.placeholder('float')
#my neural network
def neural_network(x_train):
hidden_layer_1={
'weights':tf.Variable(tf.random_normal([784,layer1_neuron])),
'biases': tf.Variable(tf.random_normal([layer1_neuron]))
}
hidden_layer_2={
'weights':tf.Variable(tf.random_normal([layer1_neuron,layer2_neuron])),
'biases':tf.Variable(tf.random_normal([layer2_neuron]))
}
hidden_layer_3={
'weights':tf.Variable(tf.random_normal([layer2_neuron,layer3_neuron])),
'biases':tf.Variable(tf.random_normal([layer3_neuron]))
}
output={
'weights':tf.Variable(tf.random_normal([layer3_neuron,number_of_class])),
'biases':tf.Variable(tf.random_normal([number_of_class]))
}
l1=tf.add(tf.matmul(x_train,hidden_layer_1['weights']),hidden_layer_1['biases'])
l1=tf.nn.relu(l1)
l2=tf.add(tf.matmul(l1,hidden_layer_2['weights']),hidden_layer_2['biases'])
l2=tf.nn.relu(l2)
l3=tf.add(tf.matmul(l2,hidden_layer_3['weights']),hidden_layer_3['biases'])
l3=tf.nn.relu(l3)
output=tf.add(tf.matmul(l3,output['weights']),output['biases'])
return output
# for splitting out batches of data
def next_batch(num, data, labels):
idx = np.arange(0 , len(data))
np.random.shuffle(idx)
idx = idx[:num]
data_shuffle = [data[ i] for i in idx]
labels_shuffle = [labels[ i] for i in idx]
return np.asarray(data_shuffle), np.asarray(labels_shuffle)
def traning_neuralNetwork(x_test,x_train,y_test,y_train):
total_epochs=5
total_loss=0
epoch_loss=0
batch_size=200
num_batch = int(np.ceil(42000/batch_size))
prediction=[]
prediction=neural_network(x_train)
cost=tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(logits=prediction,labels=y_train))
optimizer=tf.train.AdamOptimizer().minimize(cost)
with tf.Session() as sess:
sess.run(tf.global_variables_initializer())
for epoch in range (total_epochs):
epoch_loss=0
for _ in range (num_batch):
x_train,y_train=next_batch(batch_size,x_train,y_train)
_,epoch_loss=sess.run([optimizer,cost],feed_dict={x:x_train,y:y_train})
total_loss+=epoch_loss
print('Epoch ',epoch, " loss = ",total_loss)
print("Traning Complete!")
correct=tf.equal(tf.argmax(prediction,1),tf.argmax(y,1))
accuracy=tf.reduce_mean(tf.cast(correct,'float'))
print('accuracy',accuracy.eval({x : x_test,y : y_test}))
traning_neuralNetwork(x_test,x_train,y_test,y_train)
输出错误
WARNING:tensorflow:From <ipython-input-3-92b45e11aa74>:61: softmax_cross_entropy_with_logits (from tensorflow.python.ops.nn_ops) is deprecated and will be removed in a future version.
Instructions for updating:
Future major versions of TensorFlow will allow gradients to flow
into the labels input on backprop by default.
See tf.nn.softmax_cross_entropy_with_logits_v2.
Epoch 0 loss = 968685.6919555664
Epoch 1 loss = 1076421.9005126953
Epoch 2 loss = 1108946.4575500488
Epoch 3 loss = 1117600.8527259827
Epoch 4 loss = 1119452.7342455387
Traning Complete!
---------------------------------------------------------------------------
InvalidArgumentError Traceback (most recent call last)
/opt/conda/lib/python3.6/site-packages/tensorflow/python/client/session.py in _do_call(self, fn, *args)
1329 try:
-> 1330 return fn(*args)
1331 except errors.OpError as e:
/opt/conda/lib/python3.6/site-packages/tensorflow/python/client/session.py in _run_fn(feed_dict, fetch_list, target_list, options, run_metadata)
1314 return self._call_tf_sessionrun(
-> 1315 options, feed_dict, fetch_list, target_list, run_metadata)
1316
/opt/conda/lib/python3.6/site-packages/tensorflow/python/client/session.py in _call_tf_sessionrun(self, options, feed_dict, fetch_list, target_list, run_metadata)
1422 self._session, options, feed_dict, fetch_list, target_list,
-> 1423 status, run_metadata)
1424
/opt/conda/lib/python3.6/site-packages/tensorflow/python/framework/errors_impl.py in __exit__(self, type_arg, value_arg, traceback_arg)
515 compat.as_text(c_api.TF_Message(self.status.status)),
--> 516 c_api.TF_GetCode(self.status.status))
517 # Delete the underlying status object from memory otherwise it stays alive
InvalidArgumentError: Incompatible shapes: [55000] vs. [10000]
[[Node: Equal = Equal[T=DT_INT64, _device="/job:localhost/replica:0/task:0/device:GPU:0"](ArgMax, ArgMax_1)]]
During handling of the above exception, another exception occurred:
InvalidArgumentError Traceback (most recent call last)
<ipython-input-4-6ce6d479d3df> in <module>()
1
2
----> 3 traning_neuralNetwork(x_test,x_train,y_test,y_train)
<ipython-input-3-92b45e11aa74> in traning_neuralNetwork(x_test, x_train, y_test, y_train)
75 correct=tf.equal(tf.argmax(prediction,1),tf.argmax(y,1))
76 accuracy=tf.reduce_mean(tf.cast(correct,'float'))
---> 77 print('accuracy',accuracy.eval({x : x_test,y : y_test}))
78
79
/opt/conda/lib/python3.6/site-packages/tensorflow/python/framework/ops.py in eval(self, feed_dict, session)
659
660 """
--> 661 return _eval_using_default_session(self, feed_dict, self.graph, session)
662
663
/opt/conda/lib/python3.6/site-packages/tensorflow/python/framework/ops.py in _eval_using_default_session(tensors, feed_dict, graph, session)
5061 "the tensor's graph is different from the session's "
5062 "graph.")
-> 5063 return session.run(tensors, feed_dict)
5064
5065
/opt/conda/lib/python3.6/site-packages/tensorflow/python/client/session.py in run(self, fetches, feed_dict, options, run_metadata)
906 try:
907 result = self._run(None, fetches, feed_dict, options_ptr,
--> 908 run_metadata_ptr)
909 if run_metadata:
910 proto_data = tf_session.TF_GetBuffer(run_metadata_ptr)
/opt/conda/lib/python3.6/site-packages/tensorflow/python/client/session.py in _run(self, handle, fetches, feed_dict, options, run_metadata)
1141 if final_fetches or final_targets or (handle and feed_dict_tensor):
1142 results = self._do_run(handle, final_targets, final_fetches,
-> 1143 feed_dict_tensor, options, run_metadata)
1144 else:
1145 results = []
/opt/conda/lib/python3.6/site-packages/tensorflow/python/client/session.py in _do_run(self, handle, target_list, fetch_list, feed_dict, options, run_metadata)
1322 if handle is None:
1323 return self._do_call(_run_fn, feeds, fetches, targets, options,
-> 1324 run_metadata)
1325 else:
1326 return self._do_call(_prun_fn, handle, feeds, fetches)
/opt/conda/lib/python3.6/site-packages/tensorflow/python/client/session.py in _do_call(self, fn, *args)
1341 except KeyError:
1342 pass
-> 1343 raise type(e)(node_def, op, message)
1344
1345 def _extend_graph(self):
InvalidArgumentError: Incompatible shapes: [55000] vs. [10000]
[[Node: Equal = Equal[T=DT_INT64, _device="/job:localhost/replica:0/task:0/device:GPU:0"](ArgMax, ArgMax_1)]]
Caused by op 'Equal', defined at:
File "/opt/conda/lib/python3.6/runpy.py", line 193, in _run_module_as_main
"__main__", mod_spec)
File "/opt/conda/lib/python3.6/runpy.py", line 85, in _run_code
exec(code, run_globals)
File "/opt/conda/lib/python3.6/site-packages/ipykernel_launcher.py", line 16, in <module>
app.launch_new_instance()
File "/opt/conda/lib/python3.6/site-packages/traitlets/config/application.py", line 658, in launch_instance
app.start()
File "/opt/conda/lib/python3.6/site-packages/ipykernel/kernelapp.py", line 477, in start
ioloop.IOLoop.instance().start()
File "/opt/conda/lib/python3.6/site-packages/zmq/eventloop/ioloop.py", line 177, in start
super(ZMQIOLoop, self).start()
File "/opt/conda/lib/python3.6/site-packages/tornado/ioloop.py", line 888, in start
handler_func(fd_obj, events)
File "/opt/conda/lib/python3.6/site-packages/tornado/stack_context.py", line 277, in null_wrapper
return fn(*args, **kwargs)
File "/opt/conda/lib/python3.6/site-packages/zmq/eventloop/zmqstream.py", line 440, in _handle_events
self._handle_recv()
File "/opt/conda/lib/python3.6/site-packages/zmq/eventloop/zmqstream.py", line 472, in _handle_recv
self._run_callback(callback, msg)
File "/opt/conda/lib/python3.6/site-packages/zmq/eventloop/zmqstream.py", line 414, in _run_callback
callback(*args, **kwargs)
File "/opt/conda/lib/python3.6/site-packages/tornado/stack_context.py", line 277, in null_wrapper
return fn(*args, **kwargs)
File "/opt/conda/lib/python3.6/site-packages/ipykernel/kernelbase.py", line 283, in dispatcher
return self.dispatch_shell(stream, msg)
File "/opt/conda/lib/python3.6/site-packages/ipykernel/kernelbase.py", line 235, in dispatch_shell
handler(stream, idents, msg)
File "/opt/conda/lib/python3.6/site-packages/ipykernel/kernelbase.py", line 399, in execute_request
user_expressions, allow_stdin)
File "/opt/conda/lib/python3.6/site-packages/ipykernel/ipkernel.py", line 196, in do_execute
res = shell.run_cell(code, store_history=store_history, silent=silent)
File "/opt/conda/lib/python3.6/site-packages/ipykernel/zmqshell.py", line 533, in run_cell
return super(ZMQInteractiveShell, self).run_cell(*args, **kwargs)
File "/opt/conda/lib/python3.6/site-packages/IPython/core/interactiveshell.py", line 2698, in run_cell
interactivity=interactivity, compiler=compiler, result=result)
File "/opt/conda/lib/python3.6/site-packages/IPython/core/interactiveshell.py", line 2808, in run_ast_nodes
if self.run_code(code, result):
File "/opt/conda/lib/python3.6/site-packages/IPython/core/interactiveshell.py", line 2862, in run_code
exec(code_obj, self.user_global_ns, self.user_ns)
File "<ipython-input-4-6ce6d479d3df>", line 3, in <module>
traning_neuralNetwork(x_test,x_train,y_test,y_train)
File "<ipython-input-3-92b45e11aa74>", line 75, in traning_neuralNetwork
correct=tf.equal(tf.argmax(prediction,1),tf.argmax(y,1))
File "/opt/conda/lib/python3.6/site-packages/tensorflow/python/ops/gen_math_ops.py", line 2455, in equal
"Equal", x=x, y=y, name=name)
File "/opt/conda/lib/python3.6/site-packages/tensorflow/python/framework/op_def_library.py", line 787, in _apply_op_helper
op_def=op_def)
File "/opt/conda/lib/python3.6/site-packages/tensorflow/python/framework/ops.py", line 3306, in create_op
op_def=op_def)
File "/opt/conda/lib/python3.6/site-packages/tensorflow/python/framework/ops.py", line 1669, in __init__
self._traceback = self._graph._extract_stack() # pylint: disable=protected-access
InvalidArgumentError (see above for traceback): Incompatible shapes: [55000] vs. [10000]
[[Node: Equal = Equal[T=DT_INT64, _device="/job:localhost/replica:0/task:0/device:GPU:0"](ArgMax, ArgMax_1)]]
答案 0 :(得分：0)
您的数据矩阵是大小为（48000 * 28 * 28 * 1）的大于784,500的4D数组。 顺便说一句，32,928,000实际上是28 * 28 * 42000，可能X_train矩阵具有不同的形状。 您可以添加print（X_train.shape [0]）并仔细检查矩阵吗？
要解决GraphDef的问题，请查看以下响应： https://stackoverflow.com/a/36358913/4601719
tf.initialize_all_variables已贬值，请按照此处的建议使用tf.global_variables_initializer：
https://www.tensorflow.org/api_docs/python/tf/initialize_all_variables