我在Kaggle内核上的手写A_Z数据集上使用Tensorflow。
我已经依次使用了2个conv层和2个maxpool，然后将上述层重塑为full_1（-1，* 7 * 7 * 64），然后将其重新设置为完全连接的层（full_2），我对其应用了dropout ），然后将其连接到名为shape的最后一层（无，26），最后得到代表26个英文字母的预测输出。
CONV-> MAXPOOL-> CONV-> MAXPOOL->重塑（命名为full_1）-> FULLY_CONNECTED（full_2）-> OUTPUT（last）
较早（有时回溯）跑步的训练过程给出了准确性的数值，但后来由于某些未知原因而开始给出NaNs。
此外，准确性的数值在整个训练过程中从未增加太多，并且保持在非常低的水平，这使我担心我是否正确地应用了卷积网络，因为随着数据批次的增加，网络应该只能更好地学习以提供更高的准确性处理到培训过程中。是因为层数少，模型复杂度低而导致准确性降低吗？
此外，我对代码中的tf.nn.softmax_cross_entropy_with_logits（labels = output，logits = last）语句感到怀疑，因为relu函数已应用于last变量，该变量表示我的输出层转换网并在上面用作登录。
错误提示：
FailedPreconditionError: Attempting to use uninitialized value W_4
代码是：
import tensorflow as tf
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
from sklearn.model_selection import train_test_split
from sklearn import preprocessing
import copy
import warnings
warnings.filterwarnings('ignore')
#dataset=pd.read_csv('/Users/ajay/Documents/IpyNote/A_Z Handwritten Data.csv')
dataset=pd.read_csv('../input/handwritten_data_785.csv')
#print(dataset.head(3))
#print(dataset.info())
dataset['0'].unique()
dataset=dataset.astype('float32')
X=copy.deepcopy(dataset)
X.head(1)
Y=X.loc[:,'0']
#print(Y.head(3))
Y=Y.astype('int64')
s=pd.get_dummies(Y)
list(s)
Y=s
Y=Y.astype('float32')
Y.head(2)
X.drop('0',axis=1,inplace=True)
X_train,X_test,Y_train,Y_test=train_test_split(X,Y,test_size=0.25,stratify=Y)
input=tf.placeholder(dtype=tf.float32,shape=(None,28*28))
output=tf.placeholder(dtype=tf.float32,shape=(None,26))
W1=tf.Variable(tf.truncated_normal(shape=(5,5,1,32)),name='W')#28,28,32
b1=tf.Variable(tf.truncated_normal(shape=(1,32)),name='b')#14,14,32
W2=tf.Variable(tf.truncated_normal(shape=(5,5,32,64)),name='W')#14,14,64
b2=tf.Variable(tf.truncated_normal(shape=(1,64)),name='b')#7,7,64
W3=tf.Variable(tf.truncated_normal(shape=(7*7*64,1024)),name='W')
b3=tf.Variable(tf.truncated_normal(shape=(1,1024)),name='b')
W4=tf.Variable(tf.truncated_normal(shape=(1024,26)),name='W')
b4=tf.Variable(tf.truncated_normal(shape=(1,26)),name='b')
def conv(input,W,b):
return tf.nn.relu(tf.nn.conv2d(input=input,filter=W,strides=(1,1,1,1),padding='SAME')+b)
def maxpool(x):
return tf.nn.max_pool(value=x,ksize=(1,2,2,1),strides=(1,2,2,1),padding='SAME')
def full_connected(x,W,b):
return tf.nn.relu(tf.matmul(x,W)+b)
p=tf.reshape(input,[-1,28,28,1])
conv_1=conv(p,W1,b1)
print('conv_1.shape',conv_1.shape)
maxpool_1=maxpool(conv_1)
print('maxpool_1.shape',maxpool_1.shape)
conv_2=conv(maxpool_1,W2,b2)
print('conv_2.shape',conv_2.shape)
maxpool_2=maxpool(conv_2)
print('maxpool_2.shape',maxpool_2.shape)
full_1=tf.reshape(maxpool_2,[-1,7*7*64])
full_2=full_connected(full_1,W3,b3)#full_1->full_2
print('full_2.shape',full_2.shape)
keep_prob=tf.placeholder(tf.float32)
full_2_dropout=tf.nn.dropout(full_2,keep_prob)
last=full_connected(full_2_dropout,W4,b4)
last = tf.clip_by_value(last, 1e-10, 0.9999999)
print('last.shape',last.shape)
loss=tf.nn.softmax_cross_entropy_with_logits(labels=output,logits=last)#loss=tf.nn.softmax(logits=last)
train_step=tf.train.AdamOptimizer(0.005).minimize(loss)
accuracy=tf.reduce_mean(tf.cast(tf.equal(tf.argmax(output,1), tf.argmax(last,1) ) , tf.float32))
init=tf.global_variables_initializer()
with tf.Session() as sess:
epoch=1
n_iterations=10
sess.run(init)
for i in range(n_iterations):
j=i*50
k=i*50+50
print('j=',j,'k=',k)
x = X_train.iloc[i*50:j,:]
y = Y_train.iloc[i*50:j,:]
#sess.run(accuracy,feed_dict={input:X_train,output:Y_train,keep_prob:1.0})
print('Train_accuracy : ',sess.run(accuracy, feed_dict={input: x, output: y,keep_prob:1.0}))
sess.run(train_step,feed_dict={input:x,output:y,keep_prob:1.0})
with tf.Session() as sess:
n_iterations=20
for i in range(n_iterations):
j=i*50
k=i*50+50
print('j=',j,'k=',k)
x = X_test.iloc[i*50:j,:]
y = Y_test.iloc[i*50:j,:]
print('Test_accuracy : ',sess.run(accuracy, feed_dict={input: x, output: y,keep_prob:1.0}))
该错误显示如下内容：
conv_1.shape (?, 28, 28, 32)
maxpool_1.shape (?, 14, 14, 32)
conv_2.shape (?, 14, 14, 64)
maxpool_2.shape (?, 7, 7, 64)
full_2.shape (?, 1024)
last.shape (?, 26)
j= 0 k= 50
Train_accuracy : nan
j= 50 k= 100
Train_accuracy : nan
j= 100 k= 150
Train_accuracy : nan
j= 150 k= 200
Train_accuracy : nan
j= 200 k= 250
Train_accuracy : nan
j= 250 k= 300
Train_accuracy : nan
j= 300 k= 350
Train_accuracy : nan
j= 350 k= 400
Train_accuracy : nan
j= 400 k= 450
Train_accuracy : nan
j= 450 k= 500
Train_accuracy : nan
j= 0 k= 50
---------------------------------------------------------------------------
FailedPreconditionError 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
FailedPreconditionError: Attempting to use uninitialized value W_4
[[Node: W_4/read = Identity[T=DT_FLOAT, _class=["loc:@W_4"], _device="/job:localhost/replica:0/task:0/device:GPU:0"](W_4)]]
During handling of the above exception, another exception occurred:
FailedPreconditionError Traceback (most recent call last)
<ipython-input-2-496ec024fd3b> in <module>()
114 x = X_test.iloc[i*50:j,:]
115 y = Y_test.iloc[i*50:j,:]
--> 116 print('Test_accuracy : ',sess.run(accuracy, feed_dict={input: x, output: y,keep_prob:1.0}))
/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):
FailedPreconditionError: Attempting to use uninitialized value W_4
[[Node: W_4/read = Identity[T=DT_FLOAT, _class=["loc:@W_4"], _device="/job:localhost/replica:0/task:0/device:GPU:0"](W_4)]]
Caused by op 'W_4/read', 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 2802, 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-2-496ec024fd3b>", line 42, in <module>
W1=tf.Variable(tf.truncated_normal(shape=(5,5,1,32)),name='W')#28,28,32
File "/opt/conda/lib/python3.6/site-packages/tensorflow/python/ops/variables.py", line 235, in __init__
constraint=constraint)
File "/opt/conda/lib/python3.6/site-packages/tensorflow/python/ops/variables.py", line 397, in _init_from_args
self._snapshot = array_ops.identity(self._variable, name="read")
File "/opt/conda/lib/python3.6/site-packages/tensorflow/python/ops/array_ops.py", line 142, in identity
return gen_array_ops.identity(input, name=name)
File "/opt/conda/lib/python3.6/site-packages/tensorflow/python/ops/gen_array_ops.py", line 3052, in identity
"Identity", input=input, 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
FailedPreconditionError (see above for traceback): Attempting to use uninitialized value W_4
[[Node: W_4/read = Identity[T=DT_FLOAT, _class=["loc:@W_4"], _device="/job:localhost/replica:0/task:0/device:GPU:0"](W_4)]]
答案 0 :(得分：3)
给出NaNs的准确性的原因：您已经将训练数据分为X_train和X_test，这是由于它们的索引受到干扰，并且火车数据集相对于索引变得相当随机，并且当您分批喂X_train时，索引从[0:50]开始训练时不存在，因此您最终没有为模型提供任何东西。
在训练模型之前，请执行以下操作：
X_test.reset_index(drop=True)
Y_test.reset_index(drop=True)
这将重置您的索引，而drop=True将阻止原始索引成为转换后的数据框中的另一列。
就Weights和Biases而言，请勿使用另一个会话来测试模型，因为您所有训练后的变量都将在此会话中丢失，因此错误Attempting to use uninitialized value W_4会发生。
为了方便起见，您也可以尝试保存变量。
另外，请在您的logits部分参考此内容：here
答案 1 :(得分：0)
您可以调用：sess.run(tf.global_variables_initializer())初始化变量。有关初始化程序的更多信息，请参见此StackOverflow answer。