当我尝试训练我的CNN用于识别Python Tensorflow中的猫和狗图像时，第一个纪元被成功执行但后来出现了错误。如果有人请帮忙解决这个问题。我跟着博客，然后继续调整他们习惯的CNN解决我的问题，但它没有很好地解决。
还有一个dataset.py文件，用于加载猫和狗的数据进行训练。我想这个错误可能是由于最新的Tensorflow更新根据我在谷歌上看到的，但我不确定，因为我是CNN类型的神经网络的初学者。
命令行日志：
Training Epoch 1 --- Training Accuracy: 50.0%, Validation Accuracy: 43.8%,
Validation Loss: 0.703
2018-03-05 17:14:34.438263: W c:\l\tensorflow_1501918863922\work\tensorflow-
1.2.1\tensorflow\core\framework\op_kernel.cc:1158] Not found: Failed to
create a directory:
Traceback (most recent call last):
File "C:\Users\Diti\Miniconda3\envs\diti\lib\site-
packages\tensorflow\python\client\session.py", line 1139, in _do_call
return fn(*args)
File "C:\Users\Diti\Miniconda3\envs\diti\lib\site-
packages\tensorflow\python\client\session.py", line 1121, in _run_fn
status, run_metadata)
File "C:\Users\Diti\Miniconda3\envs\diti\lib\contextlib.py", line 88, in __
_exit__
next(self.gen)
File "C:\Users\Diti\Miniconda3\envs\diti\lib\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.NotFoundError: Failed to create a
directory:
[[Node: save/SaveV2 = SaveV2[dtypes=[DT_FLOAT, DT_FLOAT, DT_FLOAT,
DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_FLOAT,
DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_FLOAT,
DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_FLOAT,
DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_FLOAT,
DT_FLOAT], _device="/job:localhost/replica:0/task:0/cpu:0"]
(_arg_save/Const_0_0, save/SaveV2/tensor_names,
save/SaveV2/shape_and_slices, Variable, Variable/Adam, Variable/Adam_1,
Variable_1, Variable_1/Adam, Variable_1/Adam_1, Variable_2, Variable_2/Adam,
Variable_2/Adam_1, Variable_3, Variable_3/Adam, Variable_3/Adam_1,
Variable_4, Variable_4/Adam, Variable_4/Adam_1, Variable_5, Variable_5/Adam,
Variable_5/Adam_1, Variable_6, Variable_6/Adam, Variable_6/Adam_1,
Variable_7, Variable_7/Adam, Variable_7/Adam_1, Variable_8, Variable_8/Adam,
Variable_8/Adam_1, Variable_9, Variable_9/Adam, Variable_9/Adam_1,
beta1_power, beta2_power)]]
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "C:\Users\Diti\Miniconda3\envs\diti\lib\site-
packages\tensorflow\python\training\saver.py", line 1472, in save
{self.saver_def.filename_tensor_name: checkpoint_file})
File "C:\Users\Diti\Miniconda3\envs\diti\lib\site-
packages\tensorflow\python\client\session.py", line 789, in run
run_metadata_ptr)
File "C:\Users\Diti\Miniconda3\envs\diti\lib\site-
packages\tensorflow\python\client\session.py", line 997, in _run
feed_dict_string, options, run_metadata)
File "C:\Users\Diti\Miniconda3\envs\diti\lib\site-
packages\tensorflow\python\client\session.py", line 1132, in _do_run
target_list, options, run_metadata)
File "C:\Users\Diti\Miniconda3\envs\diti\lib\site-
packages\tensorflow\python\client\session.py", line 1152, in _do_call
raise type(e)(node_def, op, message)
tensorflow.python.framework.errors_impl.NotFoundError: Failed to create a
directory:
[[Node: save/SaveV2 = SaveV2[dtypes=[DT_FLOAT, DT_FLOAT, DT_FLOAT,
DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_FLOAT,
DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_FLOAT,
DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_FLOAT,
DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_FLOAT,
DT_FLOAT], _device="/job:localhost/replica:0/task:0/cpu:0"]
(_arg_save/Const_0_0, save/SaveV2/tensor_names,
save/SaveV2/shape_and_slices, Variable, Variable/Adam, Variable/Adam_1,
Variable_1, Variable_1/Adam, Variable_1/Adam_1, Variable_2, Variable_2/Adam,
Variable_2/Adam_1, Variable_3, Variable_3/Adam, Variable_3/Adam_1,
Variable_4, Variable_4/Adam, Variable_4/Adam_1, Variable_5, Variable_5/Adam,
Variable_5/Adam_1, Variable_6, Variable_6/Adam, Variable_6/Adam_1,
Variable_7, Variable_7/Adam, Variable_7/Adam_1, Variable_8, Variable_8/Adam,
Variable_8/Adam_1, Variable_9, Variable_9/Adam, Variable_9/Adam_1,
beta1_power, beta2_power)]]
Caused by op 'save/SaveV2', defined at:
File "train.py", line 177, in <module>
saver = tf.train.Saver()
File "C:\Users\Diti\Miniconda3\envs\diti\lib\site-
packages\tensorflow\python\training\saver.py", line 1139, in __init__
self.build()
File "C:\Users\Diti\Miniconda3\envs\diti\lib\site-
packages\tensorflow\python\training\saver.py", line 1170, in build
restore_sequentially=self._restore_sequentially)
File "C:\Users\Diti\Miniconda3\envs\diti\lib\site-
packages\tensorflow\python\training\saver.py", line 689, in build
save_tensor = self._AddSaveOps(filename_tensor, saveables)
File "C:\Users\Diti\Miniconda3\envs\diti\lib\site-
packages\tensorflow\python\training\saver.py", line 276, in _AddSaveOps
save = self.save_op(filename_tensor, saveables)
File "C:\Users\Diti\Miniconda3\envs\diti\lib\site-
packages\tensorflow\python\training\saver.py", line 219, in save_op
tensors)
File "C:\Users\Diti\Miniconda3\envs\diti\lib\site-
packages\tensorflow\python\ops\gen_io_ops.py", line 745, in save_v2
tensors=tensors, name=name)
File "C:\Users\Diti\Miniconda3\envs\diti\lib\site-
packages\tensorflow\python\framework\op_def_library.py", line 767, in
apply_op
op_def=op_def)
File "C:\Users\Diti\Miniconda3\envs\diti\lib\site-
packages\tensorflow\python\framework\ops.py", line 2506, in create_op
original_op=self._default_original_op, op_def=op_def)
File "C:\Users\Diti\Miniconda3\envs\diti\lib\site-
packages\tensorflow\python\framework\ops.py", line 1269, in __init__
self._traceback = _extract_stack()
NotFoundError (see above for traceback): Failed to create a directory:
[[Node: save/SaveV2 = SaveV2[dtypes=[DT_FLOAT, DT_FLOAT, DT_FLOAT,
DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_FLOAT,
DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_FLOAT,
DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_FLOAT,
DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_FLOAT,
DT_FLOAT], _device="/job:localhost/replica:0/task:0/cpu:0"]
(_arg_save/Const_0_0, save/SaveV2/tensor_names,
save/SaveV2/shape_and_slices, Variable, Variable/Adam, Variable/Adam_1,
Variable_1, Variable_1/Adam, Variable_1/Adam_1, Variable_2, Variable_2/Adam,
Variable_2/Adam_1, Variable_3, Variable_3/Adam, Variable_3/Adam_1,
Variable_4, Variable_4/Adam, Variable_4/Adam_1, Variable_5, Variable_5/Adam,
Variable_5/Adam_1, Variable_6, Variable_6/Adam, Variable_6/Adam_1,
Variable_7, Variable_7/Adam, Variable_7/Adam_1, Variable_8, Variable_8/Adam,
Variable_8/Adam_1, Variable_9, Variable_9/Adam, Variable_9/Adam_1,
beta1_power, beta2_power)]]
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "train.py", line 205, in <module>
train(num_iteration=3000)
File "train.py", line 200, in train
saver.save(session, 'dogs-cats-model')
File "C:\Users\Diti\Miniconda3\envs\diti\lib\site-
packages\tensorflow\python\training\saver.py", line 1488, in save
raise exc
ValueError: Parent directory of dogs-cats-model doesn't exist, can't save.
mycode的：
import dataset
import tensorflow as tf
import time
from datetime import timedelta
import math
import random
import numpy as np
#Adding Seed so that random initialization is consistent
from numpy.random import seed
seed(1)
from tensorflow import set_random_seed
set_random_seed(2)
batch_size = 32
#Prepare input data
classes = ['dogs','cats']
num_classes = len(classes)
# 20% of the data will automatically be used for validation
validation_size = 0.2
img_size = 128
num_channels = 3
train_path='training_data'
# We shall load all the training and validation images and labels into
memory using openCV and use that during training
data = dataset.read_train_sets(train_path, img_size, classes,
validation_size=validation_size)
print("Complete reading input data. Will Now print a snippet of it")
print("Number of files in Training-
set:\t\t{}".format(len(data.train.labels)))
print("Number of files in Validation-
set:\t{}".format(len(data.valid.labels)))
session = tf.Session()
x = tf.placeholder(tf.float32, shape=[None, img_size,img_size,num_channels],
name='x')
## labels
y_true = tf.placeholder(tf.float32, shape=[None, num_classes],
name='y_true')
y_true_cls = tf.argmax(y_true, dimension=1)
##Network graph params
filter_size_conv1 = 3
num_filters_conv1 = 32
filter_size_conv2 = 3
num_filters_conv2 = 32
filter_size_conv3 = 3
num_filters_conv3 = 64
fc_layer_size = 128
def create_weights(shape):
return tf.Variable(tf.truncated_normal(shape, stddev=0.05))
def create_biases(size):
return tf.Variable(tf.constant(0.05, shape=[size]))
def create_convolutional_layer(input,
num_input_channels,
conv_filter_size,
num_filters):
## We shall define the weights that will be trained using create_weights
function.
weights = create_weights(shape=[conv_filter_size, conv_filter_size,
num_input_channels, num_filters])
## We create biases using the create_biases function. These are also
trained.
biases = create_biases(num_filters)
## Creating the convolutional layer
layer = tf.nn.conv2d(input=input,
filter=weights,
strides=[1, 1, 1, 1],
padding='SAME')
layer += biases
## We shall be using max-pooling.
layer = tf.nn.max_pool(value=layer,
ksize=[1, 2, 2, 1],
strides=[1, 2, 2, 1],
padding='SAME')
## Output of pooling is fed to Relu which is the activation function for us.
layer = tf.nn.relu(layer)
return layer
def create_flatten_layer(layer):
#We know that the shape of the layer will be [batch_size img_size img_size
num_channels]
# But let's get it from the previous layer.
layer_shape = layer.get_shape()
## Number of features will be img_height * img_width* num_channels. But we
shall calculate it in place of hard-coding it.
num_features = layer_shape[1:4].num_elements()
## Now, we Flatten the layer so we shall have to reshape to num_features
layer = tf.reshape(layer, [-1, num_features])
return layer
def create_fc_layer(input,
num_inputs,
num_outputs,
use_relu=True):
#Let's define trainable weights and biases.
weights = create_weights(shape=[num_inputs, num_outputs])
biases = create_biases(num_outputs)
# Fully connected layer takes input x and produces wx+b.Since, these are
matrices, we use matmul function in Tensorflow
layer = tf.matmul(input, weights) + biases
if use_relu:
layer = tf.nn.relu(layer)
return layer
layer_conv1 = create_convolutional_layer(input=x,
num_input_channels=num_channels,
conv_filter_size=filter_size_conv1,
num_filters=num_filters_conv1)
layer_conv2 = create_convolutional_layer(input=layer_conv1,
num_input_channels=num_filters_conv1,
conv_filter_size=filter_size_conv2,
num_filters=num_filters_conv2)
layer_conv3= create_convolutional_layer(input=layer_conv2,
num_input_channels=num_filters_conv2,
conv_filter_size=filter_size_conv3,
num_filters=num_filters_conv3)
layer_flat = create_flatten_layer(layer_conv3)
layer_fc1 = create_fc_layer(input=layer_flat,
num_inputs=layer_flat.get_shape()[1:4].num_elements(),
num_outputs=fc_layer_size,
use_relu=True)
layer_fc2 = create_fc_layer(input=layer_fc1,
num_inputs=fc_layer_size,
num_outputs=num_classes,
use_relu=False)
y_pred = tf.nn.softmax(layer_fc2,name='y_pred')
y_pred_cls = tf.argmax(y_pred, dimension=1)
session.run(tf.global_variables_initializer())
cross_entropy = tf.nn.softmax_cross_entropy_with_logits(logits=layer_fc2,
labels=y_true)
cost = tf.reduce_mean(cross_entropy)
optimizer = tf.train.AdamOptimizer(learning_rate=1e-4).minimize(cost)
correct_prediction = tf.equal(y_pred_cls, y_true_cls)
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
session.run(tf.global_variables_initializer())
def show_progress(epoch, feed_dict_train, feed_dict_validate, val_loss):
acc = session.run(accuracy, feed_dict=feed_dict_train)
val_acc = session.run(accuracy, feed_dict=feed_dict_validate)
msg = "Training Epoch {0} --- Training Accuracy: {1:>6.1%}, Validation
Accuracy: {2:>6.1%}, Validation Loss: {3:.3f}"
print(msg.format(epoch + 1, acc, val_acc, val_loss))
total_iterations = 0
saver = tf.train.Saver()
def train(num_iteration):
global total_iterations
for i in range(total_iterations,
total_iterations + num_iteration):
x_batch, y_true_batch, _, cls_batch = data.train.next_batch(batch_size)
x_valid_batch, y_valid_batch, _, valid_cls_batch =
data.valid.next_batch(batch_size)
feed_dict_tr = {x: x_batch,
y_true: y_true_batch}
feed_dict_val = {x: x_valid_batch,
y_true: y_valid_batch}
session.run(optimizer, feed_dict=feed_dict_tr)
if i % int(data.train.num_examples/batch_size) == 0:
val_loss = session.run(cost, feed_dict=feed_dict_val)
epoch = int(i / int(data.train.num_examples/batch_size))
show_progress(epoch, feed_dict_tr, feed_dict_val, val_loss)
saver.save(session, 'dogs-cats-model')
total_iterations += num_iteration
train(num_iteration=3000)
在显示进度之后，错误发生在行saver.save(session, 'dogs-cats-model')中。现在解决这个问题，将路径从'dogs-cats-model'更改为'./dogs-cats-model'。这应该解决它。