我正在尝试通过遵循2_fullyconnected.ipynb udacity分配将图像传递给我创建的模型。
我创建模型的代码如下所示。
# In[1]:
from __future__ import print_function
import numpy as np
import tensorflow as tf
from six.moves import cPickle as pickle
from six.moves import range
# First reload the data we generated in `1_notmnist.ipynb`.
# In[2]:
pickle_file = 'notMNIST.pickle'
with open(pickle_file, 'rb') as f:
save = pickle.load(f)
train_dataset = save['train_dataset']
train_labels = save['train_labels']
valid_dataset = save['valid_dataset']
valid_labels = save['valid_labels']
test_dataset = save['test_dataset']
test_labels = save['test_labels']
del save # hint to help gc free up memory
print('Training set', train_dataset.shape, train_labels.shape)
print('Validation set', valid_dataset.shape, valid_labels.shape)
print('Test set', test_dataset.shape, test_labels.shape)
print(train_dataset[0])
print(train_labels[0])
# Reformat into a shape that's more adapted to the models we're going to train:
# - data as a flat matrix,
# - labels as float 1-hot encodings.
# In[3]:
image_size = 28
num_labels = 10
def reformat(dataset, labels):
print(type(dataset))
#print(dataset[0])
dataset = dataset.reshape((-1, image_size * image_size)).astype(np.float32)
# Map 0 to [1.0, 0.0, 0.0 ...], 1 to [0.0, 1.0, 0.0 ...]
labels = (np.arange(num_labels) == labels[:,None]).astype(np.float32)
return dataset, labels
train_dataset, train_labels = reformat(train_dataset, train_labels)
valid_dataset, valid_labels = reformat(valid_dataset, valid_labels)
test_dataset, test_labels = reformat(test_dataset, test_labels)
print('Training set', train_dataset.shape, train_labels.shape)
print('Validation set', valid_dataset.shape, valid_labels.shape)
print('Test set', test_dataset.shape, test_labels.shape)
#stochastic gradient descent training
# In[7]:
batch_size = 128
graph = tf.Graph()
with graph.as_default():
# Input data. For the training data, we use a placeholder that will be fed
# at run time with a training minibatch.
tf_train_dataset = tf.placeholder(tf.float32,
shape=(batch_size, image_size * image_size))
tf_train_labels = tf.placeholder(tf.float32, shape=(batch_size, num_labels))
tf_valid_dataset = tf.constant(valid_dataset)
tf_test_dataset = tf.constant(test_dataset)
# Variables.
weights = tf.Variable(
tf.truncated_normal([image_size * image_size, num_labels]),name = "weights")
biases = tf.Variable(tf.zeros([num_labels]),name ="biases")
# Training computation.
logits = tf.matmul(tf_train_dataset, weights) + biases
loss = tf.reduce_mean(
tf.nn.softmax_cross_entropy_with_logits(logits, tf_train_labels))
# Optimizer.
optimizer = tf.train.GradientDescentOptimizer(0.5).minimize(loss)
# Predictions for the training, validation, and test data.
train_prediction = tf.nn.softmax(logits)
valid_prediction = tf.nn.softmax(
tf.matmul(tf_valid_dataset, weights) + biases)
test_prediction = tf.nn.softmax(tf.matmul(tf_test_dataset, weights) + biases)
# In[9]:
def accuracy(predictions, labels):
return (100.0 * np.sum(np.argmax(predictions, 1) == np.argmax(labels, 1))
/ predictions.shape[0])
# Let's run it:
# In[10]:
num_steps = 3001
with tf.Session(graph=graph) as session:
tf.initialize_all_variables().run()
print("Initialized")
for step in range(num_steps):
# Pick an offset within the training data, which has been randomized.
# Note: we could use better randomization across epochs.
offset = (step * batch_size) % (train_labels.shape[0] - batch_size)
# Generate a minibatch.
batch_data = train_dataset[offset:(offset + batch_size), :]
batch_labels = train_labels[offset:(offset + batch_size), :]
# Prepare a dictionary telling the session where to feed the minibatch.
# The key of the dictionary is the placeholder node of the graph to be fed,
# and the value is the numpy array to feed to it.
feed_dict = {tf_train_dataset : batch_data, tf_train_labels : batch_labels}
_, l, predictions = session.run(
[optimizer, loss, train_prediction], feed_dict=feed_dict)
if (step % 500 == 0):
print("Minibatch loss at step %d: %f" % (step, l))
print("Minibatch accuracy: %.1f%%" % accuracy(predictions, batch_labels))
print("Validation accuracy: %.1f%%" % accuracy(
valid_prediction.eval(), valid_labels))
print("Test accuracy: %.1f%%" % accuracy(test_prediction.eval(), test_labels))
save_path = tf.train.Saver().save(session, "/tmp/important_model/model.ckpt")
print("Model saved in file: %s" % save_path)
模型保存在/ tmp / important_model /.
中该文件夹的树结构如下：
important_model/
|-- checkpoint
|-- model.ckpt
`-- model.ckpt.meta
现在我正在创建一个新文件，我正在尝试恢复模型，然后将图像传递给模型进行分类。
我也在新的python文件中创建了图形，这对于恢复模型是必要的（我想，我可能是错的。如果我错了，请纠正我。）
# In[16]:
# These are all the modules we'll be using later. Make sure you can import them
# before proceeding further.
from __future__ import print_function
import numpy as np
import tensorflow as tf
from six.moves import cPickle as pickle
from six.moves import range
from scipy import ndimage
# In[17]:
image_size = 28
num_labels = 10
# In[25]:
# With gradient descent training, even this much data is prohibitive.
# Subset the training data for faster turnaround.
#train_subset = 1000
batch_size = 1
graph = tf.Graph()
with graph.as_default():
# Variables.
# These are the parameters that we are going to be training. The weight
# matrix will be initialized using random valued following a (truncated)
# normal distribution. The biases get initialized to zero.
# Variables.
#saver = tf.train.Saver()
weights = tf.Variable(
tf.truncated_normal([image_size * image_size, num_labels]),name = "weights")
biases = tf.Variable(tf.zeros([num_labels]),name ="biases")
tf_valid_dataset = tf.placeholder(tf.float32,
shape=(batch_size, image_size * image_size))
valid_prediction = tf.nn.softmax(
tf.matmul(tf_valid_dataset, weights) + biases)
# In[26]:
def accuracy(predictions, labels):
return (100.0 * np.sum(np.argmax(predictions, 1) == np.argmax(labels, 1))
/ predictions.shape[0])
# In[34]:
pixel_depth = 255
image_data = (ndimage.imread('notMNIST_small/A/QXJyaWJhQXJyaWJhU3RkLm90Zg==.png').astype(float) -
pixel_depth / 2) / pixel_depth
print(image_data.shape)
resized_data = image_data.reshape((-1,784))
print(resized_data.shape)
with tf.Session(graph=graph) as session:
tf.train.Saver().restore(session, "/tmp/important_model/model.ckpt")
print("Model restored.")
session.run(valid_prediction,feed_dict={tf_valid_dataset:resized_data})
当我在这个ipython笔记本中执行ln [34]时，即将出现的输出是：
(28, 28)
(1, 784)
Model restored
我想告诉给定图像可能属于的5个可能标签，但不知道如何操作，上述程序没有显示任何错误，但都没有显示所需的输出。我想我会得到图像在所有类中的概率，因为我在tf.nn.softmax函数中传递了我的图像，但遗憾的是没有得到任何东西。
任何帮助都将不胜感激。
答案 0 :(得分：2)
代码中的以下行计算数据集中每个图像的可能输出标签的概率分布（在本例中为单个图像）：
session.run(valid_prediction,feed_dict={tf_valid_dataset:resized_data})
此方法的结果是形状为(1, 10)的NumPy数组。要查看概率，您只需打印数组：
result = session.run(valid_prediction,feed_dict={tf_valid_dataset:resized_data})
print(result)
您可以通过多种方式获取图片的顶级 k 预测。最简单的方法之一是在定义图表时使用TensorFlow的tf.nn.top_k()运算符：
valid_prediction = tf.nn.softmax(tf.matmul(tf_valid_dataset, weights) + biases)
top_5_labels = tf.nn.top_k(valid_prediction, k=5)
# ...
result = session.run(top_5_labels, feed_dict={tf_valid_dataset: resized_data})
print(result)