Thanks for your help.
This question has bothered me for 2 days. I searched many sites and did not solve.
Background:
I am learning mnist, and it goes right at first, but when I save the model and restore, there is an Error, told me placeholder_1 must be fed. I am confused.
Code:
Below code goes right.
import tensorflow.examples.tutorials.mnist.input_data as input_data
mnist = input_data.read_data_sets("mnist data/", one_hot=True)
import tensorflow as tf
# 操作符号变量来描述这些可交互的操作单元
x = tf.placeholder(tf.float32, [None, 784])
# 权重值和偏置量
W = tf.Variable(tf.zeros([784,10]))
b = tf.Variable(tf.zeros([10]))
# 实现模型
y = tf.nn.softmax(tf.matmul(x,W) + b)
# 添加一个新的占位符用于输入正确值
y_ = tf.placeholder("float", [None,10])
# 计算交叉熵:
cross_entropy = -tf.reduce_sum(y_*tf.log(y))
# 要求TensorFlow用梯度下降算法（gradient descent algorithm）以0.01的学习速率最小化交叉熵
train_step = tf.train.GradientDescentOptimizer(0.01).minimize(cross_entropy)
# 添加一个操作来初始化我们创建的变量
init = tf.initialize_all_variables()
saver = tf.train.Saver()
sess = tf.Session()
sess.run(init)
for i in range(1000):
batch_xs, batch_ys = mnist.train.next_batch(100)
sess.run(train_step, feed_dict={x: batch_xs, y_: batch_ys})
save_path = saver.save(sess, "./model_mnist.ckpt",write_meta_graph=False)
print("Model saved in life:", save_path)
import cv2
import numpy as np
img = cv2.imread('lena.png')
img = cv2.resize(img, (28,28))
img = cv2.cvtColor(img,cv2.COLOR_RGB2GRAY)
arr = []
for i in range(28):
for j in range(28):
gray = 1 - img[i,j]/255
arr.append(gray)
arr_mnist = np.array([arr])
#print(arr_mnist)
result = sess.run(y, feed_dict={x:arr_mnist})
print(result)
#print(np.argmax(result[0]))
#print(np.sum(result[0]))
print("预测值为：",np.argmax(result[0]),"；概率为：",np.max(result[0])/np.sum(result[0]))
#print(tf.argmax(result,1))
But, when I want to use the model to restore. it goes wrong.
import cv2
import numpy as np
import tensorflow as tf
img = cv2.imread('lena.png')
img = cv2.resize(img, (28,28))
img = cv2.cvtColor(img,cv2.COLOR_RGB2GRAY)
arr = []
for i in range(28):
for j in range(28):
gray = 1 - img[i,j]/255
arr.append(gray)
arr_mnist = np.array([arr])
#print(arr_mnist)
tf.reset_default_graph()
x = tf.placeholder("float", shape=[None, 784])
y = tf.placeholder("float", shape=[None, 10])
#keep_prob = tf.placeholder("float")
sess = tf.Session()
saver = tf.train.import_meta_graph('./model_mnist.ckpt.meta')
saver.restore(sess, './model_mnist.ckpt')
result = sess.run(y, feed_dict={x:arr_mnist})
print(result)
print("预测值为：",np.argmax(result[0]),"；概率为：",np.max(result[0])/np.sum(result[0]))
the Error is :
InvalidArgumentError (see above for traceback): You must feed a value for placeholder tensor 'Placeholder_1' with dtype float and shape [?,10]
[[Node: Placeholder_1 = Placeholder[dtype=DT_FLOAT, shape=[?,10], _device="/job:localhost/replica:0/task:0/device:CPU:0"]()]]
so, I suppose the problem should be in the model save or restore process, but I cannot figure out.
how can I correct the code? thank you!
When restoring the graph, you are declaring two placeholders, and only feed one when running the session. The y placeholder is the one matching the error name.
But you do not need to declare these placeholders in the run script. The restoration takes care of it. Note that you can specify the feed dictionary with string keys:
feed_dict: { 'x': [1,2,3] }
Related
I have trained a deep CNN that predicts a one-dimentional array and saved the weight variables in the format of .ckpt. But when I give the model new inputs, it always outputs the same array. I have already check the preprocess of the inputs and I'm sure they are alright. Here is the code of my prediction.
import pandas as pd
import numpy as np
import os
import tensorflow as tf
sess = tf.Session()
sess.run(tf.global_variables_initializer())
filename = os.listdir("D:/project/test datasets/image")
new_dir = "D:/project/test datasets/"
for img in filename:
img=os.path.splitext(img)[0]
xs = pd.read_csv(new_dir+img+'.csv',index_col=0)
xs = xs.values.flatten()
xs = np.expand_dims(xs,0)
saver = tf.train.import_meta_graph('model.ckpt.meta')
saver.restore(sess, 'model.ckpt')
graph = tf.get_default_graph()
x = graph.get_tensor_by_name("x:0")
keep_prob = graph.get_tensor_by_name("keep_prob:0")
y_conv = graph.get_tensor_by_name("y_conv:0")
print(sess.run(y_conv,feed_dict={x:xs,keep_prob:1.0}))
And I also find that when I add the code statement y_conv = tf.constant(0) in the end of the loop, the following output will all be 0, which means my prediction y_conv doesn't update in each loop.
I have no idea where is wrong. Any feedback or advice would be greatly appreciated.
Your code looks fine to me. Please can you try in the below format
with tf.Session() as sess:
saver = tf.train.import_meta_graph(savefile)
saver.restore(sess, tf.train.latest_checkpoint(savedir))
graph = tf.get_default_graph()
input_x = graph.get_tensor_by_name("input_x:0")
result = graph.get_tensor_by_name("result:0")
feed_dict = {input_x: x_data,}
predictions = result.eval(feed_dict=feed_dict)
I am running a simple neural network for linear regression. However TensorFlow is complaining that my feed_dict placeholder(s) are not an element of the graph. However my placeholders and my model are all defined within my graph as can be seen below:
import numpy as np
import tensorflow as tf
from tensorflow.keras.layers import Dense
with tf.Graph().as_default():
x = tf.placeholder(dtype=tf.float32, shape = (None,4))
y = tf.placeholder(dtype=tf.float32, shape = (None,4))
model = tf.keras.Sequential([
Dense(units=4, activation=tf.nn.relu)
])
y = model(x)
loss = tf.reduce_mean(tf.square(y-x))
train_op = tf.train.AdamOptimizer().minimize(loss)
with tf.Session() as sess:
sess.run(train_op, feed_dict = {x:np.ones(dtype='float32', shape=(4)),
y:5*np.ones(dtype='float32', shape=(4,))})
This gives an error:
TypeError: Cannot interpret feed_dict key as Tensor: Tensor
Tensor("Placeholder:0", shape=(?, 4), dtype=float32) is not an element of this graph.
____________UPDATE________________
Following the advice from #Silgon and #Mcangus, I have modified the code:
g= tf.Graph()
with g.as_default():
x = tf.placeholder(dtype=tf.float32, shape = (None,4))
model = tf.keras.Sequential([
Dense(units=4, activation=tf.nn.relu)
])
y = model(x)
loss = tf.reduce_mean(tf.square(y-x))
train_op = tf.train.AdamOptimizer().minimize(loss)
init_op = tf.group(tf.global_variables_initializer(),
tf.local_variables_initializer())
with tf.Session(graph=g) as sess:
sess.run(init_op)
for i in range(5):
_ , answer = sess.run([train_op,loss], feed_dict = {x:np.ones(dtype='float32', shape=(1,4)),
y:5*np.ones(dtype='float32', shape=(1,4))})
print(answer)
However the model doesn't appear to be learning:
16.0
16.0
16.0
16.0
16.0
The error tells you that the variable is not an element of the graph. It might be because it's not in the same scope. One way to solve it is to have a structure like the following.
# define a graph
graph = tf.Graph()
with graph.as_default():
# placeholder
x = tf.placeholder(...)
y = tf.placeholder(...)
# create model
model = create_model(x, w, b)
with tf.Session(graph=graph) as sess:
# initialize all the variables
sess.run(init)
Also, as #Mcangus points out, be careful with the definition of your variables.
I believe your issue is this line:
y = model(x)
You overwrite y with the output of your model so it's no longer a placeholder.
I've built a neural network that performs reasonably well, and I'd like to replicate my model in a non-Python environment. I set up my network as follows:
sess = tf.InteractiveSession()
x = tf.placeholder(tf.float32, shape=[None, 23])
y_ = tf.placeholder(tf.float32, shape=[None, 2])
W = tf.Variable(tf.zeros([23,2]))
b = tf.Variable(tf.zeros([2]))
sess.run(tf.initialize_all_variables())
y = tf.nn.softmax(tf.matmul(x,W) + b)
How can I obtain a decipherable .csv or .txt of my weights and biases?
EDIT: Below is my full script:
import csv
import numpy
import tensorflow as tf
data = list(csv.reader(open("/Users/sjayaram/developer/TestApp/out/production/TestApp/data.csv")))
[[float(j) for j in i] for i in data]
numpy.random.shuffle(data)
results=data
#delete results from data
data = numpy.delete(data, [23, 24], 1)
#delete data from results
results = numpy.delete(results, range(23), 1)
sess = tf.InteractiveSession()
x = tf.placeholder(tf.float32, shape=[None, 23])
y_ = tf.placeholder(tf.float32, shape=[None, 2])
W = tf.Variable(tf.zeros([23,2]))
b = tf.Variable(tf.zeros([2]))
sess.run(tf.initialize_all_variables())
y = tf.nn.softmax(tf.matmul(x,W) + b)
cross_entropy = tf.reduce_mean(-tf.reduce_sum(y_ * tf.log(y), reduction_indices=[1]))
train_step = tf.train.GradientDescentOptimizer(0.5).minimize(cross_entropy)
#train the model, saving 80 entries for testing
#batch-size: 40
for i in range(0, 3680, 40):
train_step.run(feed_dict={x: data[i:i+40], y_: results[i:i+40]})
correct_prediction = tf.equal(tf.argmax(y,1), tf.argmax(y_,1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
print(accuracy.eval(feed_dict={x: data[3680:], y_: results[3680:]}))
You can fetch the variables as NumPy arrays, and use numpy.savetxt() to write out the contents as text or CSV:
import numpy as np
W_val, b_val = sess.run([W, b])
np.savetxt("W.csv", W_val, delimiter=",")
np.savetxt("b.csv", b_val, delimiter=",")
Note that this is unlikely to give performance as good as using TensorFlow's native replication mechanisms, in the distributed runtime.
I'm following this tutorial:
https://www.tensorflow.org/versions/r0.9/tutorials/mnist/beginners/index.html#mnist-for-ml-beginners
What I want to be able to do is pass in a test image x - as a numpy array, and see the resulting softmax classification values - perhaps as another numpy array. Everything I can find online about testing tensor flow models works by passing in test values and test labels and the outputting the accuracy. In my case, I want to output the model labels just based on the test values.
This is what Im trying:
import tensorflow as tf
import numpy as np
from skimage import color,io
from tensorflow.examples.tutorials.mnist import input_data
mnist = input_data.read_data_sets("MNIST_data/", one_hot=True)
x = tf.placeholder(tf.float32, [None, 784])
W = tf.Variable(tf.zeros([784, 10]))
b = tf.Variable(tf.zeros([10]))
y = tf.nn.softmax(tf.matmul(x, W) + b)
y_ = tf.placeholder(tf.float32, [None, 10])
cross_entropy = tf.reduce_mean(-tf.reduce_sum(y_ * tf.log(y), reduction_indices=[1]))
train_step = tf.train.GradientDescentOptimizer(0.5).minimize(cross_entropy)
init = tf.initialize_all_variables()
sess = tf.Session()
sess.run(init)
for i in range(1000):
batch_xs, batch_ys = mnist.train.next_batch(100)
sess.run(train_step, feed_dict={x: batch_xs, y_: batch_ys})
#so now its trained successfully, and W and b should be the stored "model"
#now to load in a test image
greyscale_test = color.rgb2gray(io.imread('4.jpeg'))
greyscale_expanded = np.expand_dims(greyscale_test,axis=0) #now shape (1,28,28)
x = np.reshape(greyscale_expanded,(1,784)) #now same dimensions as mnist.train.images
#initialize the variable
init_op = tf.initialize_all_variables()
#run the graph
with tf.Session() as sess:
sess.run(init_op) #execute init_op
print (sess.run(feed_dict={x:x})) #this is pretty much just a shot in the dark. What would go here?
Right now it results in this:
TypeError Traceback (most recent call last)
<ipython-input-116-f232a17507fb> in <module>()
36 sess.run(init_op) #execute init_op
---> 37 print (sess.run(feed_dict={x:x})) #this is pretty much just a shot in the dark. What would go here?
TypeError: unhashable type: 'numpy.ndarray'
So when training, the sess.run is passed a train_step and a feed_dict. When I am trying to evaluate a tensor x, would this go in the feed dict? Would I even use sess.run?(seems I have to), but what would the train_step be? Is there a "test_step" or "evaluate_step"?
You're getting the TypeError because you are using a (mutable) numpy.ndarray as a key for your dictionary but the key should be a tf.placeholder and the value a numpy array.
The following adjustment fixes this problem:
x_placeholder = tf.placeholder(tf.float32, [None, 784])
# ...
x = np.reshape(greyscale_expanded,(1,784))
# ...
print(sess.run([inference_step], feed_dict={x_placeholder:x}))
If you just want to perform inference on your model, this will print a numpy array with the predictions.
If you want to evaluate your model (for example compute the accuracy) you also need to feed in the corresponding ground truth labels y as in:
accuracy = sess.run([accuracy_op], feed_dict={x_placeholder:x, y_placeholder:y}
In your case, the accuracy_op could be defined as follows:
correct_predictions = tf.equal(tf.argmax(predictions, 1), tf.cast(labels, tf.int64))
accuracy_op = tf.reduce_mean(tf.cast(correct_predictions, tf.float32))
Here, predictions is the output tensor of your model.
your tf.Session.run op needs a fetches
tf.Session.run(fetches, feed_dict=None, options=None, run_metadata=None)
https://www.tensorflow.org/versions/r0.9/api_docs/python/client.html#session-management
print (sess.run(train_step,feed_dict={x:x})) #but it also needs a feed_dict for y_
what do you mean with:
print the random values that we sample
i am new to neural networks.
i have gone through TensorFlow mninst ML Beginners
used tensorflow basic mnist tutorial
and trying to get prediction using external image
I have the updated the mnist example provided by tensorflow
On top of that i have added few things :
1. Saving trained models locally
2. loading the saved models.
3. preprocessing the image into 28 * 28.
i have attached the image for reference
1. while training the models, save it locally. So i can reuse it at any point of time.
2. once after training, loading the models.
3. creating an external image via gimp which contains any one values ranging from [0 - 9]
4. using opencv to convert the image into 28 * 28 image and reversing the bit as well.
5. Then trying to predict.
i am able to train the models and save it properly.
i am getting predictions which are not right.
Find my codes Below
TrainSimple.py
# Load MNIST Data
from tensorflow.examples.tutorials.mnist import input_data
mnist = input_data.read_data_sets("MNIST_data/", one_hot=True)
from random import randint
from scipy import misc
# Start TensorFlow InteractiveSession
import tensorflow as tf
sess = tf.InteractiveSession()
# Placeholders
x = tf.placeholder(tf.float32, shape=[None, 784])
y_ = tf.placeholder(tf.float32, shape=[None, 10])
# Variables
W = tf.Variable(tf.zeros([784,10]))
b = tf.Variable(tf.zeros([10]))
sess.run(tf.initialize_all_variables())
# Predicted Class and Cost Function
y = tf.nn.softmax(tf.matmul(x,W) + b)
cross_entropy = -tf.reduce_sum(y_*tf.log(y))
saver = tf.train.Saver() # defaults to saving all variables
# GradientDescentOptimizer
train_step = tf.train.GradientDescentOptimizer(0.01).minimize(cross_entropy)
# Train the Model
for i in range(40000):
if (i + 1) == 40000 :
saver.save(sess, "/Users/xxxx/Desktop/TensorFlow/"+"/model.ckpt", global_step=i)
batch = mnist.train.next_batch(50)
train_step.run(feed_dict={x: batch[0], y_: batch[1]})
# Evaluate the Model
correct_prediction = tf.equal(tf.argmax(y,1), tf.argmax(y_,1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
print(accuracy.eval(feed_dict={x: mnist.test.images, y_: mnist.test.labels}))
loadImageAndPredict.py
from random import randint
from scipy import misc
import numpy as np
import cv2
def preProcess(invert_file):
print "preprocessing the images" + invert_file
image=cv2.imread(invert_file,0)
ret,image_thresh = cv2.threshold(image,127,255,cv2.THRESH_BINARY)
l,b=image.shape
fr=0
lr=0
fc=0
lc=0
i=0
while len(set(image_thresh[i,]))==1:
i+=1
fr=i
i=0
while len(set(image_thresh[-1+i,]))==1:
i-=1
lr=i+l
j=0
while len(set(image_thresh[0:,j]))==1:
j+=1
fc=j
j=0
while len(set(image_thresh[0:,-1+j]))==1:
j-=1
lc=j+b
image_crop=image_thresh[fr:lr,fc:lc]
image_padded= cv2.copyMakeBorder(image_crop,5,5,5,5,cv2.BORDER_CONSTANT,value=255)
image_resized = cv2.resize(image_padded, (28, 28))
image_resized = (255-image_resized)
cv2.imwrite(invert_file, image_resized)
import tensorflow as tf
sess = tf.InteractiveSession()
# Placeholders
x = tf.placeholder(tf.float32, shape=[None, 784])
y_ = tf.placeholder(tf.float32, shape=[None, 10])
# # Variables
W = tf.Variable(tf.zeros([784,10]))
b = tf.Variable(tf.zeros([10]))
# Predicted Class and Cost Function
y = tf.nn.softmax(tf.matmul(x,W) + b)
cross_entropy = tf.reduce_mean(-tf.reduce_sum(y_ * tf.log(y), reduction_indices=[1]))
saver = tf.train.Saver() # defaults to saving all variables - in this case w and b
# Train the Model
# GradientDescentOptimizer
train_step = tf.train.GradientDescentOptimizer(0.5).minimize(cross_entropy)
flag_1 = 0
# create an an array where we can store 1 picture
images = np.zeros((1,784))
# and the correct values
correct_vals = np.zeros((1,10))
preProcess("4_white.png")
gray = cv2.imread("4_white.png", 0)
flatten = gray.flatten() / 255.0
"""
we need to store the flatten image and generate
the correct_vals array
correct_val for a digit (9) would be
[0,0,0,0,0,0,0,0,0,1]
"""
images[0] = flatten
# print images[0]
print len(images[0])
sess.run(tf.initialize_all_variables())
ckpt = tf.train.get_checkpoint_state("/Users/xxxx/Desktop/TensorFlow")
if ckpt and ckpt.model_checkpoint_path:
saver.restore(sess, ckpt.model_checkpoint_path)
my_classification = sess.run(tf.argmax(y, 1), feed_dict={x: [images[0]]})
print 'Neural Network predicted', my_classification[0], "for your digit"
i am not sure what mistake i have done.
Thinking that simple model might not work i have used this convolution code to predict.
https://github.com/tensorflow/tensorflow/blob/master/tensorflow/models/image/mnist/convolutional.py
Even that does not predict properly :(