When I run the following code, it prints a constant loss at every training step; I also tried printing the parameters, which also do not change.
I can't seem to figure out why train_step, which uses a GradientDescentOptimizer, doesnt change the weights in W_fc1, b_fc1, W_fc2, and b_fc2.
I'm a beginner to machine learning so I might be missing something obvious.
(An answer for a similar question was that weights should not be initialized at zero, but the weights here are initialized with truncated normal so that cant be the problem).
import tensorflow as tf
import numpy as np
import csv
import random
with open('wine_data.csv', 'rb') as csvfile:
input_arr = list(csv.reader(csvfile, delimiter=','))
for i in range(len(input_arr)):
input_arr[i][0] = int(input_arr[i][0]) - 1 # 0 index for one hot
for j in range(1, len(input_arr[i])):
input_arr[i][j] = float(input_arr[i][j])
random.shuffle(input_arr)
training_data = np.array(input_arr[:2*len(input_arr)/3]) # train on first two thirds of data
testing_data = np.array(input_arr[2*len(input_arr)/3:]) # test on last third of data
x_train = training_data[0:, 1:]
y_train = training_data[0:, 0]
x_test = testing_data[0:, 1:]
y_test = testing_data[0:, 0]
def weight_variable(shape):
initial = tf.truncated_normal(shape, stddev=0.1)
return tf.Variable(initial)
def bias_variable(shape):
initial = tf.constant(0.1, shape=shape)
return tf.Variable(initial)
x = tf.placeholder(tf.float32, shape=[None, 13], name='x')
y_ = tf.placeholder(tf.float32, shape=[None], name='y_')
y_one_hot = tf.one_hot(tf.cast(y_, tf.int32), 3) # actual y values
W_fc1 = weight_variable([13, 128])
b_fc1 = bias_variable([128])
fc1 = tf.matmul(x, W_fc1)+b_fc1
W_fc2 = weight_variable([128, 3])
b_fc2 = bias_variable([3])
y = tf.nn.softmax(tf.matmul(fc1, W_fc2)+b_fc2)
cross_entropy = tf.reduce_sum(tf.nn.softmax_cross_entropy_with_logits(labels=y_one_hot, logits=y))
train_step = tf.train.GradientDescentOptimizer(1e-17).minimize(cross_entropy)
correct_prediction = tf.equal(tf.argmax(y,1), tf.argmax(y_one_hot,1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
sess = tf.InteractiveSession()
tf.global_variables_initializer().run()
for _ in range(1000):
train_step.run(feed_dict={x: x_train, y_: y_train})
if _%10 == 0:
loss = cross_entropy.eval(feed_dict={x: x_train, y_: y_train})
print('step', _, 'loss', loss)
Thanks in advance.
From the official tensorflow documentation:
WARNING: This op expects unscaled logits, since it performs a softmax on logits internally for efficiency. Do not call this op with the output of softmax, as it will produce incorrect results.
Remove the softmax on y before feeding it into tf.nn.softmax_cross_entropy_with_logits
Also set your learning rate to something higher (like 3e-4)
Related
I'm trying to use GradientTape mechanism for the first time. I've looked at some examples but I'm getting the "No gradients provided for any variable" error and was wondering how to overcome this?
I want to define some complex loss functions, so I tried using GradientTape to produce its gradient for the CNN training. What was I doing wrong and can I fix it?
Attached is a run-able example code that demonstrates my problem:
# imports
import numpy as np
import tensorflow as tf
import sklearn
from tensorflow import keras
from tensorflow.keras import layers
from sklearn.model_selection import train_test_split
from sklearn.svm import SVC
tf.config.run_functions_eagerly(True)
#my loss function
def my_loss_fn(y_true, y_pred):
` # train SVM classifier
VarC=1E6
VarGamma='scale'
clf = SVC(kernel='rbf', C=VarC, gamma=VarGamma, probability=True )
clf.fit(y_pred, y_true)
y_pred = clf.predict_proba(y_pred)
scce = tf.keras.losses.SparseCategoricalCrossentropy()
return scce(y_true, y_pred)
`
#creating inputs to demontration
X0=0.5*np.ones((12,12))
X0[2:12:4,:]=0
X0[3:12:4,:]=0
X1=0.5*np.ones((12,12))
X1[1:12:4,:]=0
X1[2:12:4,:]=0
X1=np.transpose(X1)
X=np.zeros((2000,12,12))
for i in range(0,1000):
X[i]=X0+np.random.rand(12,12)
for i in range(1000,2000):
X[i]=X1+np.random.rand(12,12)
y=np.zeros(2000, dtype=int)
y[1000:2000]=1
x_train, x_val, y_train, y_val = train_test_split(X, y, train_size=0.5)
x_val, x_test, y_val, y_test = train_test_split(x_val, y_val, train_size=0.5)
x_train = tf.convert_to_tensor(x_train)
x_val = tf.convert_to_tensor(x_val)
x_test = tf.convert_to_tensor(x_test)
y_train = tf.convert_to_tensor(y_train)
y_val = tf.convert_to_tensor(y_val)
y_test = tf.convert_to_tensor(y_test)
inputs = keras.Input((12,12,1), name='images')
x0 = tf.keras.layers.Conv2D(8,4,strides=4)(inputs)
x0 = tf.keras.layers.AveragePooling2D(pool_size=(3, 3), name='pooling')(x0)
outputs = tf.keras.layers.Flatten(name='predictions')(x0)
model = keras.Model(inputs=inputs, outputs=outputs)
optimizer=tf.keras.optimizers.Adam(learning_rate=0.001)
# Instantiate a loss function.
loss_fn = my_loss_fn
# Prepare the training dataset.
batch_size = 256
train_dataset = tf.data.Dataset.from_tensor_slices((x_train, y_train))
train_dataset = train_dataset.shuffle(buffer_size=1024).batch(batch_size)
epochs = 100
for epoch in range(epochs):
print('Start of epoch %d' % (epoch,))
# Iterate over the batches of the dataset.
for step, (x_batch_train, y_batch_train) in enumerate(train_dataset):
# Open a GradientTape to record the operations run
# during the forward pass, which enables autodifferentiation.
with tf.GradientTape() as tape:
tape.watch(model.trainable_weights)
# Run the forward pass of the layer.
# The operations that the layer applies
# to its inputs are going to be recorded
# on the GradientTape.
logits = model(x_batch_train, training=True) # Logits for this minibatch
# Compute the loss value for this minibatch.
loss_value = loss_fn(y_batch_train, logits)
# Use the gradient tape to automatically retrieve
# the gradients of the trainable variables with respect to the loss.
grads = tape.gradient(loss_value, model.trainable_weights)
# Run one step of gradient descent by updating
# the value of the variables to minimize the loss.
optimizer.apply_gradients(zip(grads, model.trainable_weights))
# Log every 200 batches.
if step % 200 == 0:
print('Training loss (for one batch) at step %s: %s' % (step, float(loss_value)))
print('Seen so far: %s samples' % ((step + 1) * 64))
And when running, I get:
ValueError: No gradients provided for any variable: (['conv2d_2/kernel:0', 'conv2d_2/bias:0'],). Provided grads_and_vars is ((None, <tf.Variable 'conv2d_2/kernel:0' shape=(4, 4, 1, 8) dtype=float32, nump
If I use some standard loss function:
For example the following model and loss function
inputs = keras.Input((12,12,1), name='images')
x0 = tf.keras.layers.Conv2D(8,4,strides=4)(inputs)
x0 = tf.keras.layers.AveragePooling2D(pool_size=(3, 3), name='pooling')(x0)
x0 = tf.keras.layers.Flatten(name='features')(x0)
x0 = layers.Dense(16, name='meta_features')(x0)
outputs = layers.Dense(2, name='predictions')(x0)
model = keras.Model(inputs=inputs, outputs=outputs)
loss_fn = keras.losses.SparseCategoricalCrossentropy(from_logits=True)
Everything works fine and converges well.
What am I doing wrong and can I fix it?
I don't know why occur this problem,I have checked many times, I have feed xs and ys to feed_dict. So, what is the reason for this problem? How do I modify my code to solve these error? Below is the error log.
InvalidArgumentError (see above for traceback): You must feed a value for placeholder tensor 'Placeholder_2' with dtype float and shape [?,10]
[[node Placeholder_2 (defined at /home/jiayu/dropout.py:41) = Placeholder[dtype=DT_FLOAT, shape=[?,10], _device="/job:localhost/replica:0/task:0/device:GPU:0"]()]]
[[{{node Mean_5/_55}} = _Recv[client_terminated=false, recv_device="/job:localhost/replica:0/task:0/device:CPU:0", send_device="/job:localhost/replica:0/task:0/device:GPU:0", send_device_incarnation=1, tensor_name="edge_271_Mean_5", tensor_type=DT_FLOAT, _device="/job:localhost/replica:0/task:0/device:CPU:0"]()]]
This code run on ubuntu 16.04, tensorflow 1.12.0 and python 3.6.8.
from __future__ import print_function
import tensorflow as tf
from sklearn.datasets import load_digits
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import LabelBinarizer
# load data
digits = load_digits()
X = digits.data
y = digits.target
y = LabelBinarizer().fit_transform(y)
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=.3)
def add_layer(inputs, in_size, out_size, layer_name, activation_function=None, ):
# add one more layer and return the output of this layer
Weights = tf.Variable(tf.random_normal([in_size, out_size]))
biases = tf.Variable(tf.zeros([1, out_size]) + 0.1, )
Wx_plus_b = tf.matmul(inputs, Weights) + biases
# here to dropout
Wx_plus_b = tf.nn.dropout(Wx_plus_b, keep_prob)
if activation_function is None:
outputs = Wx_plus_b
else:
outputs = activation_function(Wx_plus_b, )
tf.summary.histogram(layer_name + '/outputs', outputs)
return outputs
# define placeholder for inputs to network
keep_prob = tf.placeholder(tf.float32)
xs = tf.placeholder(tf.float32, [None, 64]) # 8x8
ys = tf.placeholder(tf.float32, [None, 10])
# add output layer
l1 = add_layer(xs, 64, 50, 'l1', activation_function=tf.nn.tanh)
prediction = add_layer(l1, 50, 10, 'l2', activation_function=tf.nn.softmax)
# the loss between prediction and real data
cross_entropy = tf.reduce_mean(-tf.reduce_sum(ys * tf.log(prediction),reduction_indices=[1])) # loss
tf.summary.scalar('loss', cross_entropy)
train_step = tf.train.GradientDescentOptimizer(0.5).minimize(cross_entropy)
sess = tf.Session()
merged = tf.summary.merge_all()
# summary writer goes in here
train_writer = tf.summary.FileWriter("logs/train", sess.graph)
test_writer = tf.summary.FileWriter("logs/test", sess.graph)
# tf.initialize_all_variables() no long valid from
# 2017-03-02 if using tensorflow >= 0.12
if int((tf.__version__).split('.')[1]) < 12 and int((tf.__version__).split('.')[0]) < 1:
init = tf.initialize_all_variables()
else:
init = tf.global_variables_initializer()
sess.run(init)
for i in range(500):
# here to determine the keeping probability
sess.run(train_step, feed_dict={xs: X_train, ys: y_train, keep_prob: 1})
if i % 50 == 0:
# record loss
train_result = sess.run(merged, feed_dict={xs: X_train, ys: y_train, keep_prob: 1})
test_result = sess.run(merged, feed_dict={xs: X_test, ys: y_test, keep_prob: 1})
train_writer.add_summary(train_result, i)
test_writer.add_summary(test_result, i)
The right result is display scale in tensorboard.
You cannot run the script more than once because otherwise you are creating nested graph
For the first run, it will run OK without any errors. But when you run it more than once, nested computation graph will be created. You can view the behavior in tensorboard, after several runs, the computation graph will get bigger and bigger, and when you try to evaluate the bigger graph, extra placeholders simply don't get data fed to them and they will give error.
Here is the simple solution. Use ft.reset_default_graph() and put it before the place where you create the graph
tf.reset_default_graph()
# define placeholder for inputs to network
keep_prob = tf.placeholder(tf.float32, name='prob')
xs = tf.placeholder(tf.float32, [None, 64], name='x_input') # 8x8
ys = tf.placeholder(tf.float32, [None, 10], name='y_input')
...
some further reading Remove nodes from graph or reset entire default graph
I am trying to build a linear classifier with CIFAR - 100 using TensorFlow. I got the code from Martin Gorner's MNIST tutorial and change a bit. When I run this code, tensorflow does not training (code is running but accuracy remains 1.0 and loss(cross entropy remains as 4605.17), I don't know what is wrong, I am actually newbie to TF any help is appreciated.
import pickle
import numpy as np
import os
import tensorflow as tf
from tensorflow.python.framework import tensor_util
import math
#imports data
def unpickle(file):
import pickle
with open(file, 'rb') as fo:
dict = pickle.load(fo, encoding='bytes')
return dict
cifar100_test = {}
cifar100_train = {}
labelMap = {}
labelNames = {}
# Load the raw CIFAR-10 data.
cifar100_test = unpickle('dataset/cifar-100-python/test')
cifar100_train = unpickle('dataset/cifar-100-python/train')
labelMap = unpickle('dataset/cifar-100-python/meta')
#tr for training data and te for testing data, X is data, Y is label
Xtr = cifar100_train[b'data']
Yr = cifar100_train[b'fine_labels']
Xte = cifar100_test[b'data']
Ye = cifar100_test[b'fine_labels']
classNames = labelMap[b'fine_label_names']
num_train = Xtr.shape[0]
num_test = Xte.shape[0]
num_class = len(classNames)
Ytr = np.zeros([num_train, num_class])
Yte = np.zeros([num_test, num_class])
Ytr[0:num_train, Yr[0:num_train]] = 1
Yte[0:num_test, Ye[0:num_test]] = 1
# As a sanity check, we print out the size of the training and test data.
print('Train data shape:', Xtr.shape)
print('Train Label shape:', Ytr.shape)
print('Test data shape:', Xte.shape)
print('Test Label shape:', Yte.shape)
print('Name of Predicted Class:', classNames[0]) #indice of the label name is the indice of the class.
Xtrain = Xtr#[:1000]
Xtest = Xte#[:100]
Ytrain = Ytr#[:1000]
Ytest = Yte#[:100]
print('Train data shape:', Xtrain.shape)
print('Train Label shape:', Ytrain.shape)
print('Test data shape:', Xtest.shape)
print('Test Label shape:', Ytest.shape)
Xtrain = np.reshape(Xtrain,(50000, 32, 32, 3)).transpose(0,1,2,3).astype(float)
Xtest = np.reshape(Xtest,(10000, 32, 32, 3)).transpose(0,1,2,3).astype(float)
Xbatches = np.split(Xtrain, 500); #second number is # of batches
Ybatches = np.split(np.asarray(Ytrain), 500);
XtestB = np.split(Xtest, 100);
YtestB = np.split(Ytest, 100);
print('X # of batches:', len(Xbatches))
print('Y # of batches:', len(Ybatches))
# input X: 28x28 grayscale images, the first dimension (None) will index the images in the mini-batch
X = tf.placeholder(tf.float32, [100, 32, 32, 3])
# correct answers will go here
Y_ = tf.placeholder(tf.float32, [100, 100])
# weights W[784, 10] 784=28*28
W = tf.Variable(tf.zeros([3072, 100]))
# biases b[10]
b = tf.Variable(tf.zeros([100]))
# flatten the images into a single line of pixels
# -1 in the shape definition means "the only possible dimension that will preserve the number of elements"
XX = tf.reshape(X, [-1, 3072])
# The model
Y = tf.nn.softmax(tf.matmul(XX, W) + b)
# loss function: cross-entropy = - sum( Y_i * log(Yi) )
# Y: the computed output vector
# Y_: the desired output vector
# cross-entropy
# log takes the log of each element, * multiplies the tensors element by element
# reduce_mean will add all the components in the tensor
# so here we end up with the total cross-entropy for all images in the batch
cross_entropy = -tf.reduce_mean(Y_ * tf.log(Y)) * 1000.0 # normalized for batches of 100 images,
# *10 because "mean" included an unwanted division by 10
# accuracy of the trained model, between 0 (worst) and 1 (best)
correct_prediction = tf.equal(tf.argmax(Y, 1), tf.argmax(Y_, 1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
# training, learning rate = 0.005
train_step = tf.train.GradientDescentOptimizer(0.01).minimize(cross_entropy)
# init
init = tf.global_variables_initializer()
sess = tf.Session()
sess.run(init)
for i in range(500):
# the backpropagation training step
t, Loss = sess.run([train_step, cross_entropy], feed_dict={X: Xbatches[i], Y_: Ybatches[i]})
print(Loss)
print(i)
for i in range(100):
print('accuracy:', sess.run(accuracy, feed_dict={X: XtestB[i], Y_: YtestB[i]}))
You compute the accuracy a hundred times after the training process is completed. Nothing will change there. You should place your print('accuracy:'....) within the for loop in which you perform the backpropagation:
for i in range(500):
# the backpropagation training step
t, Loss = sess.run([train_step, cross_entropy], feed_dict={X: Xbatches[i], Y_: Ybatches[i]})
print(Loss)
print(i)
print('accuracy:', sess.run(accuracy, feed_dict={X: XtestB[i], Y_: YtestB[i]}))
Sorry for the post it turns out that it is a basic mistake.
I changed following;
Ytr[0:num_train, Yr[0:num_train]] = 1
Yte[0:num_test, Ye[0:num_test]] = 1
with
Ytr[range(num_train), Yr_temp[range(num_train)]] = 1
Yte[range(num_test), Ye_temp[range(num_test)]] = 1
First one make all values 1, but I just wanted to make indice of the true class 1 and other elements 0. Thanks for your time.
how can i solve this ? this is my first time for Tensortflow. I try to copy Train and Evaluate the Model from tensortflow tutorial but it seem not work. Can someone help me to solve my problem? Thanks!
http://pastebin.com/NCQKNyKy
import tensorflow as tf
sess = tf.InteractiveSession()
import numpy as np
from numpy import genfromtxt
def weight_variable(shape):
initial = tf.truncated_normal(shape, stddev=0.1)
return tf.Variable(initial)
def bias_variable(shape):
initial = tf.constant(0.1, shape=shape)
return tf.Variable(initial)
def conv2d(x, W):
return tf.nn.conv2d(x, W, strides=[1, 1, 3*3, 1], padding='VALID')
data = genfromtxt('circle_deeplearn_data_small.txt',delimiter=',')
out = genfromtxt('circle_deeplearn_output_small.txt',delimiter=',')
x = tf.placeholder(tf.float32, shape =[None, 3*3*15]) # size of x
y_ = tf.placeholder(tf.float32, shape =[None, 1]) # size of output
W_conv1 = weight_variable([1,3*3,1,15])
b_conv1 = bias_variable([15])
x_image = tf.reshape(x,[-1,1,3*3*15,1])
h_conv1 = tf.nn.relu(conv2d(x_image,W_conv1) + b_conv1)
W_fc1 = weight_variable([1 * 1 * 15 , 1])
b_fc1 = bias_variable([1])
h_conv1_flat = tf.reshape(h_conv1 , [-1,1 * 1 * 15])
h_fc1 = tf.nn.relu(tf.matmul(h_conv1_flat , W_fc1) + b_fc1)
y_conv = h_fc1
keep_prob = tf.placeholder(tf.float32)
h_fc1_drop = tf.nn.dropout(h_fc1, keep_prob)
#Adam
cross_entropy = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(y_conv, y_))
train_step = tf.train.AdamOptimizer(1e-4).minimize(cross_entropy)
correct_prediction = tf.equal(tf.argmax(y_conv,1), tf.argmax(y_,1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
#sess.run(tf.global_variables_initializer())
sess.run(tf.initialize_all_variables())
for i in range(20000):
batch = data.train.next_batch(50)
if i%100 == 0:
train_accuracy = accuracy.eval(feed_dict={x:batch[0], y_: batch[1], keep_prob: 1.0})
print("step %d, training accuracy %g"%(i, train_accuracy))
train_step.run(feed_dict={x: batch[0], y_: batch[1], keep_prob: 0.5})
print("test accuracy %g"%accuracy.eval(feed_dict={x: data, y_: out, keep_prob: 1.0}))
This is result:
AttributeError: 'numpy.ndarray' object has no attribute 'train'
here datais just a numpy array. You may need to write ur own train data iterator
It is not quite clear what you are trying to do. The problem occurs because data is a numpy array generated in this line
data = genfromtxt('circle_deeplearn_data_small.txt',delimiter=',')
The error occurs when you try to use the method train of data, which does not exist, in the following line
batch = data.train.next_batch(50)
Instead you need to feed data to tensorflow.
I have faced same problem. Actually, it's not a problem. Literally, I didn't know the structure of the data that's why I have faced this problem. Te datasets comes from tensorflow lib are compressed in a single file and separated in a file as train, test, and validation set. That's why when we call dataset.train.next_batch() it does work. You own datatset is not compressed in the same way that's why it doesn't work. You have to configure your dataset on the own way so do the batch system and looping.
You may try to use numpy.reshape to turn your data from 2 dimension into 3 dimension.
For example if you had 20 samples and 100 features, so a (20,100) data matrix and used a minibatch size of 5. Then you could reshape using np.reshape(data,[10,5,-1]) to get a (10,5,40) matrix.
*The "-1" meaning that you leave numpy to count the array for your, the total number of array is 20,000.
Thus, in this example: 10*5*40 = 20,000.
I have seen a few posts on restoring TF models and the Google doc page on exporting graphs but I think I am missing something.
I use the code in this Gist to save the model along with this utils file to which defines the model
Now I would like to restore it and run in a previously unseen test data as follows:
def evaluate(X_data, y_data):
num_examples = len(X_data)
total_accuracy = 0
total_loss = 0
sess = tf.get_default_session()
acc_steps = len(X_data) // BATCH_SIZE
for i in range(acc_steps):
batch_x, batch_y = next_batch(X_val, Y_val, BATCH_SIZE)
loss, accuracy = sess.run([loss_value, acc], feed_dict={
images_placeholder: batch_x,
labels_placeholder: batch_y,
keep_prob: 0.5
})
total_accuracy += (accuracy * len(batch_x))
total_loss += (loss * len(batch_x))
return (total_accuracy / num_examples, total_loss / num_examples)
## re-execute the code that defines the model
# Image Tensor
images_placeholder = tf.placeholder(tf.float32, shape=[None, 32, 32, 3], name='x')
gray = tf.image.rgb_to_grayscale(images_placeholder, name='gray')
gray /= 255.
# Label Tensor
labels_placeholder = tf.placeholder(tf.float32, shape=(None, 43), name='y')
# dropout Tensor
keep_prob = tf.placeholder(tf.float32, name='drop')
# construct model
logits = inference(gray, keep_prob)
# calculate loss
loss_value = loss(logits, labels_placeholder)
# training
train_op = training(loss_value, 0.001)
# accuracy
acc = accuracy(logits, labels_placeholder)
with tf.Session() as sess:
loader = tf.train.import_meta_graph('gtsd.meta')
loader.restore(sess, tf.train.latest_checkpoint('./'))
sess.run(tf.initialize_all_variables())
test_accuracy = evaluate(X_test, y_test)
print("Test Accuracy = {:.3f}".format(test_accuracy[0]))
I'm getting a test accuracy of only 3%. However If I don't close the Notebook and run the test code immediately after training the model, I get a 95% accuracy.
This leads me to believe I'm not loading the model correctly?
The problem arises from these two lines:
loader.restore(sess, tf.train.latest_checkpoint('./'))
sess.run(tf.initialize_all_variables())
The first line loads the saved model from a checkpoint. The second line re-initializes all of the variables in the model (such as the weight matrices, convolutional filters, and bias vectors), usually to random numbers, and overwrites the loaded values.
The solution is simple: delete the second line (sess.run(tf.initialize_all_variables())) and evaluation will proceed with the trained values loaded from the checkpoint.
PS. There is a small chance that this change will give you an error about "uninitialized variables". In that case, you should execute sess.run(tf.initialize_all_variables()) to initialize any variables not saved in the checkpoint before executing loader.restore(sess, tf.train.latest_checkpoint('./')).
I had a similar problem and for me this worked:
with tf.Session() as sess:
saver=tf.train.Saver(tf.all_variables())
saver=tf.train.import_meta_graph('model.meta')
saver.restore(sess,"model")
test_accuracy = evaluate(X_test, y_test)
The answer found here is what ended up working as follows:
save_path = saver.save(sess, '/home/ubuntu/gtsd-12-23-16.chkpt')
print("Model saved in file: %s" % save_path)
## later re-run code that creates the model
# Image Tensor
images_placeholder = tf.placeholder(tf.float32, shape=[None, 32, 32, 3], name='x')
gray = tf.image.rgb_to_grayscale(images_placeholder, name='gray')
gray /= 255.
# Label Tensor
labels_placeholder = tf.placeholder(tf.float32, shape=(None, 43), name='y')
# dropout Tensor
keep_prob = tf.placeholder(tf.float32, name='drop')
# construct model
logits = inference(gray, keep_prob)
# calculate loss
loss_value = loss(logits, labels_placeholder)
# training
train_op = training(loss_value, 0.001)
# accuracy
acc = accuracy(logits, labels_placeholder)
saver = tf.train.Saver()
with tf.Session() as sess:
saver.restore(sess, '/home/ubuntu/gtsd-12-23-16.chkpt')
print("Model restored.")
test_accuracy = evaluate(X_test, y_test)
print("Test Accuracy = {:.3f}".format(test_accuracy[0]*100))