I'm completely new to Python and Tensorflow. I want to implement a simple kind of CNN, and this is what I have done till now:
import tensorflow as tf
import numpy as np
from libs import utils
import cv2
import glob
from tensorflow.python.framework.ops import reset_default_graph
reset_default_graph()
# We first get the graph that we used to compute the network
g = tf.get_default_graph()
# And can inspect everything inside of it
[op.name for op in g.get_operations()]
X = tf.placeholder(tf.float32, [None,720000])
Y = tf.placeholder(tf.int32, [None])
X_data = []
files = glob.glob ("C:/Users/Maede/Desktop/Master Thesis/imlearning/*.jpg")
for myFile in files:
print(myFile)
image = cv2.imread (myFile)
X_data.append (image)
print('X_data shape:', np.array(X_data).shape)
data=np.array(X_data)
data=np.reshape(data,(30,720000))
label=np.array([(0,1),(1,0),(0,1),(1,0),(0,1),(1,0),(0,1),(1,0),(0,1),(1,0),
(0,1),(1,0),(0,1),(1,0),(0,1),(1,0),(0,1),(1,0),(0,1),(1,0),
(0,1),(1,0),(0,1),(1,0),(0,1),(1,0),(0,1),(1,0),(0,1),(1,0)])
###########################################################
train_batch_size = 2
def random_batch():
num_images = 30
idx = np.random.choice(num_images,
size=train_batch_size,
replace=False)
x_batch = data[idx,:]
y_batch = label[idx, :]
return x_batch, y_batch
######################
#
X_tensor = tf.reshape(X, [-1, 400,600,3])
filter_size = 5
n_filters_in = 3
n_filters_out = 32
W_1 = tf.get_variable(
name='W',
shape=[filter_size, filter_size, n_filters_in, n_filters_out],
initializer=tf.random_normal_initializer())
b_1 = tf.get_variable(
name='b',
shape=[n_filters_out],
initializer=tf.constant_initializer())
h_1 = tf.nn.relu(
tf.nn.bias_add(
tf.nn.conv2d(input=X_tensor,
filter=W_1,
strides=[1, 2, 2, 1],
padding='SAME'),
b_1))
n_filters_in = 32
n_filters_out = 64
n_output = 2
W_2 = tf.get_variable(
name='W2',
shape=[filter_size, filter_size, n_filters_in, n_filters_out],
initializer=tf.random_normal_initializer())
b_2 = tf.get_variable(
name='b2',
shape=[n_filters_out],
initializer=tf.constant_initializer())
h_2 = tf.nn.relu(
tf.nn.bias_add(
tf.nn.conv2d(input=h_1,
filter=W_2,
strides=[1, 2, 2, 1],
padding='SAME'),
b_2))
# We'll now reshape so we can connect to a fully-connected/linear layer:
h_2_flat = tf.reshape(h_2, [-1, 100*150* n_filters_out])
# NOTE: This uses a slightly different version of the linear function than the lecture!
h_3, W = utils.linear(h_2_flat, 400, activation=tf.nn.relu, name='fc_1')
# NOTE: This uses a slightly different version of the linear function than the lecture!
Y_pred, W = utils.linear(h_3, n_output, activation=tf.nn.softmax, name='fc_2')
y_one_hot = tf.one_hot( Y , 2 )
cross_entropy = -tf.reduce_sum(y_one_hot * tf.log(Y_pred + 1e-12))
optimizer = tf.train.AdamOptimizer().minimize(cross_entropy)
correct_prediction = tf.equal(tf.argmax(Y_pred, 1), tf.argmax(y_one_hot, 1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, 'float'))
sess = tf.Session()
sess.run(tf.global_variables_initializer())
batch_size = 2
n_epochs = 5
for epoch_i in range(n_epochs):
for batch_xs, batch_ys in random_batch():
sess.run(optimizer, feed_dict={
X: np.array(batch_xs).reshape([1,720000]),
Y: batch_ys
})
valid = data #### DATA haie validation
print(sess.run(accuracy,
feed_dict={
X: data,
Y: label
}))
The input is 30 image with 400*600*3 dimension and i want to classify them into two class. The problem is when i'm using this command:
X: np.array(batch_xs).reshape([1,720000]),
The error is like below:
ValueError: cannot reshape array of size 2 into shape (1,720000)
and when I'm using:
X: batch_xs
The error is:
ValueError: Cannot feed value of shape (720000,) for Tensor 'Placeholder:0', which has shape '(?, 720000)'
I'm totally confused what is batch_xs dimension and why does it change in different situation.
np.array(batch_xs) is not the same size as your image.
for batch_xs, batch_ys in random_batch() is also a slightly strange way to run the code and I guess this also causes your problem. You usually use for to iterate over a some iterable.
In your case the iterable is just what your function returns, a tuple with batch_xs, batch_ys. But in the same step you are unpacking the first (!) value of the tuple into two variables batch_xs and batch_ys.
The replace=False does not do anything in your case, because you are calling the function random_batch() only once. In the next iteration it will have the complete dataset again.
Here is an simple example on your case:
import numpy as np
# I removed a dimension from the arrays
data = np.array([[1.0, 1.0, 1.0],
[2.0, 2.0, 2.0],
[3.0, 3.0, 3.0]])
label = np.array([[10.0, 10.0, 10.0],
[20.0, 20.0, 20.0],
[30.0, 30.0, 30.0]])
def random_batch():
idx = np.random.choice(3, size=2)
x_batch = data[idx,:]
y_batch = label[idx, :]
return x_batch, y_batch
# the outer variable names x_batch and y_batch are not related at all to the ones
# inside random_batch()
# iterate over whatever random_batch() returns
# for x_batch, y_batch in random_batch() is equivalent to
# for (x_batch, y_batch) in random_batch()
# in the first iteration the iterable is `x_batch`, in the second one`y_batch`.
# and each of the iterable is "unpacked", basically in the first iteration
# your are assigning
# (x_batch, y_batch) = x_batch
# in the second iteration
# (x_batch, y_batch) = y_batch
# When unpacking you are splitting the two elements created by `size=2`
# in `random_batch()`
for (x_batch, y_batch) in random_batch():
print(x_batch)
print(y_batch)
This is fundamental Python basics, to get familiar with it look for tuple unpacking, iterable and for loops.
Replace the inner for-loop with this, it should work. It might not be what you expected, but it is what you code is supposed to do.
batch_xs, batch_ys = random_batch()
sess.run(optimizer, feed_dict={
X: np.array(batch_xs).reshape([1,720000]),
Y: batch_ys
})
If if you want to train with 100 batches do something like this
for k in range(100):
batch_xs, batch_ys = random_batch()
sess.run(optimizer, feed_dict={
X: np.array(batch_xs).reshape([1,720000]),
Y: batch_ys
})
Usually you try to remove as much of the code that is not related to the problem to make it easier to find the problem. Find as less code as possible that still shows your problem.
Your problem is not related to tensorflow, so you could remove everything related to tensorflow to make it easier to find. Your problem is related to numpy and array shapes.
Related
I am developing a neural network model for classifying benign and malware apks.
I have tried using tf.squeeze() function but after using it I am unable to use optimizer
def neural_network_model(data):
l1 = tf.add(tf.matmul(data,hidden_1_layer['weight']), hidden_1_layer['bias'])
l1 = tf.nn.relu(l1)
l2 = tf.add(tf.matmul(l1,hidden_2_layer['weight']), hidden_2_layer['bias'])
l2 = tf.nn.relu(l2)
l3 = tf.add(tf.matmul(l2,hidden_3_layer['weight']), hidden_3_layer['bias'])
l3 = tf.nn.relu(l3)
output = tf.matmul(l3,output_layer['weight']) + output_layer['bias']
return output
def train_neural_network(x):
prediction = neural_network_model(x)
cost = tf.reduce_mean( tf.nn.softmax_cross_entropy_with_logits(logits=prediction, labels= y) )
optimizer = tf.train.AdamOptimizer(learning_rate=0.001).minimize(cost)
The shape of pred and y must be same however by running the code I am having different shape of pred is (3799,2) whereas the shape of y is (1,3799).
My remarks:
If your labels aren't one-hot encoded you can use tf.nn.sparse_softmax_cross_entropy_with_logits() without converting it to the one-hot encoded representation. Otherwise, tf.nn.softmax_cross_entropy_with_logits() accepts only one-hot encoded labels.
You can't pass numpy values as inputs to the loss function (or as inputs to anything except for feed_dict in session.run()) if you're writing code in a graph mode. Use placeholders instead.
Following is the example to illustrate how to use placeholders and feed numpy arrays of data.
import numpy as np
import tensorflow as tf
# Dummy data with 3 classes for illustration
n_classes =3
x_train = np.random.normal(size=(3799, 2)) # 3799 samples of size (2, ) each
y_train = np.random.randint(low=0, high=n_classes, size=(1, 3799))
# Define placeholders here
x = tf.placeholder(tf.float32, shape=(None, 2))
y = tf.placeholder(tf.int32, shape=(1, None))
# Define your network here
w = tf.Variable(tf.random_normal(shape=[2, n_classes]), dtype=tf.float32)
b = tf.Variable(tf.zeros([n_classes, ]), dtype=tf.float32)
logits = tf.matmul(x, w) + b
labels = tf.squeeze(y)
xentropy = tf.nn.sparse_softmax_cross_entropy_with_logits(logits=logits,
labels=labels)
cost = tf.reduce_mean(xentropy)
train_op = tf.train.AdamOptimizer(learning_rate=0.001).minimize(cost)
# Training
with tf.Session() as sess:
sess.run(tf.global_variables_initializer())
cost_val = sess.run(cost, feed_dict={x:x_train, y:y_train})
print(cost_val) # 1.8630761
sess.run(train_op, feed_dict={x:x_train, y:y_train}) # optimizer step
cost_val = sess.run(cost, feed_dict={x:x_train, y:y_train})
print(cost_val) # 1.8619089
I'm trying to get started with TensorFlow in python, building a simple CNN with batch normalization. But when i create a new graph to run, exception happens to BN.
My key codes is as follows
**# exception here**
def batch_norm(x, beta, gamma, phase_train, scope='bn', decay=0.9, eps=1e-5):
with tf.variable_scope(scope):
batch_mean, batch_var = tf.nn.moments(x, [0], name='moments')
ema = tf.train.ExponentialMovingAverage(decay=decay)
def mean_var_with_update():
ema_apply_op = ema.apply([batch_mean, batch_var])
with tf.control_dependencies([ema_apply_op]):
return tf.identity(batch_mean), tf.identity(batch_var)
mean, var = tf.cond(phase_train, mean_var_with_update, lambda: (ema.average(batch_mean), ema.average(batch_var)))
normed = tf.nn.batch_normalization(x, mean, var, beta, gamma, eps)
return normed
training code:
# start training
output = conv2d_net()
loss = tf.reduce_mean(tf.nn.sigmoid_cross_entropy_with_logits(logits=output, labels=Y))
optimizer = tf.train.AdamOptimizer(learning_rate=0.002).minimize(loss)
predict = tf.reshape(output, [-1, MAX_CAPTCHA, CHAR_SET_LEN])
max_idx_p = tf.argmax(predict, 2)
max_idx_l = tf.argmax(tf.reshape(Y, [-1, MAX_CAPTCHA, CHAR_SET_LEN]), 2)
correct_pred = tf.equal(max_idx_p, max_idx_l)
accuracy = tf.reduce_mean(tf.cast(correct_pred, tf.float32))
with tf.Session() as sess:
sess.run(tf.global_variables_initializer())
step = 0
while True:
batch_x, batch_y = get_next_batch(64)
_, loss_ = sess.run([optimizer, loss],
feed_dict={X: batch_x, Y: batch_y, keep_prob: 0.75, train_phase: True})
print(step, loss_)
if step % 10 == 0 and step != 0:
batch_x_test, batch_y_test = get_next_batch(100)
acc = sess.run(accuracy,
feed_dict={X: batch_x_test, Y: batch_y_test, keep_prob: 1., train_phase: False})
print("step %s，accuracy：%s" % (step, acc))
if acc > 0.05:
# stop training and save parameters in layer
result_weights['wc1'] = weights['wc1'].eval(sess)
...
break
step += 1
Create new graph for exporting:
EXPORT_DIR = './model'
if os.path.exists(EXPORT_DIR):
shutil.rmtree(EXPORT_DIR)
g = tf.Graph()
with g.as_default():
x_2 = tf.placeholder(tf.float32, shape=[None, IMAGE_HEIGHT * IMAGE_WIDTH], name="input")
x_image = tf.reshape(x_2, shape=[-1, IMAGE_HEIGHT, IMAGE_WIDTH, 1])
# fill trained parameters and create new cnn layers
WC1 = tf.constant(result_weights['wc1'], name="WC1")
...
**# crash here!!!**
CONV1 = conv2d(WC1, BC1, x_image, tf.constant(0.0, shape=[32]),
tf.random_normal(shape=[32], mean=1.0, stddev=0.02), scope='BN_1')
OUTPUT = tf.add(tf.matmul(FULL1, W_OUT), B_OUT)
OUTPUT = tf.nn.sigmoid(OUTPUT, name="output")
sess = tf.Session()
sess.run(tf.global_variables_initializer())
graph_def = g.as_graph_def()
tf.train.write_graph(graph_def, EXPORT_DIR, 'phone_model_graph.pb', as_text=True)
I create a new graph at last. The exception means it uses incorrect parameter in old training graph. How to explain it?
Thank you very much!
Log is:
I call batch_norm in fuction conv2d. It seems no tensor passed to the new graph.
def conv2d(w, b, x, tf_constant, tf_random_normal, scope, keep_p=1., phase=tf.constant(False)):
out = tf.nn.bias_add(tf.nn.conv2d(x, w, strides=[1, 1, 1, 1], padding='SAME'), b)
out = batch_norm(out, tf_constant, tf_random_normal, phase, scope=scope)
out = tf.nn.relu(out)
out = tf.nn.max_pool(out, ksize=[1, 2, 2, 1], strides=[1, 2, 2, 1], padding='SAME')
out = tf.nn.dropout(out, keep_p)
return out
I create a new graph at last.
That's the key statement here: upon creation of a new graph one can't use any tensor from the old graph. See a detailed explanation in this question. According to the stacktrace, at least one of the tensors that is passed to the batch_norm is defined before g.as_default(), that's why tensorflow crashes. From your code snippets it's unclear how exactly the batch_norm is called, so I can't say which one.
You can check this hypothesis by printing x.graph and g and checking if these values are different. In order to avoid this problem you can either do all the work inside one graph (which is a recommended way) or define both graphs in different python scopes thus making impossible to accidentally reuse the same python variable in two graphs.
I am using LSTM RNN to detect whether a heart beat is arrhythmic or not. So the output classes are:[0,1] and n_classes=2, but when this code is executed:
# Fit training using batch data
_, loss, acc = sess.run(
[optimizer, cost, accuracy],
feed_dict={
x: batch_xs,
y: batch_ys
}
)
It gives following error
ValueError: Cannot feed value of shape (1, 1) for Tensor 'Placeholder_1:0', which has shape '(?, 2)'
Here is the whole code:
import numpy as np
import matplotlib
import matplotlib.pyplot as plt
import tensorflow as tf # Version 1.0.0 (some previous versions are used in past commits)
from sklearn import metrics
import _pickle as cPickle
import os
import pandas as pd
import functions as f
[ml2_train_input,ml2_train_output,ml2_train_peaks,ml2_test_input,ml2_test_output,ml2_test_peaks]=f.get_ml2(0.5)
ml2_train_output=f.get_binary_output(ml2_train_output[:52500])
ml2_test_output=f.get_binary_output(ml2_test_output[:52500])
# Output classes to learn how to classify
LABELS = [0,1 ]
training_data_count = len(ml2_train_input[:52500]) # training series
test_data_count = len(ml2_test_input[:52500]) # testing series
n_input = 360 # 360 input parameters per timestep
# LSTM Neural Network's internal structure
n_hidden = 8 # Hidden layer num of features
n_classes = 2 # Total classes
# Training
learning_rate = 0.005
lambda_loss_amount = 0.0015
training_iters = training_data_count * 10 # Loop 10 times on the dataset
batch_size = 500
display_iter = 1000 # To show test set accuracy during training
X_test=np.array(ml2_test_input[:52500])
y_test=np.array(ml2_test_output[:52500])
# Some debugging info
print("Some useful info to get an insight on dataset's shape and normalisation:")
print("(X shape, y shape, every X's mean, every X's standard deviation)")
print(X_test.shape, y_test.shape, np.mean(X_test), np.std(X_test))
print("The dataset is therefore properly normalised, as expected, but not yet one-hot encoded.")
def LSTM_RNN(_X, _weights, _biases):
# Function returns a tensorflow LSTM (RNN) artificial neural network from given parameters.
# Moreover, two LSTM cells are stacked which adds deepness to the neural network.
# Note, some code of this notebook is inspired from an slightly different
# RNN architecture used on another dataset, some of the credits goes to
# "aymericdamien" under the MIT license.
# (NOTE: This step could be greatly optimised by shaping the dataset once
# input shape: (batch_size, n_steps, n_input)
# permute n_steps and batch_size
# Reshape to prepare input to hidden activation
#_X = tf.reshape(_X, [-1, n_input])
# new shape: (n_steps*batch_size, n_input)
# Linear activation
_X = tf.nn.relu(tf.matmul(_X, _weights['hidden']) + _biases['hidden'])
# Split data because rnn cell needs a list of inputs for the RNN inner loop
_X = tf.split(_X, 500,0)
# new shape: n_steps * (batch_size, n_hidden)
# Define two stacked LSTM cells (two recurrent layers deep) with tensorflow
lstm_cell_1 = tf.contrib.rnn.BasicLSTMCell(n_hidden, forget_bias=1.0, state_is_tuple=True,reuse=None)
lstm_cell_2 = tf.contrib.rnn.BasicLSTMCell(n_hidden, forget_bias=1.0, state_is_tuple=True,reuse=None)
lstm_cells = tf.contrib.rnn.MultiRNNCell([lstm_cell_1, lstm_cell_2], state_is_tuple=True)
# Get LSTM cell output
outputs, states = tf.contrib.rnn.static_rnn(lstm_cells, _X, dtype=tf.float32)
# Get last time step's output feature for a "many to one" style classifier,
# as in the image describing RNNs at the top of this page
lstm_last_output = outputs[-1]
# Linear activation
return tf.matmul(lstm_last_output, _weights['out']) + _biases['out']
def extract_batch_size(_train, step, batch_size):
# Function to fetch a "batch_size" amount of data from "(X|y)_train" data.
shape = list(_train.shape)
shape[0] = batch_size
batch_s = np.empty(shape)
for i in range(batch_size):
# Loop index
index = ((step-1)*batch_size + i) % len(_train)
batch_s[i] = _train[index]
return batch_s
def one_hot(y_):
# Function to encode output labels from number indexes
# e.g.: [[5], [0], [3]] --> [[0, 0, 0, 0, 0, 1], [1, 0, 0, 0, 0, 0], [0, 0, 0, 1, 0, 0]]
y_ = y_.reshape(len(y_))
n_values = int(np.max(y_)) + 1
return np.eye(n_values)[np.array(y_, dtype=np.int32)] # Returns FLOATS
# Graph input/output
x = tf.placeholder(tf.float32, [None, n_input])
y = tf.placeholder(tf.float32, [None, n_classes])
# Graph weights
weights = {
'hidden': tf.Variable(tf.random_normal([n_input, n_hidden])), # Hidden layer weights
'out': tf.Variable(tf.random_normal([n_hidden, n_classes], mean=1.0))
}
biases = {
'hidden': tf.Variable(tf.random_normal([n_hidden])),
'out': tf.Variable(tf.random_normal([n_classes]))
}
pred = LSTM_RNN(x, weights, biases)
# Loss, optimizer and evaluation
l2 = lambda_loss_amount * sum(
tf.nn.l2_loss(tf_var) for tf_var in tf.trainable_variables()
) # L2 loss prevents this overkill neural network to overfit the data
cost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(labels=y, logits=pred)) + l2 # Softmax loss
optimizer = tf.train.AdamOptimizer(learning_rate=learning_rate).minimize(cost) # Adam Optimizer
correct_pred = tf.equal(tf.argmax(pred,1), tf.argmax(y,1))
accuracy = tf.reduce_mean(tf.cast(correct_pred, tf.float32))
# To keep track of training's performance
test_losses = []
test_accuracies = []
train_losses = []
train_accuracies = []
# Launch the graph
sess = tf.InteractiveSession(config=tf.ConfigProto(log_device_placement=True))
init = tf.global_variables_initializer()
sess.run(init)
X_train=np.array(ml2_train_input[:52500])
y_train=np.array(ml2_train_output[:52500])
step = 1
while step * batch_size <= training_iters:
batch_xs = extract_batch_size(X_train, step, batch_size)
batch_ys = one_hot(extract_batch_size(y_train, step, batch_size))
# Fit training using batch data
_, loss, acc = sess.run(
[optimizer, cost, accuracy],
feed_dict={
x: batch_xs,
y: batch_ys
}
)
train_losses.append(loss)
train_accuracies.append(acc)
# Evaluate network only at some steps for faster training:
if (step*batch_size % display_iter == 0) or (step == 1) or (step * batch_size > training_iters):
# To not spam console, show training accuracy/loss in this "if"
print("Training iter #" + str(step*batch_size) + \
": Batch Loss = " + "{:.6f}".format(loss) + \
", Accuracy = {}".format(acc))
# Evaluation on the test set (no learning made here - just evaluation for diagnosis)
loss, acc = sess.run(
[cost, accuracy],
feed_dict={
x: X_test,
y: one_hot(y_test)
}
)
test_losses.append(loss)
test_accuracies.append(acc)
print("PERFORMANCE ON TEST SET: " + \
"Batch Loss = {}".format(loss) + \
", Accuracy = {}".format(acc))
step += 1
print("Optimization Finished!")
Please help!
I feel you should convert your Y values to categorical (one-hot encoded) than it should work. So try to convert your Y values to categorical
I'm trying to build a softmax regression model for CIFAR classification. At first when I tried to pass in my images and labels into the feed dictionary, I got an error that said that feed dictionaries do not accept Tensors. I then converted them into numpy arrays using .eval() but the program hangs at the .eval() line and does not continue any further. How can I pass this data into the feed_dict?
CIFARIMAGELOADING.PY
import tensorflow as tf
import os
import tensorflow.models.image.cifar10 as cf
IMAGE_SIZE = 24
BATCH_SIZE = 128
def loadimagesandlabels(size):
# Load the images from the CIFAR data directory
FLAGS = tf.app.flags.FLAGS
data_dir = os.path.join(FLAGS.data_dir, 'cifar-10-batches-bin')
filenames = [os.path.join(data_dir, 'data_batch_%d.bin' % i) for i in xrange(1, 6)]
filename_queue = tf.train.string_input_producer(filenames)
read_input = cf.cifar10_input.read_cifar10(filename_queue)
# Reshape and crop the image
height = IMAGE_SIZE
width = IMAGE_SIZE
reshaped_image = tf.cast(read_input.uint8image, tf.float32)
cropped_image = tf.random_crop(reshaped_image, [height, width, 3])
# Generate a batch of images and labels by building up a queue of examples
print('Filling queue with CIFAR images')
num_preprocess_threads = 16
min_fraction_of_examples_in_queue = 0.4
min_queue_examples = int(BATCH_SIZE*min_fraction_of_examples_in_queue)
images, label_batch = tf.train.batch([cropped_image,read_input.label],batch_size=BATCH_SIZE, num_threads=num_preprocess_threads, capacity=min_queue_examples+3*BATCH_SIZE)
print(images)
print(label_batch)
return images, tf.reshape(label_batch, [BATCH_SIZE])
CIFAR.PY
#Set up placeholder vectors for image and labels
x = tf.placeholder(tf.float32, shape = [None, 1728])
y_ = tf.placeholder(tf.float32, shape = [None,10])
W = tf.Variable(tf.zeros([1728,10]))
b = tf.Variable(tf.zeros([10]))
#Implement regression model. Multiply input images x by weight matrix W, add the bias b
#Compute the softmax probabilities that are assigned to each class
y = tf.nn.softmax(tf.matmul(x,W) + b)
#Define cross entropy
#tf.reduce sum sums across all classes and tf.reduce_mean takes the average over these sums
cross_entropy = tf.reduce_mean(-tf.reduce_sum(y_*tf.log(y), reduction_indices = [1]))
#Train the model
#Each training iteration we load 128 training examples. We then run the train_step operation
#using feed_dict to replace the placeholder tensors x and y_ with the training examples
train_step = tf.train.GradientDescentOptimizer(0.5).minimize(cross_entropy)
#Open up a Session
init = tf.initialize_all_variables()
sess = tf.Session()
sess.run(init)
for i in range(1000) :
images, labels = CIFARImageLoading.loadimagesandlabels(size=BATCH_SIZE)
unrolled_images = tf.reshape(images, (1728, BATCH_SIZE))
#convert labels to their one_hot representations
# should produce [[1,0,0,...],[0,1,0...],...]
one_hot_labels = tf.one_hot(indices= labels, depth=NUM_CLASSES, on_value=1.0, off_value= 0.0, axis=-1)
print(unrolled_images)
print(one_hot_labels)
images_numpy, labels_numpy = unrolled_images.eval(session=sess), one_hot_labels.eval(session=sess)
sess.run(train_step, feed_dict = {x: images_numpy, y_:labels_numpy})
#Evaluate the model
#.equal returns a tensor of booleans, we want to cast these as floats and then take their mean
#to get percent correctness (accuracy)
print("evaluating")
test_images, test_labels = CIFARImageLoading.loadimagesandlabels(TEST_SIZE)
test_images_unrolled = tf.reshape(test_images, (1728, TEST_SIZE))
test_images_one_hot = tf.one_hot(indices= test_labels, depth=NUM_CLASSES, on_value=1.0, off_value= 0.0, axis=-1)
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: unrolled_images.eval(), y_ : test_images_one_hot.eval()}))
Theres a couple of things that you not are understanding really well. Throughout your graph you will work with Tensors. You define Tensors by either using tf.placeholder and feeding them in the session.run(feed_dict{}) or with tf.Variable and initializing it with session.run(tf.initialize_all_variables()). You must feed your input this way, and it should be numpy arrays in the same as shape as you expect in the placeholders. Here's a simple example:
images = tf.placeholder(type, [1728, BATCH_SIZE])
labels = tf.placeholder(type, [size])
'''
Build your network here so you have the variable: Output
'''
images_feed, labels_feed = CIFARImageLoading.loadimagesandlabels(size=BATCH_SIZE)
# here you can see your output
print sess.run(Output, feed_dict = {x: images_feed, y_:labels_feed})
You do not feed tf.functions with numpy arrays, you always feed them with Tensors. And the feed_dict is always fed with numpy arrays. The thing is: you will never have to convert tensors to numpy arrays for the input, that does not make sense. Your input must be numpy arrays, if it's a list, you can use np.asarray(list), if it's a tensor, you are doing this wrong.
I do not know what CIFARImageLoading.loadimagesandlabels returns to you, but I imagine it's not a Tensor, it's probably a numpy array already, so just get rid of this .eval().
I have a simple program, mostly copied from the MNIST tutorial on Tensorflow. I have a 2D array 118 items long, with each subarray being 13 long. And a 2nd 2D array that is 118 long with a single integer in each sub array, containing either 1, 2, or 3 (the matching class of the first array's item)
Whenever I run it however, I get various dimension errors.
either ValueError: Dimensions X and X are not compatible
or ValueError: Incompatible shapes for broadcasting: (?, 13) and (3,)
or something along those lines. I've tried most every combination of numbers I can think of here in the various places to get it to align properly but am unable to get it to.
x = tf.placeholder(tf.float32, [None, 13])
W = tf.Variable(tf.zeros([118, 13]))
b = tf.Variable(tf.zeros([3]))
y = tf.nn.softmax(tf.matmul(x, W) + b)
y_ = tf.placeholder(tf.float32, [None, 13])
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 = npWineList
batch_ys = npWineClass
sess.run(train_step, feed_dict={x: batch_xs, y_: batch_ys})
correct_prediction = tf.equal(tf.argmax(y,1), tf.argmax(y_,1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
print(sess.run(accuracy, feed_dict={x: mnist.test.images, y_: mnist.test.labels}))
First, it's not clear how many labels you have (3 or 13), and what is the size of input (X) vector (113 or 13)? I assume you have 13 labels, and 118 X vectors based on:
W = tf.Variable(tf.zeros([118, 13]))
y_ = tf.placeholder(tf.float32, [None, 13])
Then, you may change your code something like this:
x = tf.placeholder(tf.float32, [None, 118])
W = tf.Variable(tf.zeros([118, 13]))
b = tf.Variable(tf.zeros([13]))
y = tf.nn.softmax(tf.matmul(x, W) + b)
y_ = tf.placeholder(tf.float32, [None, 13])
Let me know it addresses your issue.