Related
Can i get a full example somewhere where they feed tf.data.Dataset iterator to a model? I'm trying to feed this data into a model without the help of tf.Estimators.
def preprocess_image(image):
image = tf.image.decode_jpeg(image, channels=1)
image = tf.image.resize_images(image, [224, 224])
image = tf.image.random_flip_left_right(image)
image /= 255.0
image = tf.cast(image, tf.float32)
image = tf.train.shuffle_batch([image],batch_size=16, num_threads=10, capacity=100000, min_after_dequeue=15)
return image
def load_and_preprocess_image(path):
image = tf.read_file(path)
return preprocess_image(image)
train_data_dx = tf.data.Dataset.from_tensor_slices(xray_data_train['full_path'].values)
train_data_dx = train_data_dx.map(load_and_preprocess_image, num_parallel_calls=8)
train_data_dy = xray_data_train['Finding_strings']
print(train_data_dx.output_shapes)
print(train_data_dx.output_types)
test_data_dx = tf.data.Dataset.from_tensor_slices(xray_data_test['full_path'].values)
test_data_dx = test_data_dx.map(load_and_preprocess_image, num_parallel_calls=8)
test_data_dy = xray_data_test['Finding_strings']
Here's a full example.
Note
Iterator must be initialized at the beginning
We can set number of epochs to perform by using repeat() method of number of epochs and batch() method for batch size. Note that I use first repeat() and then batch().
At each iteration we're using tf.Session() interface to access the next batch.
We use try-except since when repetition of data ends it raises tf.error.OutOfRangeError.
import tensorflow as tf
from sklearn.datasets import make_blobs
# generate dummy data for illustration
x_train, y_train = make_blobs(n_samples=25,
n_features=2,
centers=[[1, 1], [-1, -1]],
cluster_std=0.5)
n_epochs = 2
batch_size = 10
with tf.name_scope('inputs'):
x = tf.placeholder(tf.float32, shape=[None, 2])
y = tf.placeholder(tf.int32, shape=[None])
with tf.name_scope('logits'):
logits = tf.layers.dense(x,
units=2,
name='logits')
with tf.name_scope('loss'):
xentropy = tf.nn.sparse_softmax_cross_entropy_with_logits(labels=y, logits=logits)
loss_tensor = tf.reduce_mean(xentropy)
with tf.name_scope('optimizer'):
train_op = tf.train.GradientDescentOptimizer(0.01).minimize(loss_tensor)
# create dataset `from_tensor_slices` and create iterator
dataset = tf.data.Dataset.from_tensor_slices({'x':x_train, 'y':y_train})
dataset = dataset.repeat(n_epochs).batch(10)
iterator = dataset.make_initializable_iterator()
with tf.Session() as sess:
sess.run([tf.global_variables_initializer(),
iterator.initializer]) # <-- must be initialized!
next_batch = iterator.get_next()
while True:
try:
batch = sess.run(next_batch) # <-- extract next batch
loss_val, _ = sess.run([loss_tensor, train_op],
feed_dict={x:batch['x'], y:batch['y']})
print(loss_val)
except tf.errors.OutOfRangeError:
break
I've created this graph to try:
Import BMP files and generate label based on their filename (L/R).
Train a network to determine between the left and right eye.
Evaluate the network.
I'm using the new framework and get it all in as a dataset. The code runs, but I only get 50% accuracy (no learning happening).
Can anyone check that the graph is right and it's just my network I need to fix ?
""" Routine for processing Eye Image dataset
determines left/right eye
Using Tensorflow API v1.3
"""
from __future__ import absolute_import
from __future__ import division
from __future__ import print_function
import os
import fnmatch
import tensorflow as tf
from six.moves import xrange # pylint: disable=redefined-builtin
import nnLayers as nnLayer
IMAGE_SIZE = 460
SCALE_SIZE = 100
NUM_CLASSES = 2
IMAGE_DEPTH = 3
FLAGS = tf.app.flags.FLAGS
# Basic model parameters.
tf.app.flags.DEFINE_integer('batch_size', 200,
"""Number of images to process in a batch.""")
tf.app.flags.DEFINE_integer('num_epochs', 1001,
"""Number of images to process in a batch.""")
tf.app.flags.DEFINE_string('train_directory', './eyeImages',
"""directory of images to process.""")
tf.app.flags.DEFINE_string('test_directory', './eyeTest',
"""directory of images to process.""")
tf.app.flags.DEFINE_string('log_dir', './logs',
"""logging directory""")
def _parse_function(filename, label):
"""Takes filenames and labels and returns
one hot labels and image values"""
#read the file
image_string = tf.read_file(filename)
#decode BMP file
image_decoded = tf.image.decode_bmp(image_string)
#resize accordingly
image = tf.image.resize_images(image_decoded, [SCALE_SIZE, SCALE_SIZE])
#convert label to one hot
one_hot = tf.one_hot(label, NUM_CLASSES)
return image, one_hot
def inference(image):
#shape image for convolution
with tf.name_scope('input_reshape'):
x_image = tf.reshape(image, [-1, SCALE_SIZE, SCALE_SIZE, IMAGE_DEPTH]) #infer number of images, last dimension is features
tf.summary.image('input_images',x_image)
#neural net layers
#100x100x3 -> 50x50x32
h_pool1 = nnLayer.conv_layer(x_image, IMAGE_DEPTH, 5, 32, 'hiddenLayer1', act=tf.nn.relu)
#50x50x32 -> 25x25x64
h_pool2 = nnLayer.conv_layer(h_pool1, 32, 5, 64, 'hiddenLayer2', act=tf.nn.relu)
#25x25x64 -> 1024x2
h_fc1 = nnLayer.fc_layer(h_pool2, 64, 25, 1024, 'fcLayer1', act=tf.nn.relu)
#1024x2 ->1x2
with tf.name_scope('final-layer'):
with tf.name_scope('weights'):
W_fc2 = nnLayer.weight_variable([1024,NUM_CLASSES])
with tf.name_scope('biases'):
b_fc2 = nnLayer.bias_variable([NUM_CLASSES])
y_conv = tf.matmul(h_fc1, W_fc2) + b_fc2
return y_conv
def folderParser(folder):
"""output BMP file names in directory and
label based on file name"""
#create list of filenames in directory
files = os.listdir(folder)
#filter for BMP files
bmpfiles = fnmatch.filter(files, '*.bmp')
#create empty lists
labels = []
fullNames = []
#get the length of the filename and determine left/right label
for i in range(len(bmpfiles)):
length = len(bmpfiles[i])
fullNames.append(folder + '/' + bmpfiles[i])
if (bmpfiles[i][length-17])=='L':
labels.append(1)
else:
labels.append(0)
return fullNames,labels
def main(argv=None): # pylint: disable=unused-argument
#delete the log files if present
#if tf.gfile.Exists(FLAGS.log_dir):
# tf.gfile.DeleteRecursively(FLAGS.log_dir)
#tf.gfile.MakeDirs(FLAGS.log_dir)
#get file names and labels
trainNames, trainLabels = folderParser(FLAGS.train_directory)
testNames, testLabels = folderParser(FLAGS.test_directory)
# create a dataset of the file names and labels
tr_data = tf.contrib.data.Dataset.from_tensor_slices((trainNames, trainLabels))
ts_data = tf.contrib.data.Dataset.from_tensor_slices((testNames, testLabels))
#map the data set from file names to images
tr_data = tr_data.map(_parse_function)
ts_data = ts_data.map(_parse_function)
#shuffle the images
tr_data = tr_data.shuffle(FLAGS.batch_size*2)
ts_data = ts_data.shuffle(FLAGS.batch_size*2)
#create batches
tr_data = tr_data.batch(FLAGS.batch_size)
ts_data = ts_data.batch(FLAGS.batch_size)
#create handle for datasets
handle = tf.placeholder(tf.string, shape=[])
iterator = tf.contrib.data.Iterator.from_string_handle(handle, tr_data.output_types, tr_data.output_shapes)
next_element = iterator.get_next()
#setup iterator
training_iterator = tr_data.make_initializable_iterator()
validation_iterator = ts_data.make_initializable_iterator()
#retrieve next batch
features, labels = iterator.get_next()
#run network
y_conv = inference(features)
#determine softmax and loss function
with tf.variable_scope('softmax_linear') as scope:
diff = tf.nn.softmax_cross_entropy_with_logits(labels=labels, logits=y_conv)
with tf.name_scope('total'):
cross_entropy = tf.reduce_mean(diff)
tf.summary.scalar('cross_entropy', cross_entropy)
#run gradient descent
with tf.name_scope('train'):
training_op = tf.train.GradientDescentOptimizer(1e-3).minimize(cross_entropy)
#identify correct predictions
with tf.name_scope('correct_prediction'):
correct_prediction = tf.equal(tf.argmax(y_conv, 1), tf.argmax(labels, 1))
#find the accuracy of the model
with tf.name_scope('accuracy'):
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
tf.summary.scalar('accuracy', accuracy)
with tf.Session() as sess:
#initialization of the variables
training_handle = sess.run(training_iterator.string_handle())
validation_handle = sess.run(validation_iterator.string_handle())
sess.run(tf.global_variables_initializer())
#merge all the summaries and write test summaries
merged = tf.summary.merge_all()
train_writer = tf.summary.FileWriter(FLAGS.log_dir + '/train', sess.graph)
test_writer = tf.summary.FileWriter(FLAGS.log_dir + '/test')
#run through epochs
for epoch in range(FLAGS.num_epochs):
#initialize the training set for training epoch
sess.run(training_iterator.initializer)
if epoch % 2 ==0:
#initialize validation set
sess.run(validation_iterator.initializer)
#test
summary, acc = sess.run([merged, accuracy], feed_dict={handle: validation_handle})
train_writer.add_summary(summary, epoch) #write to test file
print('step %s, accuracy %s' % (epoch, acc))
else:
#train
sess.run(training_op, feed_dict={handle: training_handle})
#close the log files
train_writer.close()
test_writer.close()
if __name__ == '__main__':
tf.app.run()
Aaron
The answer was image standardization:
image_std = tf.image.per_image_standardization (image_resized)
Without the image standardization the neurons were becoming saturated. Improved the outcome straight away.
Thanks.
I am trying to create an end-to-end trainable offline English Handwriting Recognition Model (without segmenting individual character). I am using the word dataset from IAM Handwriting Database for training.
I tried decreasing the learning rate, increasing batch size, etc. but the loss keeps on fluctuating with no/significant overall decrease - TensorBoard visualization for cost at each step
I am new to TensorFlow so could have made some naive error. The code used:
class CRNN(object):
def __init__(self, config):
self.config = config
tf.reset_default_graph()
def read_and_decode(self, filename_queue):
reader = tf.TFRecordReader()
_, serialized_example = reader.read(filename_queue)
# Define how to parse the example
context_features = {
'length': tf.FixedLenFeature([], dtype=tf.int64),
'out_length': tf.FixedLenFeature([], dtype=tf.int64)
}
sequence_features = {
'token': tf.FixedLenSequenceFeature([], dtype=tf.float32),
'labels': tf.FixedLenSequenceFeature([], dtype=tf.int64)
}
context_parsed, sequence_parsed = tf.parse_single_sequence_example(
serialized=serialized_example,
context_features=context_features,
sequence_features=sequence_features)
image = sequence_parsed['token']
label = tf.cast(sequence_parsed['labels'], tf.int32)
length = tf.cast(context_parsed['length'], tf.int32)
lab_length = tf.cast(context_parsed['out_length'], tf.int32)
image_shape = tf.cast(tf.stack([self.config.im_height,
length/self.config.im_height]), tf.int32)
image = tf.reshape(image, image_shape)
# Updating length to represent image width
length = tf.shape(image)[1]
# Batch the variable length tensor with dynamic padding
self.images, self.labels, self.lengths, self.lab_lengths = tf.train.batch(
tensors=[image, label, length, lab_length],
batch_size=self.config.batch_size, dynamic_pad=True)
def net(self):
batch_lab_length = tf.reduce_max(self.lab_lengths)
batch_im_length = tf.reduce_max(self.lengths)
# Reshape to time major
sequences = tf.reshape(self.images, [batch_im_length, self.config.batch_size,
self.config.im_height])
# Feed sequences into RNN
with tf.name_scope('RNN'):
self.cell_fw = tf.nn.rnn_cell.LSTMCell(num_units=self.config.rnn_num_hidden,
state_is_tuple=True)
self.cell_bw = tf.nn.rnn_cell.LSTMCell(num_units=self.config.rnn_num_hidden,
state_is_tuple=True)
self.output, self.state = tf.nn.bidirectional_dynamic_rnn(
cell_fw=self.cell_fw,
cell_bw=self.cell_bw,
inputs=sequences,
dtype=tf.float32,
sequence_length=self.lengths,
time_major=True,
scope='RNN'
)
# Reshaping to apply the same weights over the timesteps
self.output = tf.reshape(self.output, [-1, self.config.rnn_num_hidden])
self.out_W = tf.Variable(tf.truncated_normal([self.config.rnn_num_hidden,
self.config.num_classes],
stddev=0.1), name='out_W')
self.out_b = tf.Variable(tf.constant(0., shape=[self.config.num_classes]), name='out_b')
# Doing the affine projection
logits = tf.matmul(self.output, self.out_W) + self.out_b
# Reshaping back to the original shape
logits = tf.reshape(logits, [self.config.batch_size, -1, self.config.num_classes])
# Time major
logits = tf.transpose(logits, (1, 0, 2))
# Training computation
# Prepare sparse tensor for CTC loss
labs = tf.reshape(self.labels, (self.config.batch_size, batch_lab_length))
sparse_tensor_indices = tf.where(tf.less(tf.cast(0, tf.int32), labs))
labels_vals = tf.reshape(self.labels, [batch_lab_length*self.config.batch_size])
mask = tf.cast(tf.sign(labels_vals), dtype=tf.bool)
labels_vals = tf.boolean_mask(labels_vals,mask)
labels_sparse = tf.SparseTensor(indices=sparse_tensor_indices, values=labels_vals,
dense_shape=[self.config.batch_size,
tf.cast(batch_lab_length, tf.int64)])
self.loss = tf.nn.ctc_loss(labels_sparse, logits, sequence_length=self.lab_lengths,
preprocess_collapse_repeated=False, ctc_merge_repeated=False,
time_major=True)
self.cost = tf.reduce_mean(self.loss)
# Optimizer
self.optimizer = tf.train.MomentumOptimizer(learning_rate=0.01,
momentum=0.9, use_nesterov=True).minimize(self.cost)
# Predictions for the training, validation, and test data.
self.train_prediction = tf.nn.ctc_beam_search_decoder(logits,
sequence_length=self.lab_lengths)
def train(self):
num_steps = int((self.config.num_epochs*self.config.sample_size)/self.config.batch_size)
tf.reset_default_graph()
filename_queue = tf.train.string_input_producer(
[self.config.tfrecord_filename], num_epochs=self.config.num_epochs)
self.read_and_decode(filename_queue)
self.net()
# The op for initializing the variables.
init_op = tf.group(tf.global_variables_initializer(),
tf.local_variables_initializer())
saver = tf.train.Saver()
with tf.Session() as sess:
training_summary = tf.summary.scalar("training_cost", self.cost)
writer = tf.summary.FileWriter("./TensorBoard/graph", sess.graph)
sess.run(init_op)
print('Initialized')
coord = tf.train.Coordinator()
threads = tf.train.start_queue_runners(coord=coord)
start = time.time()
steps_time = start
epoch = 1
for step in range(num_steps):
_, c, predictions, actual_labels, train_summ = sess.run([self.optimizer, self.cost,
self.train_prediction,
self.labels, training_summary])
writer.add_summary(train_summ, step)
if (step % 10000 == 0):
preds = np.zeros((predictions[0][0].dense_shape))
i = 0
for idx in predictions[0][0].indices:
preds[idx[0]][idx[1]] = predictions[0][0].values[i]
i+=1
print(time.time() - steps_time)
steps_time = time.time()
print('Minibatch cost at step %d: %f' % (step, c))
print('Label =', [''.join([char_map_inv[j] for j in i]) for i in actual_labels],
'Prediction =', [''.join([char_map_inv[j] for j in i]) for i in preds])
if (step!=0 and step % int(self.config.sample_size/self.config.batch_size) == 0):
print('Epoch', epoch, 'Completed')
epoch+=1
last_step = step
saver.save(sess, "model_BLSTM", global_step=last_step)
writer.close()
print(time.time() - start)
After trying a lot of things unsuccessfully, I found that an incorrect argument was provided to the sequence_length argument of tf.nn.ctc_loss. It should be set to 'length of input sequence' but I had set it to 'length of output sequence(labels - number of character)'
More details can be found in comments under the selected answer to this question - CTC Loss InvalidArgumentError: sequence_length(b) <= time
Also, if one has a GPU it would be better to use Baidu's CTC GPU implementation (https://github.com/baidu-research/warp-ctc) as it can speed up the training a lot.
The problem is that you are feeding raw images in the LSTM, so it is very difficult for it to extract any useful information. The CRNN paper first uses a series of convolutional layers to extract features from the images, and then these are fed into the LSTM.
I have read many similar questions and just cannot get this to work properly.
I have my model being trained well and checkpoint files are being made every epoch. I want to have it so the program can continue from epoch x once reloaded and also for it to print that is on that epoch with every iteration. I could simply save the data outside of the checkpoint file, however I was also wanting to do this to give me confidence everything else is also being stored properly.
Unfortunately the value in the epoch/global_step variable is always still 0 when I restart.
import tensorflow as tf
import numpy as np
import tensorflow as tf
import numpy as np
# more imports
def extract_number(f): # used to get latest checkpint file
s = re.findall("epoch(\d+).ckpt",f)
return (int(s[0]) if s else -1,f)
def restore(init_op, sess, saver): # called to restore or just initialise model
list = glob(os.path.join("./params/e*"))
if list:
file = max(list,key=extract_number)
saver.restore(sess, file[:-5])
sess.run(init_op)
return
with tf.Graph().as_default() as g:
# build models
total_batch = data.train.num_examples / batch_size
epochLimit = 51
saver = tf.train.Saver()
init_op = tf.global_variables_initializer()
with tf.Session() as sess:
saver = tf.train.Saver()
init_op = tf.global_variables_initializer()
restore(init_op, sess, saver)
epoch = global_step.eval()
while epoch < epochLimit:
total_batch = data.train.num_examples / batch_size
for i in range(int(total_batch)):
sys.stdout.flush()
voxels = newData.eval()
batch_z = np.random.uniform(-1, 1, [batch_size, z_size]).astype(np.float32)
sess.run(opt_G, feed_dict={z:batch_z, train:True})
sess.run(opt_D, feed_dict={input:voxels, z:batch_z, train:True})
with open("out/loss.csv", 'a') as f:
batch_loss_G = sess.run(loss_G, feed_dict={z:batch_z, train:False})
batch_loss_D = sess.run(loss_D, feed_dict={input:voxels, z:batch_z, train:False})
msgOut = "Epoch: [{0}], i: [{1}], G_Loss[{2:.8f}], D_Loss[{3:.8f}]".format(epoch, i, batch_loss_G, batch_loss_D)
print(msgOut)
epoch=epoch+1
sess.run(global_step.assign(epoch))
saver.save(sess, "params/epoch{0}.ckpt".format(epoch))
batch_z = np.random.uniform(-1, 1, [batch_size, z_size]).astype(np.float32)
voxels = sess.run(x_, feed_dict={z:batch_z})
v = voxels[0].reshape([32, 32, 32]) > 0
util.save_binvox(v, "out/epoch{0}.vox".format(epoch), 32)
I also update the global step variable using assign at the bottom. Any ideas? Any help would be greatly appreciated.
When you call sess.run(init_op) after restoring this resets all variables to their initial values. Comment that line out and things should work.
My original code was wrong for several reasons because I was trying so many things. The first responder Alexandre Passos gives a valid point, but I believe what changed the game was also the use of scopes (maybe?).
Below is the working updated code if it helps anyone:
import tensorflow as tf
import numpy as np
# more imports
def extract_number(f): # used to get latest checkpint file
s = re.findall("epoch(\d+).ckpt",f)
return (int(s[0]) if s else -1,f)
def restore(sess, saver): # called to restore or just initialise model
list = glob(os.path.join("./params/e*"))
if list:
file = max(list,key=extract_number)
saver.restore(sess, file[:-5])
return saver, True, sess
saver = tf.train.Saver()
init_op = tf.global_variables_initializer()
sess.run(init_op)
return saver, False , sess
batch_size = 100
learning_rate = 0.0001
beta1 = 0.5
z_size = 100
save_interval = 1
data = dataset.read()
total_batch = data.train.num_examples / batch_size
def fill_queue():
for i in range(int(total_batch*epochLimit)):
sess.run(enqueue_op, feed_dict={batch: data.train.next_batch(batch_size)}) # runnig in seperate thread to feed a FIFOqueue
with tf.variable_scope("glob"):
global_step = tf.get_variable(name='global_step', initializer=0,trainable=False)
# build models
epochLimit = 51
saver = tf.train.Saver()
with tf.Session() as sess:
saver,rstr,sess = restore(sess, saver)
with tf.variable_scope("glob", reuse=True):
epocht = tf.get_variable(name='global_step', trainable=False, dtype=tf.int32)
epoch = epocht.eval()
while epoch < epochLimit:
total_batch = data.train.num_examples / batch_size
for i in range(int(total_batch)):
sys.stdout.flush()
voxels = newData.eval()
batch_z = np.random.uniform(-1, 1, [batch_size, z_size]).astype(np.float32)
sess.run(opt_G, feed_dict={z:batch_z, train:True})
sess.run(opt_D, feed_dict={input:voxels, z:batch_z, train:True})
with open("out/loss.csv", 'a') as f:
batch_loss_G = sess.run(loss_G, feed_dict={z:batch_z, train:False})
batch_loss_D = sess.run(loss_D, feed_dict={input:voxels, z:batch_z, train:False})
msgOut = "Epoch: [{0}], i: [{1}], G_Loss[{2:.8f}], D_Loss[{3:.8f}]".format(epoch, i, batch_loss_G, batch_loss_D)
print(msgOut)
epoch=epoch+1
sess.run(global_step.assign(epoch))
saver.save(sess, "params/epoch{0}.ckpt".format(epoch))
batch_z = np.random.uniform(-1, 1, [batch_size, z_size]).astype(np.float32)
voxels = sess.run(x_, feed_dict={z:batch_z})
v = voxels[0].reshape([32, 32, 32]) > 0
util.save_binvox(v, "out/epoch{0}.vox".format(epoch), 32)
I am trying to build a CNN, I have 8 classes in the input_samples with 45 samples in each class. so total number of input samples are 360. I have divided my first 20 samples as train samples and remaining 25 samples as test samples in each class (My input is a text file and the data is in rows is my preprocessed data, so I am reading the rows in textfile and reshaping the images which are 16x12 size).
I am unable to fix the error in the code
My code:
import numpy as np
import random
import tensorflow as tf
folder = 'D:\\Lab_Project_Files\\TF\\Practice Files\\'
Datainfo = 'dataset_300.txt'
ClassInfo = 'classTrain.txt'
INPUT_WIDTH = 16
IMAGE_HEIGHT = 12
IMAGE_DEPTH = 1
IMAGE_PIXELS = INPUT_WIDTH * IMAGE_HEIGHT # 192 = 12*16
NUM_CLASSES = 8
STEPS = 500
STEP_VALIDATE = 100
BATCH_SIZE = 5
def load_data(file1,file2,folder):
filename1 = folder + file1
filename2 = folder + file2
# loading the data file
x_data = np.loadtxt(filename1, unpack=True)
x_data = np.transpose(x_data)
# loading the class information of the data loaded
y_data = np.loadtxt(filename2, unpack=True)
y_data = np.transpose(y_data)
# divide the data in to test and train data
x_data_train = x_data[np.r_[0:20, 45:65, 90:110, 135:155, 180:200, 225:245, 270:290, 315:335],:]
x_data_test = x_data[np.r_[20:45, 65:90, 110:135, 155:180, 200:225, 245:270, 290:315, 335:360], :]
y_data_train = y_data[np.r_[0:20, 45:65, 90:110, 135:155, 180:200, 225:245, 270:290, 315:335]]
y_data_test = y_data[np.r_[20:45, 65:90, 110:135, 155:180, 200:225, 245:270, 290:315, 335:360],:]
return x_data_train,x_data_test,y_data_train,y_data_test
def reshapedata(data_train,data_test):
data_train = np.reshape(data_train, (len(data_train),INPUT_WIDTH,IMAGE_HEIGHT))
data_test = np.reshape(data_test, (len(data_test), INPUT_WIDTH, IMAGE_HEIGHT))
return data_train,data_test
def batchdata(data,label, batchsize):
# generate random number required to batch data
order_num = random.sample(range(1, len(data)), batchsize)
data_batch = []
label_batch = []
for i in range(len(order_num)):
data_batch.append(data[order_num[i-1]])
label_batch.append(label[order_num[i-1]])
return data_batch, label_batch
# CNN trail
def conv_net(x):
weights = tf.Variable(tf.random_normal([INPUT_WIDTH * IMAGE_HEIGHT * IMAGE_DEPTH, NUM_CLASSES]))
biases = tf.Variable(tf.random_normal([NUM_CLASSES]))
out = tf.add(tf.matmul(x, weights), biases)
return out
sess = tf.Session()
# get filelist and labels for training and testing
data_train,data_test,label_train,label_test = load_data(Datainfo,ClassInfo,folder)
data_train, data_test, = reshapedata(data_train, data_test)
############################ get files for training ####################################################
image_batch, label_batch = batchdata(data_train,label_train,BATCH_SIZE)
# input output placeholders
x = tf.placeholder(tf.float32, [None, IMAGE_PIXELS])
y_ = tf.placeholder(tf.float32,[None, NUM_CLASSES])
# create the network
y = conv_net( x )
# loss
cost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(y, y_))
# train step
train_step = tf.train.AdamOptimizer( 1e-3 ).minimize( cost )
############################## get files for validataion ###################################################
image_batch_test, label_batch_test = batchdata(data_test,label_test,BATCH_SIZE)
correct_prediction = tf.equal(tf.argmax(y,1), tf.argmax(y_,1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
sess.run(tf.initialize_all_variables())
################ CNN Program ##############################
for i in range(STEPS):
# checking the accuracy in between.
if i % STEP_VALIDATE == 0:
imgs, lbls = sess.run([image_batch_test, label_batch_test])
print(sess.run(accuracy, feed_dict={x: imgs, y_: lbls}))
imgs, lbls = sess.run([image_batch, label_batch])
sess.run(train_step, feed_dict={x: imgs, y_: lbls})
imgs, lbls = sess.run([image_batch_test, label_batch_test])
print(sess.run(accuracy, feed_dict={ x: imgs, y_: lbls}))
file can be downloaded dataset_300.txt and ClassInfo.txt
Session.run accepts only a list of tensors or tensor names.
imgs, lbls = sess.run([image_batch_test, label_batch_test])
In the previous line, you are passing image_batch_test and label_batch_test which are numpy arrays. I am not sure what you are trying to do by imgs, lbls = sess.run([image_batch_test, label_batch_test])