Related
I have been getting this error and i cant figure out the reason. if anyone could help would be great.
this is my code:
import numpy as np
import pickle
import os
import download
#from dataset import one_hot_encoded
#from sklearn.preprocessing import OneHotEncoder
import tensorflow as tf
from random import shuffle
data_path = "D:/Personal details/Internship/"
# Width and height of each image.
img_size = 32
# Number of channels in each image, 3 channels: Red, Green, Blue.
num_channels = 3
# Length of an image when flattened to a 1-dim array.
img_size_flat = img_size * img_size * num_channels
# Number of classes.
num_classes = 10
# Number of files for the training-set.
_num_files_train = 5
# Number of images for each batch-file in the training-set.
_images_per_file = 10000
def _get_file_path(filename=""):
return os.path.join(data_path, "cifar-10-batches-py/", filename)
def _unpickle(filename):
file_path = _get_file_path(filename)
print("Loading data: " + file_path)
with open(file_path, mode='rb') as file:
# In Python 3.X it is important to set the encoding,
# otherwise an exception is raised here.
data = pickle.load(file, encoding='bytes')
return data
def _convert_images(raw):
# Convert the raw images from the data-files to floating-points.
raw_float = np.array(raw, dtype=float) / 255.0
# Reshape the array to 4-dimensions.
images = raw_float.reshape([-1, num_channels, img_size, img_size])
# Reorder the indices of the array.
images = images.transpose([0, 2, 3, 1])
return images
def _load_data(filename):
# Load the pickled data-file.
data = _unpickle(filename)
# Get the raw images.
raw_images = data[b'data']
# Get the class-numbers for each image. Convert to numpy-array.
cls = np.array(data[b'labels'])
# Convert the images.
images = _convert_images(raw_images)
return images, cls
def load_class_names():
# Load the class-names from the pickled file.
raw = _unpickle(filename="batches.meta")[b'label_names']
# Convert from binary strings.
names = [x.decode('utf-8') for x in raw]
return names
def load_training_data():
images = np.zeros(shape=[_num_images_train, img_size, img_size, num_channels], dtype=float)
cls = np.zeros(shape=[_num_images_train], dtype=int)
# Begin-index for the current batch.
begin = 0
# For each data-file.
for i in range(_num_files_train):
# Load the images and class-numbers from the data-file.
images_batch, cls_batch = _load_data(filename="data_batch_" + str(i + 1))
# Number of images in this batch.
num_images = len(images_batch)
# End-index for the current batch.
end = begin + num_images
# Store the images into the array.
images[begin:end, :] = images_batch
# Store the class-numbers into the array.
cls[begin:end] = cls_batch
# The begin-index for the next batch is the current end-index.
begin = end
return images, cls, one_hot_encoded(class_numbers=cls, num_classes=num_classes)
def load_test_data():
images, cls = _load_data(filename="test_batch")
return images, cls, one_hot_encoded(class_numbers=cls, num_classes=num_classes)
########################################################################
def one_hot_encoded(class_numbers, num_classes=None):
if num_classes is None:
num_classes = np.max(class_numbers) + 1
return np.eye(num_classes, dtype=float)[class_numbers]
class_names = load_class_names()
images_train, cls_train, labels_train = load_training_data()
images_test, cls_test, labels_test = load_test_data()
images_train_train = images_train[0:45000]
validation_train = images_train[45000:50000]
labels_train_train = labels_train[0:45000]
validation_labels = labels_train[45000:]
print(len(images_train_train))
print(len(validation_train))
##print(class_names)
##print(len(images_train))
##print(cls_train)
##print(labels_train)
##print(cls_test)
##print(labels_test)
n_classes = len(class_names)
batch_size = 128
x = tf.placeholder(tf.float32, shape=[None, 32, 32, 3], name='x')
y = tf.placeholder(tf.float32, shape=[None, n_classes], name='y_true')
def conv2d(x,W):
return tf.nn.conv2d(x, W, strides=[1,1,1,1], padding='SAME')
def maxpool2d(x):
return tf.nn.max_pool(x, ksize=[1,2,2,1], strides=[1,2,2,1], padding='SAME')
def convolutional_neural_network(x):
weights = {'W_conv1': tf.Variable(tf.random_normal([3,3,3,64])),
'W_conv2': tf.Variable(tf.random_normal([3,3,64,128])),
'W_conv3': tf.Variable(tf.random_normal([3,3,128,256])),
'W_conv4': tf.Variable(tf.random_normal([3,3,256,256])),
'W_fc1': tf.Variable(tf.random_normal([256,1024])),
'W_fc2': tf.Variable(tf.random_normal([1024,1024])),
'soft_max': tf.Variable(tf.random_normal([1024, n_classes]))}
biases = {'b_conv1': tf.Variable(tf.random_normal([64])),
'b_conv2': tf.Variable(tf.random_normal([128])),
'b_conv3': tf.Variable(tf.random_normal([256])),
'b_conv4': tf.Variable(tf.random_normal([256])),
'b_fc1': tf.Variable(tf.random_normal([1024])),
'b_fc2': tf.Variable(tf.random_normal([1024])),
'soft_max': tf.Variable(tf.random_normal([n_classes]))}
conv1 = tf.nn.relu(conv2d(x, weights['W_conv1']) + biases['b_conv1'])
conv1 = maxpool2d(conv1)
conv2 = tf.nn.relu(conv2d(conv1, weights['W_conv2']) + biases['b_conv2'])
conv2 = maxpool2d(conv2)
conv3 = tf.nn.relu(conv2d(conv2, weights['W_conv3']) + biases['b_conv3'])
conv4 = tf.nn.relu(conv2d(conv3, weights['W_conv4']) + biases['b_conv4'])
conv4 = maxpool2d(conv4)
fc1 = tf.reshape(conv4,[256,-1])
fc1 = tf.nn.relu(tf.matmul(fc1, weights['W_fc1']) + biases['b_fc1'])
fc2 = tf.nn.relu(tf.matmul(fc1, weights['W_fc2'] + biases['b_fc2']))
soft_max = tf.matmul(fc2, weights['soft_max']) + biases['soft_max']
return soft_max
def train_neural_network(x):
prediction = convolutional_neural_network(x)
cost = tf.reduce_mean( tf.nn.softmax_cross_entropy_with_logits(logits = prediction,labels = y) )
optimizer = tf.train.AdamOptimizer().minimize(cost)
hm_epochs = 3
with tf.Session() as sess:
sess.run(tf.initialize_all_variables())
for epoch in range(hm_epochs):
epoch_loss = 0
i = 0
while i < len(images_train_train):
start = i
end = i+batch_size
batch_x = np.array(images_train_train[start:end])
batch_y = np.array(labels_train_train[start:end])
_, c = sess.run([optimizer, cost], feed_dict={x: batch_x, y: batch_y})
epoch_loss += c
print('Epoch', epoch, 'completed out of',hm_epochs,'loss:',epoch_loss)
correct = tf.equal(tf.argmax(prediction, 1), tf.argmax(y, 1))
accuracy = tf.reduce_mean(tf.cast(correct, 'float'))
print('Accuracy:',accuracy.eval({x:validation_train, y:validation_labels}))
train_neural_network(x)
Ans this is the error i have been getting.
WARNING:tensorflow:From D:/Personal details/Internship/cifar-10v1.0.py:310: softmax_cross_entropy_with_logits (from tensorflow.python.ops.nn_ops) is deprecated and will be removed in a future version.
Instructions for updating:
Future major versions of TensorFlow will allow gradients to flow
into the labels input on backprop by default.
See #{tf.nn.softmax_cross_entropy_with_logits_v2}.
WARNING:tensorflow:From C:\Python35\lib\site-packages\tensorflow\python\util\tf_should_use.py:118: initialize_all_variables (from tensorflow.python.ops.variables) is deprecated and will be removed after 2017-03-02.
Instructions for updating:
Use `tf.global_variables_initializer` instead.
Traceback (most recent call last):
File "C:\Python35\lib\site-packages\tensorflow\python\client\session.py", line 1322, in _do_call
return fn(*args)
File "C:\Python35\lib\site-packages\tensorflow\python\client\session.py", line 1307, in _run_fn
options, feed_dict, fetch_list, target_list, run_metadata)
File "C:\Python35\lib\site-packages\tensorflow\python\client\session.py", line 1409, in _call_tf_sessionrun
run_metadata)
tensorflow.python.framework.errors_impl.InvalidArgumentError: Matrix size-incompatible: In[0]: [256,2048], In[1]: [256,1024]
[[Node: MatMul = MatMul[T=DT_FLOAT, transpose_a=false, transpose_b=false, _device="/job:localhost/replica:0/task:0/device:CPU:0"](Reshape, Variable_4/read)]]
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "D:/Personal details/Internship/cifar-10v1.0.py", line 344, in <module>
train_neural_network(x)
File "D:/Personal details/Internship/cifar-10v1.0.py", line 327, in train_neural_network
_, c = sess.run([optimizer, cost], feed_dict={x: batch_x, y: batch_y})
File "C:\Python35\lib\site-packages\tensorflow\python\client\session.py", line 900, in run
run_metadata_ptr)
File "C:\Python35\lib\site-packages\tensorflow\python\client\session.py", line 1135, in _run
feed_dict_tensor, options, run_metadata)
File "C:\Python35\lib\site-packages\tensorflow\python\client\session.py", line 1316, in _do_run
run_metadata)
File "C:\Python35\lib\site-packages\tensorflow\python\client\session.py", line 1335, in _do_call
raise type(e)(node_def, op, message)
tensorflow.python.framework.errors_impl.InvalidArgumentError: Matrix size-incompatible: In[0]: [256,2048], In[1]: [256,1024]
[[Node: MatMul = MatMul[T=DT_FLOAT, transpose_a=false, transpose_b=false, _device="/job:localhost/replica:0/task:0/device:CPU:0"](Reshape, Variable_4/read)]]
Caused by op 'MatMul', defined at:
File "<string>", line 1, in <module>
File "C:\Python35\lib\idlelib\run.py", line 130, in main
ret = method(*args, **kwargs)
File "C:\Python35\lib\idlelib\run.py", line 357, in runcode
exec(code, self.locals)
File "D:/Personal details/Internship/cifar-10v1.0.py", line 344, in <module>
train_neural_network(x)
File "D:/Personal details/Internship/cifar-10v1.0.py", line 309, in train_neural_network
prediction = convolutional_neural_network(x)
File "D:/Personal details/Internship/cifar-10v1.0.py", line 300, in convolutional_neural_network
fc1 = tf.nn.relu(tf.matmul(fc1, weights['W_fc1']) + biases['b_fc1'])
File "C:\Python35\lib\site-packages\tensorflow\python\ops\math_ops.py", line 2122, in matmul
a, b, transpose_a=transpose_a, transpose_b=transpose_b, name=name)
File "C:\Python35\lib\site-packages\tensorflow\python\ops\gen_math_ops.py", line 4567, in mat_mul
name=name)
File "C:\Python35\lib\site-packages\tensorflow\python\framework\op_def_library.py", line 787, in _apply_op_helper
op_def=op_def)
File "C:\Python35\lib\site-packages\tensorflow\python\framework\ops.py", line 3392, in create_op
op_def=op_def)
File "C:\Python35\lib\site-packages\tensorflow\python\framework\ops.py", line 1718, in __init__
self._traceback = self._graph._extract_stack() # pylint: disable=protected-access
InvalidArgumentError (see above for traceback): Matrix size-incompatible: In[0]: [256,2048], In[1]: [256,1024]
[[Node: MatMul = MatMul[T=DT_FLOAT, transpose_a=false, transpose_b=false, _device="/job:localhost/replica:0/task:0/device:CPU:0"](Reshape, Variable_4/read)]]
It looks like the problem is in convolutional_neural_network layer() function wherein somehow it is mad at not being able to multiply the same dimension of the matrix. But it is not clear how to solve the issue
Thank you for the help in advance...
After reshaping conv4 at line fc1 = tf.reshape(conv4,[256,-1]), the shape of fc1 is (256, 2048) and the weight matrix W_fc1 has shape (256, 1024). Thus, you get a size incompatible error at the next line fc1 = tf.nn.relu(tf.matmul(fc1, weights['W_fc1']) + biases['b_fc1'])
in the matrix multiplication part. I suggest you to go through the dimensions at every step manually to find errors in future.
I've been working on a simple tensor flow neural network. My input placeholder is
x = tf.placeholder(tf.float32, shape=[None, 52000, 3]).
My weight matrix is initialized to all zeros as
W = tf.Variable(tf.zeros([52000, 10])).
I tried different combinations with and without the 3 for color channels, but I guess I'm just not understanding the dimensionality because I got the error:
Traceback (most recent call last): File
"C:\Users\Everybody\AppData\Local\Programs\Python\Python35\lib\site-packages\tensorflow\python\framework\common_shapes.py",
line 686, in _call_cpp_shape_fn_impl
input_tensors_as_shapes, status) File "C:\Users\Everybody\AppData\Local\Programs\Python\Python35\lib\site-packages\tensorflow\python\framework\errors_impl.py",
line 473, in exit
c_api.TF_GetCode(self.status.status)) tensorflow.python.framework.errors_impl.InvalidArgumentError: Shape
must be rank 2 but is rank 3 for 'MatMul' (op: 'MatMul') with input
shapes: [?,52000,3], [52000,10].
During handling of the above exception, another exception occurred:
Traceback (most recent call last): File "rating.py", line 65, in
y = tf.matmul(x, W) + b # "fake" outputs to train/test File "C:\Users\Everybody\AppData\Local\Programs\Python\Python35\lib\site-packages\tensorflow\python\ops\math_ops.py",
line 1891, in matmul
a, b, transpose_a=transpose_a, transpose_b=transpose_b, name=name) File
"C:\Users\Everybody\AppData\Local\Programs\Python\Python35\lib\site-packages\tensorflow\python\ops\gen_math_ops.py",
line 2436, in _mat_mul
name=name) File "C:\Users\Everybody\AppData\Local\Programs\Python\Python35\lib\site-packages\tensorflow\python\framework\op_def_library.py",
line 787, in _apply_op_helper
op_def=op_def) File "C:\Users\Everybody\AppData\Local\Programs\Python\Python35\lib\site-packages\tensorflow\python\framework\ops.py",
line 2958, in create_op
set_shapes_for_outputs(ret) File "C:\Users\Everybody\AppData\Local\Programs\Python\Python35\lib\site-packages\tensorflow\python\framework\ops.py",
line 2209, in set_shapes_for_outputs
shapes = shape_func(op) File "C:\Users\Everybody\AppData\Local\Programs\Python\Python35\lib\site-packages\tensorflow\python\framework\ops.py",
line 2159, in call_with_requiring
return call_cpp_shape_fn(op, require_shape_fn=True) File "C:\Users\Everybody\AppData\Local\Programs\Python\Python35\lib\site-packages\tensorflow\python\framework\common_shapes.py",
line 627, in call_cpp_shape_fn
require_shape_fn) File "C:\Users\Everybody\AppData\Local\Programs\Python\Python35\lib\site-packages\tensorflow\python\framework\common_shapes.py",
line 691, in _call_cpp_shape_fn_impl
raise ValueError(err.message) ValueError: Shape must be rank 2 but is rank 3 for 'MatMul' (op: 'MatMul') with input shapes: [?,52000,3],
[52000,10].
At first, I thought my next_batch() function was the culprit because I had to make my own due to the fact that I uploaded my images "manually" using scipy.misc.imread(), whose definition reads:
q = 0
def next_batch(batch_size):
x = images[q:q + batch_size]
y = one_hots[q:q + batch_size]
q = (q + batch_size) % len(images)
return x, y
However, after looking through, I don't see what's wrong with this, so I imagine that I'm just confused about dimensionality. It is supposed to be a "flattened" 200x260 color image. It just occurred to me now that maybe I have to flatten the color channels as well? I will place my full code below if curious. I'm a bit new to Tensorflow, so thanks, all. (Yes, it is not a CNN yet, I decided to start simple just to make sure I'm importing my dataset right. And, I know it is tiny, I'm starting my dataset small too.)
############# IMPORT DEPENDENCIES ####################################
import tensorflow as tf
sess = tf.InteractiveSession() #start session
import scipy.misc
import numpy as np
######################################################################
#SET UP DATA #########################################################
images = []
one_hots = []
########### IMAGES ##################################################
#put all the images in a list
for i in range(60):
images.append(scipy.misc.imread('./shoes/%s.jpg' % str(i+1)))
print("One image appended...\n")
#normalize them, "divide" by 255
for image in images:
print("One image normalized...\n")
for i in range(260):
for j in range(200):
for c in range(3):
image[i][j][c]/=255
for image in images:
tf.reshape(image, [52000, 3])
########################################################################
################# ONE-HOT VECTORS ######################################
f = open('rateVectors.txt')
lines = f.readlines()
for i in range(0, 600, 10):
fillerlist = []
for j in range(10):
fillerlist.append(float(lines[i+j][:-1]))
one_hots.append(fillerlist)
print("One one-hot vector added...\n")
########################################################################3
#set placeholders and such for input, output, weights, biases
x = tf.placeholder(tf.float32, shape=[None, 52000, 3])
y_ = tf.placeholder(tf.float32, shape=[None, 10])
W = tf.Variable(tf.zeros([52000, 10])) # These are our weights and biases
b = tf.Variable(tf.zeros([10])) # initialized as zeroes.
#########################################################################
sess.run(tf.global_variables_initializer()) #initialize variables in the session
y = tf.matmul(x, W) + b # "fake" outputs to train/test
##################### DEFINING OUR MODEL ####################################
#our loss function
cross_entropy = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(y, y_))
#defining our training as gradient descent
train_step = tf.train.GradientDescentOptimizer(0.5).minimize(cross_entropy)
###################### TRAINING #############################################
#################### OUR CUSTOM BATCH FUNCTION ##############################
q = 0
def next_batch(batch_size):
x = images[q:q + batch_size]
y = one_hots[q:q + batch_size]
q = (q + batch_size) % len(images)
return x, y
#train
for i in range(6):
batch = next_batch(10)
train_step.run(feed_dict={x: batch[0], y_: batch[1]})
print("Batch Number: " + i + "\n")
print("Done training...\n")
################ RESULTS #################################################
#calculating accuracy
correct_prediction = tf.equal(tf.argmax(y,1), tf.argmax(y_,1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
#print accuracy
print(accuracy.eval(feed_dict={x: images, y_: one_hots}))
Your placeholder should have the dimension [None, 200, 260, 3] where None is the batch size, 200, 260 is the image size, and 3 is the channels.
Your weights should be [filter_height, filter_width, num_channels, num_filters]
Your bias should be [num_filters]
And the dimensions for the labels should be [None, num_classes] where None is the batch size, and num_classes is the number of classes that your images have.
These are just to make sure that math works.
I took these codes from here
I'm getting an incompatible shape error when trying trying to add a CNN to a ready siamese code that I got from github : here is the link :
https://github.com/ywpkwon/siamese_tf_mnist
here is the code for running the session:
""" Siamese implementation using Tensorflow with MNIST example.
This siamese network embeds a 28x28 image (a point in 784D)
into a point in 2D.
By Youngwook Paul Kwon (young at berkeley.edu)
"""
from __future__ import absolute_import
from __future__ import division
from __future__ import print_function
#import system things
from tensorflow.examples.tutorials.mnist import input_data # for data
import tensorflow as tf
import numpy as np
import os
#import helpers
import inference
import visualize
# prepare data and tf.session
mnist = input_data.read_data_sets('MNIST_data', one_hot=False)
sess = tf.InteractiveSession()
# setup siamese network
siamese = inference.siamese();
train_step = tf.train.GradientDescentOptimizer(0.01).minimize(siamese.loss)
saver = tf.train.Saver()
tf.initialize_all_variables().run()
# start training
if new:
for step in range(1000):
batch_x1, batch_y1 = mnist.train.next_batch(128)
batch_x2, batch_y2 = mnist.train.next_batch(128)
batch_y = (batch_y1 == batch_y2).astype('float')
_, loss_v = sess.run([train_step, siamese.loss], feed_dict={
siamese.x1: batch_x1,
siamese.x2: batch_x2,
siamese.y_: batch_y})
if step % 10 == 0:
print ('step %d: loss' % (step))
print (loss_v)
here is the code for creating the Siamese model.
import tensorflow as tf
class siamese:
# Create model
def __init__(self):
self.x1 = tf.placeholder(tf.float32, [None, 784])
self.x2 = tf.placeholder(tf.float32, [None, 784])
with tf.variable_scope("siamese") as scope:
self.o1 = self.network(self.x1)
scope.reuse_variables()
self.o2 = self.network(self.x2)
# Create loss
self.y_ = tf.placeholder(tf.float32, [None])
self.loss = self.loss_with_step()
def network(self, x):
weights = []
fc1 = self.fc_layer(x, 1024, "fc1" , [5, 5, 1, 32])
return fc1
def fc_layer(self, bottom, n_weight, name,kernel_shape ): #[5, 5, 1, 32]
assert len(bottom.get_shape()) == 2
#n_prev_weight = bottom.get_shape()[1]
initer = tf.truncated_normal_initializer(stddev=0.01)
weights_for_convolution = tf.get_variable(name+"weights_for_convolution", kernel_shape,
initializer=tf.random_normal_initializer())
bias_shape = kernel_shape[-1]
biases_for_convolution = tf.get_variable(name+"biases_for_convolution", [bias_shape],
initializer=tf.constant_initializer(0.1))
biases_for_connected_layer = tf.get_variable(name+"biases_for_connected_layer", [1024],
initializer=tf.constant_initializer(0.1))
weights_for_connected_layer = tf.get_variable(name+"weights_for_connected_layer", [7*7*64,1024],
initializer=tf.random_normal_initializer())
W = tf.get_variable(name+'W', dtype=tf.float32, shape=[1024,2], initializer=initer)
b = tf.get_variable(name+'b', dtype=tf.float32, initializer=tf.constant(0.01, shape=[2], dtype=tf.float32))
#weights_for_readout_layer = tf.get_variable("weights_for_readout_layer", [1024,2],
#initializer=tf.random_normal_initializer())
#biases_for_readout_layer = tf.get_variable("biases_for_readout_layer", [2],
#initializer=tf.constant_initializer(0.1))
bottom1 = tf.reshape(bottom,[-1,28,28,1]) ##
c2 = tf.nn.conv2d(bottom1, weights_for_convolution, strides=[1, 1, 1, 1], padding='SAME')
conv = tf.nn.bias_add(c2, biases_for_convolution)
relu = tf.nn.relu(conv)
out = tf.nn.max_pool(relu, ksize=[1, 2, 2, 1],
strides=[1, 2, 2, 1], padding='SAME')
#print tf.shape(out)
h_out_flat = tf.reshape(out ,[-1,7*7*64])
h_fc1 = tf.nn.relu(tf.matmul(h_out_flat, weights_for_connected_layer) + biases_for_connected_layer)
#compute model output
final_output = tf.matmul(h_fc1,W) + b
#fc = tf.nn.bias_add(tf.matmul(bottom, W), b)
return final_output
def loss_with_spring(self):
margin = 5.0
labels_t = self.y_
labels_f = tf.subtract(1.0, self.y_, name="1-yi") # labels_ = !labels;
eucd2 = tf.pow(tf.subtract(self.o1, self.o2), 2)
print tf.shape(eucd2)
eucd2 = tf.reduce_sum(eucd2, 1)
eucd = tf.sqrt(eucd2+1e-6, name="eucd")
C = tf.constant(margin, name="C")
# yi*||CNN(p1i)-CNN(p2i)||^2 + (1-yi)*max(0, C-||CNN(p1i)-CNN(p2i)||^2)
pos = tf.multiply(labels_t, eucd2, name="yi_x_eucd2")
# neg = tf.multiply(labels_f, tf.subtract(0.0,eucd2), name="yi_x_eucd2")
# neg = tf.multiply(labels_f, tf.maximum(0.0, tf.subtract(C,eucd2)), name="Nyi_x_C-eucd_xx_2")
neg = tf.multiply(labels_f, tf.pow(tf.maximum(tf.subtract(C, eucd), 0), 2), name="Nyi_x_C-eucd_xx_2")
losses = tf.add(pos, neg, name="losses")
loss = tf.reduce_mean(losses, name="loss")
return loss
def loss_with_step(self):
margin = 5.0
labels_t = self.y_ #128
labels_f = tf.subtract(1.0, self.y_, name="1-yi") # labels_ = !labels;
eucd2 = tf.pow(tf.subtract(self.o1, self.o2), 2)
eucd2 = tf.reduce_sum(eucd2, 1)
eucd = tf.sqrt(eucd2+1e-6, name="eucd")
C = tf.constant(margin, name="C")
pos = tf.multiply(labels_t, eucd, name="y_x_eucd")
neg = tf.multiply(labels_f, tf.maximum(0.0, tf.subtract(C, eucd)), name="Ny_C-eucd")
losses = tf.add(pos, neg, name="losses")
loss = tf.reduce_mean(losses, name="loss")
return loss
Actually as the batch size is 128 label-t is 128,
the problem here is that the euclidean distance in the loss_with_step function,
as well as in the loss_with_spring function is of size 256 and not 128 I don't really know why!
here is the error I get.
Traceback (most recent call last):
File "run1.py", line 56, in <module>
siamese.y_: batch_y})
File "/home/sudonuma/anaconda2/envs/tensorflow/lib/python2.7/site- packages/tensorflow/python/client/session.py", line 789, in run
run_metadata_ptr)
File "/home/sudonuma/anaconda2/envs/tensorflow/lib/python2.7/site- packages/tensorflow/python/client/session.py", line 997, in _run
feed_dict_string, options, run_metadata)
File "/home/sudonuma/anaconda2/envs/tensorflow/lib/python2.7/site- packages/tensorflow/python/client/session.py", line 1132, in _do_run
target_list, options, run_metadata)
File "/home/sudonuma/anaconda2/envs/tensorflow/lib/python2.7/site- packages/tensorflow/python/client/session.py", line 1152, in _do_call
raise type(e)(node_def, op, message)
tensorflow.python.framework.errors_impl.InvalidArgumentError: Incompatible shapes: [128] vs. [256]
[[Node: y_x_eucd = Mul[T=DT_FLOAT, _device="/job:localhost/ replica:0/task:0/cpu:0"](_arg_Placeholder_2_0_2, eucd)]]
Caused by op u'y_x_eucd', defined at:
File "run1.py", line 28, in <module>
siamese = inference1.siamese();
File "/home/sudonuma/Documents/siamese for mnist/siamese_tf_mnist-master /inference1.py", line 18, in __init__
self.loss = self.loss_with_step()
File "/home/sudonuma/Documents/siamese for mnist/siamese_tf_mnist-master /inference1.py", line 110, in loss_with_step
pos = tf.multiply(labels_t, eucd, name="y_x_eucd")
File "/home/sudonuma/anaconda2/envs/tensorflow/lib/python2.7/site- packages/tensorflow/python/ops/math_ops.py", line 286, in multiply
return gen_math_ops._mul(x, y, name)
File "/home/sudonuma/anaconda2/envs/tensorflow/lib/python2.7/site- packages/tensorflow/python/ops/gen_math_ops.py", line 1377, in _mul
result = _op_def_lib.apply_op("Mul", x=x, y=y, name=name)
File "/home/sudonuma/anaconda2/envs/tensorflow/lib/python2.7/site- packages/tensorflow/python/framework/op_def_library.py", line 767, in apply
_op
op_def=op_def)
File "/home/sudonuma/anaconda2/envs/tensorflow/lib/python2.7/site- packages/tensorflow/python/framework/ops.py", line 2506, in create_op
original_op=self._default_original_op, op_def=op_def)
File "/home/sudonuma/anaconda2/envs/tensorflow/lib/python2.7/site- packages/tensorflow/python/framework/ops.py", line 1269, in __init__
self._traceback = _extract_stack()
InvalidArgumentError (see above for traceback): Incompatible shapes: [128] vs. [256]
[[Node: y_x_eucd = Mul[T=DT_FLOAT, _device="/job:localhost /replica:0/task:0/cpu:0"](_arg_Placeholder_2_0_2, eucd)]]
can anyone help?
Looks like your reshaping after the convolution is wrong. The output of the convolution layer would be 14x14x32 for a 28x28x1 input passed through conv(stride=1)-maxpool(stride 2). So you need to change the flatten layer to :
h_out_flat = tf.reshape(out ,[-1,14*14*32])
and also the weights_for_connected_layer appropriately.
In the beginning, I need to say that I am using TF v 1.1.
The code:
import random
import tensorflow as tf
xData = []
yData = []
for _ in range(10000):
x = random.random()
xData.append(x)
y = 2 * x
yData.append(y)
xc = tf.contrib.layers.real_valued_column("")
estimator = tf.contrib.learn.DynamicRnnEstimator(problem_type = constants.ProblemType.LINEAR_REGRESSION,
prediction_type = PredictionType.SINGLE_VALUE,
sequence_feature_columns = [xc],
context_feature_columns = None,
num_units = 5,
cell_type = 'lstm',
optimizer = 'SGD',
learning_rate = '0.1')
def get_train_inputs():
x = tf.constant(xData)
y = tf.constant(yData)
return x, y
estimator.fit(input_fn=get_train_inputs, steps=TRAINING_STEPS)
I got:
AttributeError: 'Tensor' object has no attribute 'get'
here.
The same code works for LinearRegressor instead of DynamicRnnEstimator.
WARNING:tensorflow:From
E:\Python35\lib\site-packages\tensorflow\contrib\learn\python\learn\estimators\dynamic_rnn_estimator.py:724:
regression_target (from
tensorflow.contrib.layers.python.layers.target_column) is deprecated
and will be removed after 2016-11-12. Instructions for updating: This
file will be removed after the deprecation date.Please switch to
third_party/tensorflow/contrib/learn/python/learn/estimators/head.py
WARNING:tensorflow:Using temporary folder as model directory:
C:\Users\pavel\AppData\Local\Temp\tmpzy68t_iw
Blockquote
Traceback (most recent
call last): File
"C:/Users/pavel/PycharmProjects/rnnEstimator/main.py", line 31, in
estimator.fit(input_fn=get_train_inputs, steps=1000)
File
"E:\Python35\lib\site-packages\tensorflow\python\util\deprecation.py",
line 281, in new_func return func(*args, **kwargs)
File
"E:\Python35\lib\site-packages\tensorflow\contrib\learn\python\learn\estimators\estimator.py",
line 430, in fit loss = self._train_model(input_fn=input_fn,
hooks=hooks)
File
"E:\Python35\lib\site-packages\tensorflow\contrib\learn\python\learn\estimators\estimator.py",
line 927, in _train_model model_fn_ops = self._get_train_ops(features,
labels)
File
"E:\Python35\lib\site-packages\tensorflow\contrib\learn\python\learn\estimators\estimator.py",
line 1132, in _get_train_ops return self._call_model_fn(features,
labels, model_fn_lib.ModeKeys.TRAIN)
File
"E:\Python35\lib\site-packages\tensorflow\contrib\learn\python\learn\estimators\estimator.py",
line 1103, in _call_model_fn model_fn_results =
self._model_fn(features, labels, **kwargs)
File
"E:\Python35\lib\site-packages\tensorflow\contrib\learn\python\learn\estimators\dynamic_rnn_estimator.py",
line 516, in _dynamic_rnn_model_fn sequence_length =
features.get(sequence_length_key) AttributeError: 'Tensor' object has
no attribute 'get'
Update:
Issue in TF repo's
BATCH_SIZE = 32
SEQUENCE_LENGTH = 16
xc = tf.contrib.layers.real_valued_column("")
estimator = tf.contrib.learn.DynamicRnnEstimator(problem_type = constants.ProblemType.LINEAR_REGRESSION,
prediction_type = PredictionType.SINGLE_VALUE,
sequence_feature_columns = [xc],
context_feature_columns = None,
num_units = 5,
cell_type = 'lstm',
optimizer = 'SGD',
learning_rate = 0.1)
def get_train_inputs():
x = tf.random_uniform([BATCH_SIZE, SEQUENCE_LENGTH])
y = tf.reduce_mean(x, axis=1)
x = tf.expand_dims(x, axis=2)
return {"": x}, y
estimator.fit(input_fn=get_train_inputs, steps=1000)
I am trying to implement a recurrent state tensor using tf.scan. The code I have at the moment is this:
import tensorflow as tf
import math
import numpy as np
INPUTS = 10
HIDDEN_1 = 20
BATCH_SIZE = 3
def iterate_state(prev_state_tuple, input):
with tf.name_scope('h1'):
weights = tf.get_variable('W', shape=[INPUTS, HIDDEN_1], initializer=tf.truncated_normal_initializer(stddev=1.0 / math.sqrt(float(INPUTS))))
biases = tf.get_variable('bias', shape=[HIDDEN_1], initializer=tf.constant_initializer(0.0))
matmuladd = tf.matmul(inputs, weights) + biases
unpacked_state, unpacked_out = tf.split(0,2,prev_state_tuple)
prev_state = unpacked_state
state = 0.9* prev_state + 0.1*matmuladd
output = tf.nn.relu(state)
return tf.concat(0,[state, output])
def data_iter():
while True:
idxs = np.random.rand(BATCH_SIZE, INPUTS)
yield idxs
with tf.Graph().as_default():
inputs = tf.placeholder(tf.float32, shape=(BATCH_SIZE, INPUTS))
with tf.variable_scope('states'):
initial_state = tf.zeros([HIDDEN_1],
name='initial_state')
initial_out = tf.zeros([HIDDEN_1],
name='initial_out')
concat_tensor = tf.concat(0,[initial_state, initial_out])
states, output = tf.scan(iterate_state, inputs,
initializer=concat_tensor, name='states')
sess = tf.Session()
# Run the Op to initialize the variables.
sess.run(tf.initialize_all_variables())
iter_ = data_iter()
for i in xrange(0, 2):
print ("iteration: ",i)
input_data = iter_.next()
out,st = sess.run([output,states], feed_dict={ inputs: input_data})
However, I get this error when running this:
Traceback (most recent call last):
File "cycles_in_graphs_with_scan.py", line 37, in <module>
initializer=concat_tensor, name='states')
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/framework/ops.py", line 442, in __iter__
raise TypeError("'Tensor' object is not iterable.")
TypeError: 'Tensor' object is not iterable.
(tensorflow)charlesq#Leviathan ~/projects/stuff $ python cycles_in_graphs_with_scan.py
Traceback (most recent call last):
File "cycles_in_graphs_with_scan.py", line 37, in <module>
initializer=concat_tensor, name='states')
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/framework/ops.py", line 442, in __iter__
raise TypeError("'Tensor' object is not iterable.")
TypeError: 'Tensor' object is not iterable.
I've already tried with pack/unpack and concat/split but I get this same error.
Any ideas how to solve this problem?
You're getting an error because tf.scan() returns a single tf.Tensor, so the line:
states, output = tf.scan(...)
...cannot destructure (unpack) the tensor returned from tf.scan() into two values (states and outputs). Effectively, the code is trying to treat the result of tf.scan() as a list of length 2, and assign the first element to states and the second element to output, but—unlike a Python list or tuple—tf.Tensor does not support this.
Instead you need to extract the values from the result of tf.scan() manually. For example, using tf.split():
scan_result = tf.scan(...)
# Assumes values are packed together along `split_dim`.
states, output = tf.split(split_dim, 2, scan_result)
Alternatively, you could use tf.slice() or tf.unpack() to extract the relevant states and output values.