What is the difference between SparseTensor and SparseTensorValue? Is there anything I should keep in mind if I want to build the sparse tensor based on fed indices and values? I could only find a few toy examples.
It depends on where you define your Sparse Tensor.
If you would like to define the tensor outside the graph, e.g. define the sparse tensor for later data feed, use SparseTensorValue. In contrast, if the sparse tensor is defined in graph, use SparseTensor
Sample code for tf.SparseTensorValue:
x_sp = tf.sparse_placeholder(dtype=tf.float32)
W = tf.Variable(tf.random_normal([6, 6]))
y = tf.sparse_tensor_dense_matmul(sp_a=x_sp, b=W)
init = tf.global_variables_initializer()
gpu_options = tf.GPUOptions(per_process_gpu_memory_fraction=0.2)
sess = tf.Session(config=tf.ConfigProto(gpu_options=gpu_options))
sess.run(init)
stv = tf.SparseTensorValue(indices=[[0, 0], [1, 2]], values=[1.1, 1.2],
dense_shape=[2,6])
result = sess.run(y,feed_dict={x_sp:stv})
print(result)
Sample code for tf.SparseTensor:
indices_i = tf.placeholder(dtype=tf.int64, shape=[2, 2])
values_i = tf.placeholder(dtype=tf.float32, shape=[2])
dense_shape_i = tf.placeholder(dtype=tf.int64, shape=[2])
st = tf.SparseTensor(indices=indices_i, values=values_i, dense_shape=dense_shape_i)
W = tf.Variable(tf.random_normal([6, 6]))
y = tf.sparse_tensor_dense_matmul(sp_a=st, b=W)
init = tf.global_variables_initializer()
gpu_options = tf.GPUOptions(per_process_gpu_memory_fraction=0.2)
sess = tf.Session(config=tf.ConfigProto(gpu_options=gpu_options))
sess.run(init)
result = sess.run(y,feed_dict={indices_i:[[0, 0], [1, 2]], values_i:[1.1, 1.2], dense_shape_i:[2,6]})
print(result)
Hope this help~
Related
I want to modification the value about variable 'weight1' in tf.variable_scope.
I try to modification the value by other function, but it not work follow me.
def inference(q, reuse=False):
with tf.variable_scope('layer1', reuse = reuse):
x = tf.get_variable('weight1', [1, 3], initializer = tf.truncated_normal_initializer(stddev = 0.1))
y = tf.get_variable('weight2', [3, 1], initializer = tf.constant_initializer([[1],[2],[3]]))
return tf.matmul(x, y)
def update_process(reuse=True):
with tf.variable_scope('layer1', reuse = reuse):
x = tf.get_variable('weight1',[1, 3])
update=tf.assign(x, x-1)
with tf.Session() as sess:
sess.run(init)
print(sess.run(x))
init = tf.global_variables_initializer()
z = inference(1)
with tf.Session() as sess:
sess.run(init)
for i in range(5):
update_process(reuse = True)
print(sess.run(z))
print('\n')
I want to this code output different list about sess.run(z), but the value is always same.
You need to run sess.run(update) in update_process in the same session that the inference part of the graph runs:
import tensorflow as tf
def inference(q, reuse=False):
with tf.variable_scope('layer1', reuse = reuse):
x = tf.get_variable('weight1', [1, 3], initializer = tf.truncated_normal_initializer(stddev = 0.1))
y = tf.get_variable('weight2', [3, 1], initializer = tf.constant_initializer([[1],[2],[3]]))
return tf.matmul(x, y)
def update_process(reuse=True):
with tf.variable_scope('layer1', reuse = reuse):
x = tf.get_variable('weight1',[1, 3])
update=tf.assign(x, x-1)
print(sess.run(update))
z = inference(1)
init = tf.global_variables_initializer()
with tf.Session() as sess:
sess.run(init)
for i in range(5):
update_process(reuse = True)
print(sess.run(z))
print('\n')
I am new to Tensorflow Dataset API, and I could not fully understand the simplicity of its design, so I need some help.
Here is a simple example
import tensorflow as tf
x = tf.placeholder(tf.int32, shape=[])
y = tf.square(x)
with tf.Session() as sess:
print(sess.run(y, {x: 2}))
# result is 4, simple
If I have an integer array arr_x=[2, 3, 5, 8, 10], how can I use Dateset API to iterate the array?
I am trying
p = tf.placeholder(tf.int32, shape=[None])
d = tf.data.Dataset.from_tensor_slices(p)
d = d.map(lambda x: x)
iter = d.make_initializable_iterator()
next_element = iter.get_next()
with tf.Session() as sess:
sess.run(iter.initializer, feed_dict={p: [2, 3, 4]})
while True:
try:
print sess.run(y, next_element)
except tf.errors.OutOfRangeError:
break
But no luck, any idea?
What about:
arr_x = np.array([2, 3, 5, 8, 10])
arr_y = np.array([[0,1],[1,0],[1,0],[0,1],[1,0]])
dataset = tf.data.Dataset.from_tensor_slices((arr_x, arr_y))
iterator = dataset.make_one_shot_iterator()
next_element = iterator.get_next()
sess = tf.Session()
while True:
try:
print(sess.run(next_element))
except tf.errors.OutOfRangeError:
break
Based on this post, I tried to create another model, where I'm adding both categorical and continous variables.
Please find the code below:
from __future__ import print_function
import pandas as pd;
import tensorflow as tf
import numpy as np
from sklearn.preprocessing import LabelEncoder
if __name__ == '__main__':
# 1 categorical input feature and a binary output
df = pd.DataFrame({'cat2': np.array(['o', 'm', 'm', 'c', 'c', 'c', 'o', 'm', 'm', 'm']),
'num1': np.random.rand(10),
'label': np.array([0, 0, 1, 1, 0, 0, 1, 0, 1, 1])})
encoder = LabelEncoder()
encoder.fit(df.cat2.values)
X1 = encoder.transform(df.cat2.values).reshape(-1,1)
X2 = np.array(df.num1.values).reshape(-1,1)
# X = np.concatenate((X1,X2), axis=1)
Y = np.zeros((len(df), 2))
Y[np.arange(len(df)), df.label.values] = 1
# Neural net parameters
training_epochs = 5
learning_rate = 1e-3
cardinality = len(np.unique(X))
embedding_size = 2
input_X_size = 1
n_labels = len(np.unique(Y))
n_hidden = 10
# Placeholders for input, output
cat2 = tf.placeholder(tf.int32, [None], name='cat2')
x = tf.placeholder(tf.float32, [None, 1], name="input_x")
y = tf.placeholder(tf.float32, [None, 2], name="input_y")
embed_matrix = tf.Variable(
tf.random_uniform([cardinality, embedding_size], -1.0, 1.0),
name="embed_matrix"
)
embed = tf.nn.embedding_lookup(embed_matrix, cat2)
inputs_with_embed = tf.concat([x, embedding_aggregated], axis=2, name="inputs_with_embed")
# Neural network weights
h = tf.get_variable(name='h2', shape=[inputs_with_embed, n_hidden],
initializer=tf.contrib.layers.xavier_initializer())
W_out = tf.get_variable(name='out_w', shape=[n_hidden, n_labels],
initializer=tf.contrib.layers.xavier_initializer())
# Neural network operations
#embedded_chars = tf.nn.embedding_lookup(embeddings, x)
layer_1 = tf.matmul(inputs_with_embed,h)
layer_1 = tf.nn.relu(layer_1)
out_layer = tf.matmul(layer_1, W_out)
# Define loss and optimizer
cost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(logits=out_layer, labels=y))
optimizer = tf.train.AdamOptimizer(learning_rate=learning_rate).minimize(cost)
# Initializing the variables
init = tf.global_variables_initializer()
# Launch the graph
with tf.Session() as sess:
sess.run(init)
for epoch in range(training_epochs):
avg_cost = 0.
# Run optimization op (backprop) and cost op (to get loss value)
_, c = sess.run([optimizer, cost],
feed_dict={x: X2,cat2:X1, y: Y})
print("Optimization Finished!")
But I'm getting the following error. It seems I'm not concatenating the continous variable and embedding properly. But I'm not understanding how to fix it.
Please if someone can please guide me.
ValueError: Shape must be at least rank 3 but is rank 2 for 'inputs_with_embed_2' (op: 'ConcatV2') with input shapes: [?,1], [?,2], [] and with computed input tensors: input[2] = <2>.
Thanks!
If by embedding_agregated you mean embed (probably typo)
The error is that there is no axis=2 in your case , it should be axis=1
inputs_with_embed = tf.concat([x, embed], axis=1, name="inputs_with_embed")
embed has a shape [None, embedding_dimension] and x has a shape [None, 1]
They are both 2D tensors, so you have access to axis=0 or axis=1 (indexing at 0 not 1), therefore to have your input_with_embed of shape [None, embedding_dimension+1] you need to concat on the axis=1
If I have a placeholder:
placeholder = tf.placeholder(dtype=np.float32, shape=[1, 2])
And then I create an op which assigns the placeholder to a new variable y:
y = tf.Variable([[0, 0]], dtype=tf.float32)
y_op = tf.assign(y, placeholder)
Then specify a value which I will feed into this placeholder:
x = tf.Variable([[5, 5]], dtype=np.float32)
And finally run the operation:
sess = tf.Session()
sess.run(tf.global_variables_initializer())
sess.run(y_op, feed_dict={placeholder: x})
I get the following error:
ValueError: setting an array element with a sequence.
Why is this? From what I can see, the shapes of placeholder, y, and x, are all [1, 2].
You are trying to feed a graph variable using the feed dict. Feed dict and placeholders are for feeding external values into the graph. This code works:
placeholder = tf.placeholder(dtype=np.float32, shape=[1, 2])
y = tf.Variable([[0, 0]], dtype=tf.float32)
y_op = tf.assign(y, placeholder)
value = np.array([[5,5]])
sess = tf.Session()
sess.run(tf.global_variables_initializer())
r = sess.run(y_op, feed_dict={placeholder: value})
But if the value you want to use in the graph is already a tf.Variable, there is no reason to use feed dict at all. This also works:
x = tf.Variable([[5, 5]], dtype=tf.float32)
y = tf.Variable([[0, 0]], dtype=tf.float32)
y_op = tf.assign(y, x)
sess = tf.Session()
sess.run(tf.global_variables_initializer())
r = sess.run(y_op)
import tensorflow as tf
def activation(e, f, g):
return e + f + g
with tf.Graph().as_default():
a = tf.constant([5, 4, 5], name='a')
b = tf.constant([0, 1, 2], name='b')
c = tf.constant([5, 0, 5], name='c')
res = activation(a, b, c)
init = tf.initialize_all_variables()
with tf.Session() as sess:
# Start running operations on the Graph.
merged = tf.merge_all_summaries()
sess.run(init)
hi = sess.run(res)
print hi
writer = tf.train.SummaryWriter("/tmp/basic", sess.graph_def)
output error:
Value Error: Fetch argument <tf.Tensor 'add_1:0' shape=(3,) dtype=int32> of
<tf.Tensor 'add_1:0' shape=(3,) dtype=int32> cannot be interpreted as a Tensor.
(Tensor Tensor("add_1:0", shape=(3,), dtype=int32) is not an element of this graph.)
The error is actually giving you a tip of why it's failing. When you started the session, you are actually using a different graph than the one referenced by res. The easiest solution is to simply move everything inside with tf.Graph().as_default():.
import tensorflow as tf
def activation(e, f, g):
return e + f + g
with tf.Graph().as_default():
a = tf.constant([5, 4, 5], name='a')
b = tf.constant([0, 1, 2], name='b')
c = tf.constant([5, 0, 5], name='c')
res = activation(a, b, c)
init = tf.initialize_all_variables()
with tf.Session() as sess:
# Start running operations on the Graph.
merged = tf.merge_all_summaries()
sess.run(init)
hi = sess.run(res)
print hi
writer = tf.train.SummaryWriter("/tmp/basic", sess.graph_def)
Alternatively you can also just remove the line with tf.Graph().as_default(): and then it will also worked as expected.
Another option is to initialize graph variable first:
graph = tf.Graph()
with graph.as_default():
and than pass it to your session:
with tf.Session(graph=graph) as session: