how to make a input tensor trainable
up vote
1
down vote
favorite
The following is the code trying to use the input image as a training variable during the optimization. It starts with a keras model and convert that to a tensorflow model. This tensorflow model take a tensor as input and try to optimize the cost function using the input tensor as a trainable variable.
The error is:
NotImplementedError: ('Trying to update a Tensor ', )
The reason is that the input tensor is not a variable. The question is how to make the input image trainable or cast a tensor to a tf.variable. Help is appreciated:
import tensorflow as tf
from keras.models import Sequential, load_model, Model
from keras import backend as K
from keras.layers.core import Dense, Dropout, Activation
import os
from tensorflow.python.framework import graph_util
from tensorflow.python.framework import graph_io
n_classes = 10
model = Sequential()
model.add(Dense(10, input_shape=(784,)))
model.add(Activation('relu'))
model.add(Dense(n_classes, name='logits'))
model.add(Activation('softmax'))
model.compile(loss='categorical_crossentropy', metrics=['accuracy'], optimizer='adam')
# Write the graph in binary .pb file
outdir = "model4_tf"
try:
os.mkdir(outdir )
except:
pass
prefix = "simple_nn"
name = 'output_graph.pb'
# Alias the outputs in the model - this sometimes makes them easier to access in TF
pred =
pred_node_names =
for i, o in enumerate(model.outputs):
pred_node_names.append(prefix+'_'+str(i))
pred.append(tf.identity(o,
name=pred_node_names[i]))
print('Output nodes names are: ', pred_node_names)
sess = K.get_session()
constant_graph = graph_util.convert_variables_to_constants(sess,
sess.graph.as_graph_def(), pred_node_names)
graph_io.write_graph(constant_graph, outdir, name, as_text=False)
tf.reset_default_graph()
def load_graph(model_name):
#graph = tf.Graph()
graph = tf.get_default_graph()
graph_def = tf.GraphDef()
with open(model_name, "rb") as f:
graph_def.ParseFromString(f.read())
with graph.as_default():
tf.import_graph_def(graph_def)
return graph
my_graph = load_graph(model_name=os.path.join(outdir, name))
# In[15]:
input_op = my_graph.get_operation_by_name("import/dense_1_input")
output_op = my_graph.get_operation_by_name("import/simple_nn_0")
logit_op = my_graph.get_operation_by_name("import/logits/BiasAdd")
x_hat = input_op.outputs[0] # input tensor
labels = output_op.outputs[0] # label tensor
logits = logit_op.outputs[0] # logits tensor
learning_rate = tf.placeholder(tf.float32, ())
loss = tf.nn.softmax_cross_entropy_with_logits_v2(logits=logits, labels=[labels])
optim_step = tf.train.GradientDescentOptimizer(learning_rate).minimize(loss, var_list=[x_hat])
python-3.x tensorflow keras
add a comment |
up vote
1
down vote
favorite
The following is the code trying to use the input image as a training variable during the optimization. It starts with a keras model and convert that to a tensorflow model. This tensorflow model take a tensor as input and try to optimize the cost function using the input tensor as a trainable variable.
The error is:
NotImplementedError: ('Trying to update a Tensor ', )
The reason is that the input tensor is not a variable. The question is how to make the input image trainable or cast a tensor to a tf.variable. Help is appreciated:
import tensorflow as tf
from keras.models import Sequential, load_model, Model
from keras import backend as K
from keras.layers.core import Dense, Dropout, Activation
import os
from tensorflow.python.framework import graph_util
from tensorflow.python.framework import graph_io
n_classes = 10
model = Sequential()
model.add(Dense(10, input_shape=(784,)))
model.add(Activation('relu'))
model.add(Dense(n_classes, name='logits'))
model.add(Activation('softmax'))
model.compile(loss='categorical_crossentropy', metrics=['accuracy'], optimizer='adam')
# Write the graph in binary .pb file
outdir = "model4_tf"
try:
os.mkdir(outdir )
except:
pass
prefix = "simple_nn"
name = 'output_graph.pb'
# Alias the outputs in the model - this sometimes makes them easier to access in TF
pred =
pred_node_names =
for i, o in enumerate(model.outputs):
pred_node_names.append(prefix+'_'+str(i))
pred.append(tf.identity(o,
name=pred_node_names[i]))
print('Output nodes names are: ', pred_node_names)
sess = K.get_session()
constant_graph = graph_util.convert_variables_to_constants(sess,
sess.graph.as_graph_def(), pred_node_names)
graph_io.write_graph(constant_graph, outdir, name, as_text=False)
tf.reset_default_graph()
def load_graph(model_name):
#graph = tf.Graph()
graph = tf.get_default_graph()
graph_def = tf.GraphDef()
with open(model_name, "rb") as f:
graph_def.ParseFromString(f.read())
with graph.as_default():
tf.import_graph_def(graph_def)
return graph
my_graph = load_graph(model_name=os.path.join(outdir, name))
# In[15]:
input_op = my_graph.get_operation_by_name("import/dense_1_input")
output_op = my_graph.get_operation_by_name("import/simple_nn_0")
logit_op = my_graph.get_operation_by_name("import/logits/BiasAdd")
x_hat = input_op.outputs[0] # input tensor
labels = output_op.outputs[0] # label tensor
logits = logit_op.outputs[0] # logits tensor
learning_rate = tf.placeholder(tf.float32, ())
loss = tf.nn.softmax_cross_entropy_with_logits_v2(logits=logits, labels=[labels])
optim_step = tf.train.GradientDescentOptimizer(learning_rate).minimize(loss, var_list=[x_hat])
python-3.x tensorflow keras
One thing you could do is not to use an optimizer, but instead get the input gradient withtf.gradients
and apply updates to the input outside of TensorFlow. But you can also replace the input placeholder with an actual variable, and simplyload
the input value that you want to optimize.
– jdehesa
Nov 9 at 16:15
Or, about the first option, you could actually use an optimizer, but only usecompute_gradients
, then actually apply them out of TensorFlow (I have not tried it but I think that should work, even with non-variables).
– jdehesa
Nov 9 at 16:31
Why not cast the input as variable? This should be possible,too.
– Lau
Nov 9 at 17:02
can you please show me how to do the cast?
– David
Nov 9 at 18:41
One can come out a code to do the gradient decent but it defeat the purpose of using tensorflow which suppose to simplify the procedure
– David
Nov 9 at 18:44
add a comment |
up vote
1
down vote
favorite
up vote
1
down vote
favorite
The following is the code trying to use the input image as a training variable during the optimization. It starts with a keras model and convert that to a tensorflow model. This tensorflow model take a tensor as input and try to optimize the cost function using the input tensor as a trainable variable.
The error is:
NotImplementedError: ('Trying to update a Tensor ', )
The reason is that the input tensor is not a variable. The question is how to make the input image trainable or cast a tensor to a tf.variable. Help is appreciated:
import tensorflow as tf
from keras.models import Sequential, load_model, Model
from keras import backend as K
from keras.layers.core import Dense, Dropout, Activation
import os
from tensorflow.python.framework import graph_util
from tensorflow.python.framework import graph_io
n_classes = 10
model = Sequential()
model.add(Dense(10, input_shape=(784,)))
model.add(Activation('relu'))
model.add(Dense(n_classes, name='logits'))
model.add(Activation('softmax'))
model.compile(loss='categorical_crossentropy', metrics=['accuracy'], optimizer='adam')
# Write the graph in binary .pb file
outdir = "model4_tf"
try:
os.mkdir(outdir )
except:
pass
prefix = "simple_nn"
name = 'output_graph.pb'
# Alias the outputs in the model - this sometimes makes them easier to access in TF
pred =
pred_node_names =
for i, o in enumerate(model.outputs):
pred_node_names.append(prefix+'_'+str(i))
pred.append(tf.identity(o,
name=pred_node_names[i]))
print('Output nodes names are: ', pred_node_names)
sess = K.get_session()
constant_graph = graph_util.convert_variables_to_constants(sess,
sess.graph.as_graph_def(), pred_node_names)
graph_io.write_graph(constant_graph, outdir, name, as_text=False)
tf.reset_default_graph()
def load_graph(model_name):
#graph = tf.Graph()
graph = tf.get_default_graph()
graph_def = tf.GraphDef()
with open(model_name, "rb") as f:
graph_def.ParseFromString(f.read())
with graph.as_default():
tf.import_graph_def(graph_def)
return graph
my_graph = load_graph(model_name=os.path.join(outdir, name))
# In[15]:
input_op = my_graph.get_operation_by_name("import/dense_1_input")
output_op = my_graph.get_operation_by_name("import/simple_nn_0")
logit_op = my_graph.get_operation_by_name("import/logits/BiasAdd")
x_hat = input_op.outputs[0] # input tensor
labels = output_op.outputs[0] # label tensor
logits = logit_op.outputs[0] # logits tensor
learning_rate = tf.placeholder(tf.float32, ())
loss = tf.nn.softmax_cross_entropy_with_logits_v2(logits=logits, labels=[labels])
optim_step = tf.train.GradientDescentOptimizer(learning_rate).minimize(loss, var_list=[x_hat])
python-3.x tensorflow keras
The following is the code trying to use the input image as a training variable during the optimization. It starts with a keras model and convert that to a tensorflow model. This tensorflow model take a tensor as input and try to optimize the cost function using the input tensor as a trainable variable.
The error is:
NotImplementedError: ('Trying to update a Tensor ', )
The reason is that the input tensor is not a variable. The question is how to make the input image trainable or cast a tensor to a tf.variable. Help is appreciated:
import tensorflow as tf
from keras.models import Sequential, load_model, Model
from keras import backend as K
from keras.layers.core import Dense, Dropout, Activation
import os
from tensorflow.python.framework import graph_util
from tensorflow.python.framework import graph_io
n_classes = 10
model = Sequential()
model.add(Dense(10, input_shape=(784,)))
model.add(Activation('relu'))
model.add(Dense(n_classes, name='logits'))
model.add(Activation('softmax'))
model.compile(loss='categorical_crossentropy', metrics=['accuracy'], optimizer='adam')
# Write the graph in binary .pb file
outdir = "model4_tf"
try:
os.mkdir(outdir )
except:
pass
prefix = "simple_nn"
name = 'output_graph.pb'
# Alias the outputs in the model - this sometimes makes them easier to access in TF
pred =
pred_node_names =
for i, o in enumerate(model.outputs):
pred_node_names.append(prefix+'_'+str(i))
pred.append(tf.identity(o,
name=pred_node_names[i]))
print('Output nodes names are: ', pred_node_names)
sess = K.get_session()
constant_graph = graph_util.convert_variables_to_constants(sess,
sess.graph.as_graph_def(), pred_node_names)
graph_io.write_graph(constant_graph, outdir, name, as_text=False)
tf.reset_default_graph()
def load_graph(model_name):
#graph = tf.Graph()
graph = tf.get_default_graph()
graph_def = tf.GraphDef()
with open(model_name, "rb") as f:
graph_def.ParseFromString(f.read())
with graph.as_default():
tf.import_graph_def(graph_def)
return graph
my_graph = load_graph(model_name=os.path.join(outdir, name))
# In[15]:
input_op = my_graph.get_operation_by_name("import/dense_1_input")
output_op = my_graph.get_operation_by_name("import/simple_nn_0")
logit_op = my_graph.get_operation_by_name("import/logits/BiasAdd")
x_hat = input_op.outputs[0] # input tensor
labels = output_op.outputs[0] # label tensor
logits = logit_op.outputs[0] # logits tensor
learning_rate = tf.placeholder(tf.float32, ())
loss = tf.nn.softmax_cross_entropy_with_logits_v2(logits=logits, labels=[labels])
optim_step = tf.train.GradientDescentOptimizer(learning_rate).minimize(loss, var_list=[x_hat])
python-3.x tensorflow keras
python-3.x tensorflow keras
edited Nov 9 at 15:46
asked Nov 9 at 15:35
David
263
263
One thing you could do is not to use an optimizer, but instead get the input gradient withtf.gradients
and apply updates to the input outside of TensorFlow. But you can also replace the input placeholder with an actual variable, and simplyload
the input value that you want to optimize.
– jdehesa
Nov 9 at 16:15
Or, about the first option, you could actually use an optimizer, but only usecompute_gradients
, then actually apply them out of TensorFlow (I have not tried it but I think that should work, even with non-variables).
– jdehesa
Nov 9 at 16:31
Why not cast the input as variable? This should be possible,too.
– Lau
Nov 9 at 17:02
can you please show me how to do the cast?
– David
Nov 9 at 18:41
One can come out a code to do the gradient decent but it defeat the purpose of using tensorflow which suppose to simplify the procedure
– David
Nov 9 at 18:44
add a comment |
One thing you could do is not to use an optimizer, but instead get the input gradient withtf.gradients
and apply updates to the input outside of TensorFlow. But you can also replace the input placeholder with an actual variable, and simplyload
the input value that you want to optimize.
– jdehesa
Nov 9 at 16:15
Or, about the first option, you could actually use an optimizer, but only usecompute_gradients
, then actually apply them out of TensorFlow (I have not tried it but I think that should work, even with non-variables).
– jdehesa
Nov 9 at 16:31
Why not cast the input as variable? This should be possible,too.
– Lau
Nov 9 at 17:02
can you please show me how to do the cast?
– David
Nov 9 at 18:41
One can come out a code to do the gradient decent but it defeat the purpose of using tensorflow which suppose to simplify the procedure
– David
Nov 9 at 18:44
One thing you could do is not to use an optimizer, but instead get the input gradient with
tf.gradients
and apply updates to the input outside of TensorFlow. But you can also replace the input placeholder with an actual variable, and simply load
the input value that you want to optimize.– jdehesa
Nov 9 at 16:15
One thing you could do is not to use an optimizer, but instead get the input gradient with
tf.gradients
and apply updates to the input outside of TensorFlow. But you can also replace the input placeholder with an actual variable, and simply load
the input value that you want to optimize.– jdehesa
Nov 9 at 16:15
Or, about the first option, you could actually use an optimizer, but only use
compute_gradients
, then actually apply them out of TensorFlow (I have not tried it but I think that should work, even with non-variables).– jdehesa
Nov 9 at 16:31
Or, about the first option, you could actually use an optimizer, but only use
compute_gradients
, then actually apply them out of TensorFlow (I have not tried it but I think that should work, even with non-variables).– jdehesa
Nov 9 at 16:31
Why not cast the input as variable? This should be possible,too.
– Lau
Nov 9 at 17:02
Why not cast the input as variable? This should be possible,too.
– Lau
Nov 9 at 17:02
can you please show me how to do the cast?
– David
Nov 9 at 18:41
can you please show me how to do the cast?
– David
Nov 9 at 18:41
One can come out a code to do the gradient decent but it defeat the purpose of using tensorflow which suppose to simplify the procedure
– David
Nov 9 at 18:44
One can come out a code to do the gradient decent but it defeat the purpose of using tensorflow which suppose to simplify the procedure
– David
Nov 9 at 18:44
add a comment |
active
oldest
votes
Your Answer
StackExchange.ifUsing("editor", function () {
StackExchange.using("externalEditor", function () {
StackExchange.using("snippets", function () {
StackExchange.snippets.init();
});
});
}, "code-snippets");
StackExchange.ready(function() {
var channelOptions = {
tags: "".split(" "),
id: "1"
};
initTagRenderer("".split(" "), "".split(" "), channelOptions);
StackExchange.using("externalEditor", function() {
// Have to fire editor after snippets, if snippets enabled
if (StackExchange.settings.snippets.snippetsEnabled) {
StackExchange.using("snippets", function() {
createEditor();
});
}
else {
createEditor();
}
});
function createEditor() {
StackExchange.prepareEditor({
heartbeatType: 'answer',
convertImagesToLinks: true,
noModals: true,
showLowRepImageUploadWarning: true,
reputationToPostImages: 10,
bindNavPrevention: true,
postfix: "",
imageUploader: {
brandingHtml: "Powered by u003ca class="icon-imgur-white" href="https://imgur.com/"u003eu003c/au003e",
contentPolicyHtml: "User contributions licensed under u003ca href="https://creativecommons.org/licenses/by-sa/3.0/"u003ecc by-sa 3.0 with attribution requiredu003c/au003e u003ca href="https://stackoverflow.com/legal/content-policy"u003e(content policy)u003c/au003e",
allowUrls: true
},
onDemand: true,
discardSelector: ".discard-answer"
,immediatelyShowMarkdownHelp:true
});
}
});
Sign up or log in
StackExchange.ready(function () {
StackExchange.helpers.onClickDraftSave('#login-link');
});
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Post as a guest
Required, but never shown
StackExchange.ready(
function () {
StackExchange.openid.initPostLogin('.new-post-login', 'https%3a%2f%2fstackoverflow.com%2fquestions%2f53228768%2fhow-to-make-a-input-tensor-trainable%23new-answer', 'question_page');
}
);
Post as a guest
Required, but never shown
active
oldest
votes
active
oldest
votes
active
oldest
votes
active
oldest
votes
Thanks for contributing an answer to Stack Overflow!
- Please be sure to answer the question. Provide details and share your research!
But avoid …
- Asking for help, clarification, or responding to other answers.
- Making statements based on opinion; back them up with references or personal experience.
To learn more, see our tips on writing great answers.
Some of your past answers have not been well-received, and you're in danger of being blocked from answering.
Please pay close attention to the following guidance:
- Please be sure to answer the question. Provide details and share your research!
But avoid …
- Asking for help, clarification, or responding to other answers.
- Making statements based on opinion; back them up with references or personal experience.
To learn more, see our tips on writing great answers.
Sign up or log in
StackExchange.ready(function () {
StackExchange.helpers.onClickDraftSave('#login-link');
});
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Post as a guest
Required, but never shown
StackExchange.ready(
function () {
StackExchange.openid.initPostLogin('.new-post-login', 'https%3a%2f%2fstackoverflow.com%2fquestions%2f53228768%2fhow-to-make-a-input-tensor-trainable%23new-answer', 'question_page');
}
);
Post as a guest
Required, but never shown
Sign up or log in
StackExchange.ready(function () {
StackExchange.helpers.onClickDraftSave('#login-link');
});
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Post as a guest
Required, but never shown
Sign up or log in
StackExchange.ready(function () {
StackExchange.helpers.onClickDraftSave('#login-link');
});
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Post as a guest
Required, but never shown
Sign up or log in
StackExchange.ready(function () {
StackExchange.helpers.onClickDraftSave('#login-link');
});
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Post as a guest
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
One thing you could do is not to use an optimizer, but instead get the input gradient with
tf.gradients
and apply updates to the input outside of TensorFlow. But you can also replace the input placeholder with an actual variable, and simplyload
the input value that you want to optimize.– jdehesa
Nov 9 at 16:15
Or, about the first option, you could actually use an optimizer, but only use
compute_gradients
, then actually apply them out of TensorFlow (I have not tried it but I think that should work, even with non-variables).– jdehesa
Nov 9 at 16:31
Why not cast the input as variable? This should be possible,too.
– Lau
Nov 9 at 17:02
can you please show me how to do the cast?
– David
Nov 9 at 18:41
One can come out a code to do the gradient decent but it defeat the purpose of using tensorflow which suppose to simplify the procedure
– David
Nov 9 at 18:44