How to use tf.case to control flow in tensorflow graph to perform differently during training and testing
I am trying to control the graph flow using a tf.cond() and tf.case().
I have several networks which yield an output of the same size (networks).
I have an additional network that outputs which of the networks above to use (networks_prob).
During training, I want to stack all of the networks results. During testing, I want to construct a tensor which is composed of the results in networks in the indices where networks_prob is maximal. (So I can avoid evaluating all of the networks and just evaluate the one with the highest probability)
Here is a simple example that I came up with but it doesn't work and I don't understand why.
import tensorflow as tf
networks = tf.constant([[[1], [2], [3]], [[4], [5], [6]]])
networks_prob = tf.constant([[0.2, 0.3, 0.4], [0.8, 0.1, 0.0]])
is_training = tf.placeholder(tf.bool, shape=())
network_idx = tf.argmax(networks_prob)
case_dict = {tf.equal(network_idx, i): lambda: networks[i] for i in range(networks.shape[1])}
output = tf.cond(is_training, lambda: tf.stack(networks), lambda: tf.case(case_dict, default=lambda: 1))
with tf.Session() as sess:
output_val = sess.run(output, feed_dict={is_training: False})
print(output_val)
I get Shape must be rank 0 but is rank 1 for 'cond/case/If_0/Switch' (op: 'Switch') with input shapes: [3], [3]. error.
python tensorflow
asked Nov 15 '18 at 20:32
itzik Ben Shabatitzik Ben Shabat
622616
add a comment |
I am trying to control the graph flow using a tf.cond() and tf.case().
I have several networks which yield an output of the same size (networks).
I have an additional network that outputs which of the networks above to use (networks_prob).
During training, I want to stack all of the networks results. During testing, I want to construct a tensor which is composed of the results in networks in the indices where networks_prob is maximal. (So I can avoid evaluating all of the networks and just evaluate the one with the highest probability)
Here is a simple example that I came up with but it doesn't work and I don't understand why.
import tensorflow as tf
networks = tf.constant([[[1], [2], [3]], [[4], [5], [6]]])
networks_prob = tf.constant([[0.2, 0.3, 0.4], [0.8, 0.1, 0.0]])
is_training = tf.placeholder(tf.bool, shape=())
network_idx = tf.argmax(networks_prob)
case_dict = {tf.equal(network_idx, i): lambda: networks[i] for i in range(networks.shape[1])}
output = tf.cond(is_training, lambda: tf.stack(networks), lambda: tf.case(case_dict, default=lambda: 1))
with tf.Session() as sess:
output_val = sess.run(output, feed_dict={is_training: False})
print(output_val)
I get Shape must be rank 0 but is rank 1 for 'cond/case/If_0/Switch' (op: 'Switch') with input shapes: [3], [3]. error.
python tensorflow
asked Nov 15 '18 at 20:32
itzik Ben Shabatitzik Ben Shabat
622616
add a comment |
I am trying to control the graph flow using a tf.cond() and tf.case().
I have several networks which yield an output of the same size (networks).
I have an additional network that outputs which of the networks above to use (networks_prob).
During training, I want to stack all of the networks results. During testing, I want to construct a tensor which is composed of the results in networks in the indices where networks_prob is maximal. (So I can avoid evaluating all of the networks and just evaluate the one with the highest probability)
Here is a simple example that I came up with but it doesn't work and I don't understand why.
import tensorflow as tf
networks = tf.constant([[[1], [2], [3]], [[4], [5], [6]]])
networks_prob = tf.constant([[0.2, 0.3, 0.4], [0.8, 0.1, 0.0]])
is_training = tf.placeholder(tf.bool, shape=())
network_idx = tf.argmax(networks_prob)
case_dict = {tf.equal(network_idx, i): lambda: networks[i] for i in range(networks.shape[1])}
output = tf.cond(is_training, lambda: tf.stack(networks), lambda: tf.case(case_dict, default=lambda: 1))
with tf.Session() as sess:
output_val = sess.run(output, feed_dict={is_training: False})
print(output_val)
I get Shape must be rank 0 but is rank 1 for 'cond/case/If_0/Switch' (op: 'Switch') with input shapes: [3], [3]. error.
python tensorflow
asked Nov 15 '18 at 20:32
itzik Ben Shabatitzik Ben Shabat
622616
I am trying to control the graph flow using a tf.cond() and tf.case().
I have several networks which yield an output of the same size (networks).
I have an additional network that outputs which of the networks above to use (networks_prob).
During training, I want to stack all of the networks results. During testing, I want to construct a tensor which is composed of the results in networks in the indices where networks_prob is maximal. (So I can avoid evaluating all of the networks and just evaluate the one with the highest probability)
Here is a simple example that I came up with but it doesn't work and I don't understand why.
import tensorflow as tf
networks = tf.constant([[[1], [2], [3]], [[4], [5], [6]]])
networks_prob = tf.constant([[0.2, 0.3, 0.4], [0.8, 0.1, 0.0]])
is_training = tf.placeholder(tf.bool, shape=())
network_idx = tf.argmax(networks_prob)
case_dict = {tf.equal(network_idx, i): lambda: networks[i] for i in range(networks.shape[1])}
output = tf.cond(is_training, lambda: tf.stack(networks), lambda: tf.case(case_dict, default=lambda: 1))
with tf.Session() as sess:
output_val = sess.run(output, feed_dict={is_training: False})
print(output_val)
I get Shape must be rank 0 but is rank 1 for 'cond/case/If_0/Switch' (op: 'Switch') with input shapes: [3], [3]. error.
python tensorflow
python tensorflow
asked Nov 15 '18 at 20:32
itzik Ben Shabatitzik Ben Shabat
622616
asked Nov 15 '18 at 20:32
itzik Ben Shabatitzik Ben Shabat
622616
asked Nov 15 '18 at 20:32
itzik Ben Shabatitzik Ben Shabat
622616
asked Nov 15 '18 at 20:32
itzik Ben Shabatitzik Ben Shabat
622616
asked Nov 15 '18 at 20:32
itzik Ben Shabatitzik Ben Shabat
622616
622616
add a comment |
add a comment |
0
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',
autoActivateHeartbeat: false,
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%2f53327492%2fhow-to-use-tf-case-to-control-flow-in-tensorflow-graph-to-perform-differently-du%23new-answer', 'question_page');
}
);
Post as a guest
Required, but never shown
0
active
oldest
votes
0
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.
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%2f53327492%2fhow-to-use-tf-case-to-control-flow-in-tensorflow-graph-to-perform-differently-du%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
