Display values of a dictionary in Tensorlow
Hello i'm new to TensorFlow and i'm trying to create a dictionary of weigths per layer for my ANN implementation.
The issue is that although i create the dictionary with strings as keys and tensors as values i don't know how to display them when i call the init_weight method
def init_weights(topology):
#topology: dimensions of the network
for i in range(1,len(topology)):
parameters['W' + str(i)] = tf.Variable(tf.random_normal([topology[i-1],topology[i]]))
the output of the method shows the following:
{'W1': <tf.Variable 'Variable_1:0' shape=(2, 5) dtype=float32_ref>,
'W2': <tf.Variable 'Variable_3:0' shape=(5, 5) dtype=float32_ref>,
'W3': <tf.Variable 'Variable_5:0' shape=(5, 5) dtype=float32_ref>,
'W4': <tf.Variable 'Variable_7:0' shape=(5, 10) dtype=float32_ref>}
My question is how can print the weights matrices?
python dictionary tensorflow neural-network weight
asked Nov 16 '18 at 0:22
max thundermax thunder
51
add a comment |
Hello i'm new to TensorFlow and i'm trying to create a dictionary of weigths per layer for my ANN implementation.
The issue is that although i create the dictionary with strings as keys and tensors as values i don't know how to display them when i call the init_weight method
def init_weights(topology):
#topology: dimensions of the network
for i in range(1,len(topology)):
parameters['W' + str(i)] = tf.Variable(tf.random_normal([topology[i-1],topology[i]]))
the output of the method shows the following:
{'W1': <tf.Variable 'Variable_1:0' shape=(2, 5) dtype=float32_ref>,
'W2': <tf.Variable 'Variable_3:0' shape=(5, 5) dtype=float32_ref>,
'W3': <tf.Variable 'Variable_5:0' shape=(5, 5) dtype=float32_ref>,
'W4': <tf.Variable 'Variable_7:0' shape=(5, 10) dtype=float32_ref>}
My question is how can print the weights matrices?
python dictionary tensorflow neural-network weight
asked Nov 16 '18 at 0:22
max thundermax thunder
51
add a comment |
Hello i'm new to TensorFlow and i'm trying to create a dictionary of weigths per layer for my ANN implementation.
The issue is that although i create the dictionary with strings as keys and tensors as values i don't know how to display them when i call the init_weight method
def init_weights(topology):
#topology: dimensions of the network
for i in range(1,len(topology)):
parameters['W' + str(i)] = tf.Variable(tf.random_normal([topology[i-1],topology[i]]))
the output of the method shows the following:
{'W1': <tf.Variable 'Variable_1:0' shape=(2, 5) dtype=float32_ref>,
'W2': <tf.Variable 'Variable_3:0' shape=(5, 5) dtype=float32_ref>,
'W3': <tf.Variable 'Variable_5:0' shape=(5, 5) dtype=float32_ref>,
'W4': <tf.Variable 'Variable_7:0' shape=(5, 10) dtype=float32_ref>}
My question is how can print the weights matrices?
python dictionary tensorflow neural-network weight
asked Nov 16 '18 at 0:22
max thundermax thunder
51
Hello i'm new to TensorFlow and i'm trying to create a dictionary of weigths per layer for my ANN implementation.
The issue is that although i create the dictionary with strings as keys and tensors as values i don't know how to display them when i call the init_weight method
def init_weights(topology):
#topology: dimensions of the network
for i in range(1,len(topology)):
parameters['W' + str(i)] = tf.Variable(tf.random_normal([topology[i-1],topology[i]]))
the output of the method shows the following:
{'W1': <tf.Variable 'Variable_1:0' shape=(2, 5) dtype=float32_ref>,
'W2': <tf.Variable 'Variable_3:0' shape=(5, 5) dtype=float32_ref>,
'W3': <tf.Variable 'Variable_5:0' shape=(5, 5) dtype=float32_ref>,
'W4': <tf.Variable 'Variable_7:0' shape=(5, 10) dtype=float32_ref>}
My question is how can print the weights matrices?
python dictionary tensorflow neural-network weight
python dictionary tensorflow neural-network weight
asked Nov 16 '18 at 0:22
max thundermax thunder
51
asked Nov 16 '18 at 0:22
max thundermax thunder
51
asked Nov 16 '18 at 0:22
max thundermax thunder
51
asked Nov 16 '18 at 0:22
max thundermax thunder
51
asked Nov 16 '18 at 0:22
max thundermax thunder
51
51
add a comment |
add a comment |
1 Answer
1
active
oldest
votes
Tensorflow is a statically typed framework (guess this is changing in 2.0). Meaning, you first build a static graph and the graph has values only when run using Tf.Session(). Now to answer your question. There are two ways to get what you want.
Add
tf.enable_eager_execution()at the start of your script. This creates a dynamic graph (similar to Pytorch). Your same code without any extra addition will give you what you want.Wrap everything into a
tf.Session()and run it. You will get the weight matrices
answered Nov 16 '18 at 0:31
Abhijit BalajiAbhijit Balaji
555421
add a comment |
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%2f53329708%2fdisplay-values-of-a-dictionary-in-tensorlow%23new-answer', 'question_page');
}
);
Post as a guest
Required, but never shown
1 Answer
1
active
oldest
votes
1 Answer
1
active
oldest
votes
active
oldest
votes
active
oldest
votes
Tensorflow is a statically typed framework (guess this is changing in 2.0). Meaning, you first build a static graph and the graph has values only when run using Tf.Session(). Now to answer your question. There are two ways to get what you want.
Add
tf.enable_eager_execution()at the start of your script. This creates a dynamic graph (similar to Pytorch). Your same code without any extra addition will give you what you want.Wrap everything into a
tf.Session()and run it. You will get the weight matrices
answered Nov 16 '18 at 0:31
Abhijit BalajiAbhijit Balaji
555421
add a comment |
Tensorflow is a statically typed framework (guess this is changing in 2.0). Meaning, you first build a static graph and the graph has values only when run using Tf.Session(). Now to answer your question. There are two ways to get what you want.
Add
tf.enable_eager_execution()at the start of your script. This creates a dynamic graph (similar to Pytorch). Your same code without any extra addition will give you what you want.Wrap everything into a
tf.Session()and run it. You will get the weight matrices
answered Nov 16 '18 at 0:31
Abhijit BalajiAbhijit Balaji
555421
add a comment |
Tensorflow is a statically typed framework (guess this is changing in 2.0). Meaning, you first build a static graph and the graph has values only when run using Tf.Session(). Now to answer your question. There are two ways to get what you want.
Add
tf.enable_eager_execution()at the start of your script. This creates a dynamic graph (similar to Pytorch). Your same code without any extra addition will give you what you want.Wrap everything into a
tf.Session()and run it. You will get the weight matrices
answered Nov 16 '18 at 0:31
Abhijit BalajiAbhijit Balaji
555421
Tensorflow is a statically typed framework (guess this is changing in 2.0). Meaning, you first build a static graph and the graph has values only when run using Tf.Session(). Now to answer your question. There are two ways to get what you want.
Add
tf.enable_eager_execution()at the start of your script. This creates a dynamic graph (similar to Pytorch). Your same code without any extra addition will give you what you want.Wrap everything into a
tf.Session()and run it. You will get the weight matrices
answered Nov 16 '18 at 0:31
Abhijit BalajiAbhijit Balaji
555421
answered Nov 16 '18 at 0:31
Abhijit BalajiAbhijit Balaji
555421
answered Nov 16 '18 at 0:31
Abhijit BalajiAbhijit Balaji
555421
answered Nov 16 '18 at 0:31
Abhijit BalajiAbhijit Balaji
555421
555421
add a comment |
add a comment |
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%2f53329708%2fdisplay-values-of-a-dictionary-in-tensorlow%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
