How can I plot output of convolutional layers as a scatter plot? Is it even possible?How can I represent an 'Enum' in Python?How to flush output of print function?How can I safely create a nested directory in Python?How can I remove a trailing newline in Python?How can I make a time delay in Python?How can I count the occurrences of a list item?How to put the legend out of the plotHow to put individual tags for a scatter plotHow to make IPython notebook matplotlib plot inlineHow can I freeze last layer of my own model?
Why is the A380’s with-reversers stopping distance the same as its no-reversers stopping distance?
Does Cersei deserve to be called a tyrant?
How can I make dummy text (like lipsum) grey?
Why is so much ransomware breakable?
Who is frowning in the sentence "Daisy looked at Tom frowning"?
Why is vowel phonology represented in a trapezoid instead of a square?
Would life always name the light from their sun "white"
What dog breeds survive the apocalypse for generations?
Given 0s on Assignments with suspected and dismissed cheating?
What do astronauts do with their trash on the ISS?
Why can't I share a one use code with anyone else?
What would a Dragon have to exhale to cause rain?
Is there a method to separate iron from mercury?
Canadian citizen who is presently in litigation with a US-based company
How to handle professionally if colleagues has referred his relative and asking to take easy while taking interview
How do Ctrl+C and Ctrl+V work?
Holding rent money for my friend which amounts to over $10k?
Capital gains on stocks sold to take initial investment off the table
Is it standard to have the first week's pay indefinitely withheld?
Usage of the relative pronoun "dont"
How come Arya Stark didn't burn in Game of Thrones Season 8 Episode 5
What color to choose as "danger" if the main color of my app is red
Why are there five extra turns in tournament Magic?
Would a "ring language" be possible?
How can I plot output of convolutional layers as a scatter plot? Is it even possible?
How can I represent an 'Enum' in Python?How to flush output of print function?How can I safely create a nested directory in Python?How can I remove a trailing newline in Python?How can I make a time delay in Python?How can I count the occurrences of a list item?How to put the legend out of the plotHow to put individual tags for a scatter plotHow to make IPython notebook matplotlib plot inlineHow can I freeze last layer of my own model?
.everyoneloves__top-leaderboard:empty,.everyoneloves__mid-leaderboard:empty,.everyoneloves__bot-mid-leaderboard:empty height:90px;width:728px;box-sizing:border-box;
i want to plot and see where the data points lie on any n-dimensional plane after passing through a convolutional layer for the purpose of classification. Is it possible?
model = Sequential()
model.add(TimeDistributed(Conv2D(64, (2, 2), activation='relu', padding='same'),
input_shape=(20,128, 128 ,1)))
model.add(TimeDistributed(MaxPooling2D(pool_size=(2, 2))))
model.add(TimeDistributed(Conv2D(32, (3, 3), activation='relu', padding='same')))
model.add(TimeDistributed(MaxPooling2D(pool_size=(2, 2))))
model.add(TimeDistributed(Conv2D(16, (3, 3), activation='relu', padding='same')))
model.add(TimeDistributed(MaxPooling2D(pool_size=(2, 2))))
model.add(TimeDistributed(Flatten()))
model.add(LSTM(units=64, return_sequences=True))
model.add(TimeDistributed(Reshape((8, 8, 1))))
model.add(TimeDistributed(UpSampling2D((2,2))))
model.add(TimeDistributed(Conv2D(16, (3,3), activation='relu', padding='same')))
model.add(TimeDistributed(UpSampling2D((2,2))))
model.add(TimeDistributed(Conv2D(32, (3,3), activation='relu', padding='same')))
model.add(TimeDistributed(UpSampling2D((2,2))))
model.add(TimeDistributed(Conv2D(64, (2,2), activation='relu', padding='same')))
model.add(TimeDistributed(UpSampling2D((2,2))))
model.add(TimeDistributed(Conv2D(1, (3,3), padding='same')))
Given above is the model. I want to plot output of LSTM unit. Thank you
python numpy opencv matplotlib deep-learning
asked Mar 23 at 16:17
shjkshjk
226
add a comment |
i want to plot and see where the data points lie on any n-dimensional plane after passing through a convolutional layer for the purpose of classification. Is it possible?
model = Sequential()
model.add(TimeDistributed(Conv2D(64, (2, 2), activation='relu', padding='same'),
input_shape=(20,128, 128 ,1)))
model.add(TimeDistributed(MaxPooling2D(pool_size=(2, 2))))
model.add(TimeDistributed(Conv2D(32, (3, 3), activation='relu', padding='same')))
model.add(TimeDistributed(MaxPooling2D(pool_size=(2, 2))))
model.add(TimeDistributed(Conv2D(16, (3, 3), activation='relu', padding='same')))
model.add(TimeDistributed(MaxPooling2D(pool_size=(2, 2))))
model.add(TimeDistributed(Flatten()))
model.add(LSTM(units=64, return_sequences=True))
model.add(TimeDistributed(Reshape((8, 8, 1))))
model.add(TimeDistributed(UpSampling2D((2,2))))
model.add(TimeDistributed(Conv2D(16, (3,3), activation='relu', padding='same')))
model.add(TimeDistributed(UpSampling2D((2,2))))
model.add(TimeDistributed(Conv2D(32, (3,3), activation='relu', padding='same')))
model.add(TimeDistributed(UpSampling2D((2,2))))
model.add(TimeDistributed(Conv2D(64, (2,2), activation='relu', padding='same')))
model.add(TimeDistributed(UpSampling2D((2,2))))
model.add(TimeDistributed(Conv2D(1, (3,3), padding='same')))
Given above is the model. I want to plot output of LSTM unit. Thank you
python numpy opencv matplotlib deep-learning
asked Mar 23 at 16:17
shjkshjk
226
It would be really helpful if you had a better description of what you are trying to plot.
– Jody Klymak
Mar 23 at 16:38
well, i hope themodel.add(LSTM(units=64, return_sequences=True))will produce some numerical output. Correct me if im wrong. I need to plot those encoded outputs
– shjk
Mar 23 at 16:40
add a comment |
i want to plot and see where the data points lie on any n-dimensional plane after passing through a convolutional layer for the purpose of classification. Is it possible?
model = Sequential()
model.add(TimeDistributed(Conv2D(64, (2, 2), activation='relu', padding='same'),
input_shape=(20,128, 128 ,1)))
model.add(TimeDistributed(MaxPooling2D(pool_size=(2, 2))))
model.add(TimeDistributed(Conv2D(32, (3, 3), activation='relu', padding='same')))
model.add(TimeDistributed(MaxPooling2D(pool_size=(2, 2))))
model.add(TimeDistributed(Conv2D(16, (3, 3), activation='relu', padding='same')))
model.add(TimeDistributed(MaxPooling2D(pool_size=(2, 2))))
model.add(TimeDistributed(Flatten()))
model.add(LSTM(units=64, return_sequences=True))
model.add(TimeDistributed(Reshape((8, 8, 1))))
model.add(TimeDistributed(UpSampling2D((2,2))))
model.add(TimeDistributed(Conv2D(16, (3,3), activation='relu', padding='same')))
model.add(TimeDistributed(UpSampling2D((2,2))))
model.add(TimeDistributed(Conv2D(32, (3,3), activation='relu', padding='same')))
model.add(TimeDistributed(UpSampling2D((2,2))))
model.add(TimeDistributed(Conv2D(64, (2,2), activation='relu', padding='same')))
model.add(TimeDistributed(UpSampling2D((2,2))))
model.add(TimeDistributed(Conv2D(1, (3,3), padding='same')))
Given above is the model. I want to plot output of LSTM unit. Thank you
python numpy opencv matplotlib deep-learning
asked Mar 23 at 16:17
shjkshjk
226
i want to plot and see where the data points lie on any n-dimensional plane after passing through a convolutional layer for the purpose of classification. Is it possible?
model = Sequential()
model.add(TimeDistributed(Conv2D(64, (2, 2), activation='relu', padding='same'),
input_shape=(20,128, 128 ,1)))
model.add(TimeDistributed(MaxPooling2D(pool_size=(2, 2))))
model.add(TimeDistributed(Conv2D(32, (3, 3), activation='relu', padding='same')))
model.add(TimeDistributed(MaxPooling2D(pool_size=(2, 2))))
model.add(TimeDistributed(Conv2D(16, (3, 3), activation='relu', padding='same')))
model.add(TimeDistributed(MaxPooling2D(pool_size=(2, 2))))
model.add(TimeDistributed(Flatten()))
model.add(LSTM(units=64, return_sequences=True))
model.add(TimeDistributed(Reshape((8, 8, 1))))
model.add(TimeDistributed(UpSampling2D((2,2))))
model.add(TimeDistributed(Conv2D(16, (3,3), activation='relu', padding='same')))
model.add(TimeDistributed(UpSampling2D((2,2))))
model.add(TimeDistributed(Conv2D(32, (3,3), activation='relu', padding='same')))
model.add(TimeDistributed(UpSampling2D((2,2))))
model.add(TimeDistributed(Conv2D(64, (2,2), activation='relu', padding='same')))
model.add(TimeDistributed(UpSampling2D((2,2))))
model.add(TimeDistributed(Conv2D(1, (3,3), padding='same')))
Given above is the model. I want to plot output of LSTM unit. Thank you
python numpy opencv matplotlib deep-learning
python numpy opencv matplotlib deep-learning
asked Mar 23 at 16:17
shjkshjk
226
asked Mar 23 at 16:17
shjkshjk
226
asked Mar 23 at 16:17
shjkshjk
226
asked Mar 23 at 16:17
shjkshjk
226
asked Mar 23 at 16:17
shjkshjk
226
226
It would be really helpful if you had a better description of what you are trying to plot.
– Jody Klymak
Mar 23 at 16:38
well, i hope themodel.add(LSTM(units=64, return_sequences=True))will produce some numerical output. Correct me if im wrong. I need to plot those encoded outputs
– shjk
Mar 23 at 16:40
add a comment |
It would be really helpful if you had a better description of what you are trying to plot.
– Jody Klymak
Mar 23 at 16:38
well, i hope themodel.add(LSTM(units=64, return_sequences=True))will produce some numerical output. Correct me if im wrong. I need to plot those encoded outputs
– shjk
Mar 23 at 16:40
It would be really helpful if you had a better description of what you are trying to plot.
– Jody Klymak
Mar 23 at 16:38
It would be really helpful if you had a better description of what you are trying to plot.
– Jody Klymak
Mar 23 at 16:38
well, i hope the
model.add(LSTM(units=64, return_sequences=True)) will produce some numerical output. Correct me if im wrong. I need to plot those encoded outputs– shjk
Mar 23 at 16:40
well, i hope the
model.add(LSTM(units=64, return_sequences=True)) will produce some numerical output. Correct me if im wrong. I need to plot those encoded outputs– shjk
Mar 23 at 16:40
add a comment |
1 Answer
1
active
oldest
votes
See below for some nice visualization of an LSTM model trained to recognise sign language:
https://medium.com/asap-report/visualizing-lstm-networks-part-i-f1d3fa6aace7
Here their code repository: https://github.com/asap-report/lstm-visualisation
answered Mar 24 at 22:38
Kai AeberliKai Aeberli
662515
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%2f55315794%2fhow-can-i-plot-output-of-convolutional-layers-as-a-scatter-plot-is-it-even-poss%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
See below for some nice visualization of an LSTM model trained to recognise sign language:
https://medium.com/asap-report/visualizing-lstm-networks-part-i-f1d3fa6aace7
Here their code repository: https://github.com/asap-report/lstm-visualisation
answered Mar 24 at 22:38
Kai AeberliKai Aeberli
662515
add a comment |
See below for some nice visualization of an LSTM model trained to recognise sign language:
https://medium.com/asap-report/visualizing-lstm-networks-part-i-f1d3fa6aace7
Here their code repository: https://github.com/asap-report/lstm-visualisation
answered Mar 24 at 22:38
Kai AeberliKai Aeberli
662515
add a comment |
See below for some nice visualization of an LSTM model trained to recognise sign language:
https://medium.com/asap-report/visualizing-lstm-networks-part-i-f1d3fa6aace7
Here their code repository: https://github.com/asap-report/lstm-visualisation
answered Mar 24 at 22:38
Kai AeberliKai Aeberli
662515
See below for some nice visualization of an LSTM model trained to recognise sign language:
https://medium.com/asap-report/visualizing-lstm-networks-part-i-f1d3fa6aace7
Here their code repository: https://github.com/asap-report/lstm-visualisation
answered Mar 24 at 22:38
Kai AeberliKai Aeberli
662515
answered Mar 24 at 22:38
Kai AeberliKai Aeberli
662515
answered Mar 24 at 22:38
Kai AeberliKai Aeberli
662515
answered Mar 24 at 22:38
Kai AeberliKai Aeberli
662515
662515
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%2f55315794%2fhow-can-i-plot-output-of-convolutional-layers-as-a-scatter-plot-is-it-even-poss%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
It would be really helpful if you had a better description of what you are trying to plot.
– Jody Klymak
Mar 23 at 16:38
well, i hope the
model.add(LSTM(units=64, return_sequences=True))will produce some numerical output. Correct me if im wrong. I need to plot those encoded outputs– shjk
Mar 23 at 16:40