In Keras, how to apply softmax function on each row of the weight matrix?
0
from keras.models import Model
from keras.models import Input
from keras.layers import Dense
a = Input(shape=(3,))
b = Dense(2, use_bias=False)(a)
model = Model(inputs=a, outputs=b)
Suppose that the weights of the Dense layer in the above code is [[2, 3], [3, 1], [-1, 1]]. If we give [[2, 1, 3]] as an input to the model, then the output will be:
But I want to apply the softmax function to each row of the Dense layer, so that the output will be:
How can I do this?
python machine-learning keras keras-layer softmax
asked Nov 13 '18 at 3:41
zxcvzxcv
285
add a comment |
0
from keras.models import Model
from keras.models import Input
from keras.layers import Dense
a = Input(shape=(3,))
b = Dense(2, use_bias=False)(a)
model = Model(inputs=a, outputs=b)
Suppose that the weights of the Dense layer in the above code is [[2, 3], [3, 1], [-1, 1]]. If we give [[2, 1, 3]] as an input to the model, then the output will be:
But I want to apply the softmax function to each row of the Dense layer, so that the output will be:
How can I do this?
python machine-learning keras keras-layer softmax
asked Nov 13 '18 at 3:41
zxcvzxcv
285
You mean you want the softmax to be applied on the weights of Dense layer and not on its output, right?
– today
Nov 13 '18 at 7:29
@today Yes, exactly.
– zxcv
Nov 13 '18 at 9:59
add a comment |
0
0
0
from keras.models import Model
from keras.models import Input
from keras.layers import Dense
a = Input(shape=(3,))
b = Dense(2, use_bias=False)(a)
model = Model(inputs=a, outputs=b)
Suppose that the weights of the Dense layer in the above code is [[2, 3], [3, 1], [-1, 1]]. If we give [[2, 1, 3]] as an input to the model, then the output will be:
But I want to apply the softmax function to each row of the Dense layer, so that the output will be:
How can I do this?
python machine-learning keras keras-layer softmax
asked Nov 13 '18 at 3:41
zxcvzxcv
285
from keras.models import Model
from keras.models import Input
from keras.layers import Dense
a = Input(shape=(3,))
b = Dense(2, use_bias=False)(a)
model = Model(inputs=a, outputs=b)
Suppose that the weights of the Dense layer in the above code is [[2, 3], [3, 1], [-1, 1]]. If we give [[2, 1, 3]] as an input to the model, then the output will be:
But I want to apply the softmax function to each row of the Dense layer, so that the output will be:
How can I do this?
python machine-learning keras keras-layer softmax
python machine-learning keras keras-layer softmax
asked Nov 13 '18 at 3:41
zxcvzxcv
285
asked Nov 13 '18 at 3:41
zxcvzxcv
285
edited Nov 14 '18 at 5:04
zxcv
asked Nov 13 '18 at 3:41
zxcvzxcv
285
asked Nov 13 '18 at 3:41
zxcvzxcv
285
asked Nov 13 '18 at 3:41
zxcvzxcv
285
285
You mean you want the softmax to be applied on the weights of Dense layer and not on its output, right?
– today
Nov 13 '18 at 7:29
@today Yes, exactly.
– zxcv
Nov 13 '18 at 9:59
add a comment |
You mean you want the softmax to be applied on the weights of Dense layer and not on its output, right?
– today
Nov 13 '18 at 7:29
@today Yes, exactly.
– zxcv
Nov 13 '18 at 9:59
You mean you want the softmax to be applied on the weights of Dense layer and not on its output, right?
– today
Nov 13 '18 at 7:29
You mean you want the softmax to be applied on the weights of Dense layer and not on its output, right?
– today
Nov 13 '18 at 7:29
@today Yes, exactly.
– zxcv
Nov 13 '18 at 9:59
@today Yes, exactly.
– zxcv
Nov 13 '18 at 9:59
add a comment |
1 Answer
1
active
oldest
votes
1
One way to achieve what you are looking for is to define a custom layer by subclassing the Dense layer and overriding its call method:
from keras import backend as K
class CustomDense(Dense):
def __init__(self, units, **kwargs):
super(CustomDense, self).__init__(units, **kwargs)
def call(self, inputs):
output = K.dot(inputs, K.softmax(self.kernel, axis=-1))
if self.use_bias:
output = K.bias_add(output, self.bias, data_format='channels_last')
if self.activation is not None:
output = self.activation(output)
return output
Test to make sure it works:
model = Sequential()
model.add(CustomDense(2, use_bias=False, input_shape=(3,)))
model.compile(loss='mse', optimizer='adam')
import numpy as np
w = np.array([[2,3], [3,1], [1,-1]])
inp = np.array([[2,1,3]])
model.layers[0].set_weights([w])
print(model.predict(inp))
# output
[[4.0610714 1.9389288]]
Verify it using numpy:
soft_w = np.exp(w) / np.sum(np.exp(w), axis=-1, keepdims=True)
print(np.dot(inp, soft_w))
[[4.06107115 1.93892885]]
answered Nov 13 '18 at 10:58
todaytoday
10.6k21636
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
});
}
});
draft saved
draft discarded
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%2f53273456%2fin-keras-how-to-apply-softmax-function-on-each-row-of-the-weight-matrix%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
1
One way to achieve what you are looking for is to define a custom layer by subclassing the Dense layer and overriding its call method:
from keras import backend as K
class CustomDense(Dense):
def __init__(self, units, **kwargs):
super(CustomDense, self).__init__(units, **kwargs)
def call(self, inputs):
output = K.dot(inputs, K.softmax(self.kernel, axis=-1))
if self.use_bias:
output = K.bias_add(output, self.bias, data_format='channels_last')
if self.activation is not None:
output = self.activation(output)
return output
Test to make sure it works:
model = Sequential()
model.add(CustomDense(2, use_bias=False, input_shape=(3,)))
model.compile(loss='mse', optimizer='adam')
import numpy as np
w = np.array([[2,3], [3,1], [1,-1]])
inp = np.array([[2,1,3]])
model.layers[0].set_weights([w])
print(model.predict(inp))
# output
[[4.0610714 1.9389288]]
Verify it using numpy:
soft_w = np.exp(w) / np.sum(np.exp(w), axis=-1, keepdims=True)
print(np.dot(inp, soft_w))
[[4.06107115 1.93892885]]
answered Nov 13 '18 at 10:58
todaytoday
10.6k21636
add a comment |
1
One way to achieve what you are looking for is to define a custom layer by subclassing the Dense layer and overriding its call method:
from keras import backend as K
class CustomDense(Dense):
def __init__(self, units, **kwargs):
super(CustomDense, self).__init__(units, **kwargs)
def call(self, inputs):
output = K.dot(inputs, K.softmax(self.kernel, axis=-1))
if self.use_bias:
output = K.bias_add(output, self.bias, data_format='channels_last')
if self.activation is not None:
output = self.activation(output)
return output
Test to make sure it works:
model = Sequential()
model.add(CustomDense(2, use_bias=False, input_shape=(3,)))
model.compile(loss='mse', optimizer='adam')
import numpy as np
w = np.array([[2,3], [3,1], [1,-1]])
inp = np.array([[2,1,3]])
model.layers[0].set_weights([w])
print(model.predict(inp))
# output
[[4.0610714 1.9389288]]
Verify it using numpy:
soft_w = np.exp(w) / np.sum(np.exp(w), axis=-1, keepdims=True)
print(np.dot(inp, soft_w))
[[4.06107115 1.93892885]]
answered Nov 13 '18 at 10:58
todaytoday
10.6k21636
add a comment |
1
1
1
One way to achieve what you are looking for is to define a custom layer by subclassing the Dense layer and overriding its call method:
from keras import backend as K
class CustomDense(Dense):
def __init__(self, units, **kwargs):
super(CustomDense, self).__init__(units, **kwargs)
def call(self, inputs):
output = K.dot(inputs, K.softmax(self.kernel, axis=-1))
if self.use_bias:
output = K.bias_add(output, self.bias, data_format='channels_last')
if self.activation is not None:
output = self.activation(output)
return output
Test to make sure it works:
model = Sequential()
model.add(CustomDense(2, use_bias=False, input_shape=(3,)))
model.compile(loss='mse', optimizer='adam')
import numpy as np
w = np.array([[2,3], [3,1], [1,-1]])
inp = np.array([[2,1,3]])
model.layers[0].set_weights([w])
print(model.predict(inp))
# output
[[4.0610714 1.9389288]]
Verify it using numpy:
soft_w = np.exp(w) / np.sum(np.exp(w), axis=-1, keepdims=True)
print(np.dot(inp, soft_w))
[[4.06107115 1.93892885]]
answered Nov 13 '18 at 10:58
todaytoday
10.6k21636
One way to achieve what you are looking for is to define a custom layer by subclassing the Dense layer and overriding its call method:
from keras import backend as K
class CustomDense(Dense):
def __init__(self, units, **kwargs):
super(CustomDense, self).__init__(units, **kwargs)
def call(self, inputs):
output = K.dot(inputs, K.softmax(self.kernel, axis=-1))
if self.use_bias:
output = K.bias_add(output, self.bias, data_format='channels_last')
if self.activation is not None:
output = self.activation(output)
return output
Test to make sure it works:
model = Sequential()
model.add(CustomDense(2, use_bias=False, input_shape=(3,)))
model.compile(loss='mse', optimizer='adam')
import numpy as np
w = np.array([[2,3], [3,1], [1,-1]])
inp = np.array([[2,1,3]])
model.layers[0].set_weights([w])
print(model.predict(inp))
# output
[[4.0610714 1.9389288]]
Verify it using numpy:
soft_w = np.exp(w) / np.sum(np.exp(w), axis=-1, keepdims=True)
print(np.dot(inp, soft_w))
[[4.06107115 1.93892885]]
answered Nov 13 '18 at 10:58
todaytoday
10.6k21636
answered Nov 13 '18 at 10:58
todaytoday
10.6k21636
answered Nov 13 '18 at 10:58
todaytoday
10.6k21636
answered Nov 13 '18 at 10:58
todaytoday
10.6k21636
10.6k21636
add a comment |
add a comment |
draft saved
draft discarded
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.
draft saved
draft discarded
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%2f53273456%2fin-keras-how-to-apply-softmax-function-on-each-row-of-the-weight-matrix%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
You mean you want the softmax to be applied on the weights of Dense layer and not on its output, right?
– today
Nov 13 '18 at 7:29
@today Yes, exactly.
– zxcv
Nov 13 '18 at 9:59