Styjun

Make all the squares explode

Was there a contingency plan in place if Little Boy failed to detonate?

Drawing perpendicular lines, filling areas

Why can't RGB or bicolour LEDs produce a decent yellow?

On what legal basis did the UK remove the 'European Union' from its passport?

Cropping a message using array splits

Noob at soldering, can anyone explain why my circuit won't work?

As programers say: Strive to be lazy

Can 'sudo apt-get remove [write]' destroy my Ubuntu?

Delta TSA-Precheck status removed

Pre-1993 comic in which Wolverine's claws were turned to rubber?

Is the schwa sound consistent?

Is there any evidence to support the claim that the United States was "suckered into WW1" by Zionists, made by Benjamin Freedman in his 1961 speech?

LocalDate.plus Incorrect Answer

Two researchers want to work on the same extension to my paper. Who to help?

What's the best way to update Homebrew when upgrading macOS?

"Right on the tip of my tongue" meaning?

Remove everything except csv file Bash Script

The lexical root of the perfect tense forms differs from the lexical root of the infinitive form

To what extent may I customize a demiplane?

Ex-manager wants to stay in touch, I don't want to

How did Thanos not realise this had happened at the end of Endgame?

Exception propagation: When to catch exceptions?

Is a vertical stabiliser needed for straight line flight in a glider?

Keras ConvLSTM2D: why use the averagepooling3d and how to to regression

Keras ConvLSTM2D: ValueError on output layerHow to merge two dictionaries in a single expression?How do I check if a list is empty?How do I check whether a file exists without exceptions?How can I safely create a nested directory in Python?How do I sort a dictionary by value?How to make a chain of function decorators?How to make a flat list out of list of listsHow do I list all files of a directory?How to configure a very simple LSTM with Keras / Theano for RegressionKeras ConvLSTM2D: ValueError on output layer

.everyoneloves__top-leaderboard:empty,.everyoneloves__mid-leaderboard:empty,.everyoneloves__bot-mid-leaderboard:empty height:90px;width:728px;box-sizing:border-box;

0

i have been studying Keras ConvLSTM2D: ValueError on output layer

i want to use the same code but i want to do regression ( single value ).
I dont know how to do this. And i also dont understand the use of last layers of this post code. Why is averagepolling3d used?

the code from link is

model = Sequential()

model.add(ConvLSTM2D(
 filters=40,
 kernel_size=(3, 3),
 input_shape=(None, 135, 240, 1),
 padding='same',
 return_sequences=True))
model.add(BatchNormalization())

model.add(ConvLSTM2D(
 filters=40,
 kernel_size=(3, 3),
 padding='same',
 return_sequences=True))
model.add(BatchNormalization())

model.add(ConvLSTM2D(
 filters=40,
 kernel_size=(3, 3),
 padding='same',
 return_sequences=True))
model.add(BatchNormalization())

model.add(AveragePooling3D((1, 135, 240)))
model.add(Reshape((-1, 40)))
model.add(Dense(
 units=9,
 activation='sigmoid'))

model.compile(
 loss='categorical_crossentropy',
 optimizer='adadelta'
)

python keras regression lstm

share|improve this question

asked Mar 23 at 10:55

sotirawsotiraw

63

add a comment | 

0

i have been studying Keras ConvLSTM2D: ValueError on output layer

i want to use the same code but i want to do regression ( single value ).
I dont know how to do this. And i also dont understand the use of last layers of this post code. Why is averagepolling3d used?

the code from link is

model = Sequential()

model.add(ConvLSTM2D(
 filters=40,
 kernel_size=(3, 3),
 input_shape=(None, 135, 240, 1),
 padding='same',
 return_sequences=True))
model.add(BatchNormalization())

model.add(ConvLSTM2D(
 filters=40,
 kernel_size=(3, 3),
 padding='same',
 return_sequences=True))
model.add(BatchNormalization())

model.add(ConvLSTM2D(
 filters=40,
 kernel_size=(3, 3),
 padding='same',
 return_sequences=True))
model.add(BatchNormalization())

model.add(AveragePooling3D((1, 135, 240)))
model.add(Reshape((-1, 40)))
model.add(Dense(
 units=9,
 activation='sigmoid'))

model.compile(
 loss='categorical_crossentropy',
 optimizer='adadelta'
)

python keras regression lstm

share|improve this question

asked Mar 23 at 10:55

sotirawsotiraw

63

add a comment | 

i have been studying Keras ConvLSTM2D: ValueError on output layer

i want to use the same code but i want to do regression ( single value ).
I dont know how to do this. And i also dont understand the use of last layers of this post code. Why is averagepolling3d used?

the code from link is

model = Sequential()

model.add(ConvLSTM2D(
 filters=40,
 kernel_size=(3, 3),
 input_shape=(None, 135, 240, 1),
 padding='same',
 return_sequences=True))
model.add(BatchNormalization())

model.add(ConvLSTM2D(
 filters=40,
 kernel_size=(3, 3),
 padding='same',
 return_sequences=True))
model.add(BatchNormalization())

model.add(ConvLSTM2D(
 filters=40,
 kernel_size=(3, 3),
 padding='same',
 return_sequences=True))
model.add(BatchNormalization())

model.add(AveragePooling3D((1, 135, 240)))
model.add(Reshape((-1, 40)))
model.add(Dense(
 units=9,
 activation='sigmoid'))

model.compile(
 loss='categorical_crossentropy',
 optimizer='adadelta'
)

python keras regression lstm

share|improve this question

asked Mar 23 at 10:55

sotirawsotiraw

63

model = Sequential()

model.add(ConvLSTM2D(
 filters=40,
 kernel_size=(3, 3),
 input_shape=(None, 135, 240, 1),
 padding='same',
 return_sequences=True))
model.add(BatchNormalization())

model.add(ConvLSTM2D(
 filters=40,
 kernel_size=(3, 3),
 padding='same',
 return_sequences=True))
model.add(BatchNormalization())

model.add(ConvLSTM2D(
 filters=40,
 kernel_size=(3, 3),
 padding='same',
 return_sequences=True))
model.add(BatchNormalization())

model.add(AveragePooling3D((1, 135, 240)))
model.add(Reshape((-1, 40)))
model.add(Dense(
 units=9,
 activation='sigmoid'))

model.compile(
 loss='categorical_crossentropy',
 optimizer='adadelta'
)

share|improve this question

asked Mar 23 at 10:55

sotirawsotiraw

63

share|improve this question

asked Mar 23 at 10:55

sotirawsotiraw

63

asked Mar 23 at 10:55

sotirawsotiraw

63

asked Mar 23 at 10:55

sotirawsotiraw

63