Trjtdtk

Do infinite dimensional systems make sense?

Why "Having chlorophyll without photosynthesis is actually very dangerous" and "like living with a bomb"?

How to regain access to running applications after accidentally zapping X.org?

Operational amplifier as a comparator at high frequency

Uncaught TypeError: 'set' on proxy: trap returned falsish for property Name

Can I ask the recruiters in my resume to put the reason why I am rejected?

Approximately how much travel time was saved by the opening of the Suez Canal in 1869?

What typically incentivizes a professor to change jobs to a lower ranking university?

if condition in the past

Why is 150k or 200k jobs considered good when there's 300k+ births a month?

Why do I get two different answers for this counting problem?

A case of the sniffles

Are astronomers waiting to see something in an image from a gravitational lens that they've already seen in an adjacent image?

What defenses are there against being summoned by the Gate spell?

If human space travel is limited by the G force vulnerability, is there a way to counter G forces?

Why is Minecraft giving an OpenGL error?

How much RAM could one put in a typical 80386 setup?

Mutually beneficial digestive system symbiotes

Alternative to sending password over mail?

What would happen to a modern skyscraper if it rains micro blackholes?

Replacing matching entries in one column of a file by another column from a different file

Why does Kotter return in Welcome Back Kotter?

Revoked SSL certificate

How does one intimidate enemies without having the capacity for violence?

Custom Lambda layer Keras outputs predictions. I get 'An operation has `None` for gradient' error

2

$begingroup$

I have a Lambda layer that takes input from previous layer, makes some preprocessing. Output of the Lambda layer is a prediction, and keras.losses.mean_squared_error is used.

#model
inputs = Input(shape=(len_train_data_columns,))
dense1 = Dense(777, activation='relu')(inputs)
dropout1 = Dropout(0.4)(dense1)
softmax = Dense(3, activation='softmax')(dropout1)
predictions = Lambda(custom_layer,
 output_shape= custom_layer_output_shape,
 arguments= 'experiment_config': experiment_config,
 )(softmax)

model = Model(inputs = inputs, outputs = predictions)
model.compile(optimizer=adam(lr=0.0001), loss=keras.losses.mean_squared_error, metrics=keras.losses.mean_squared_error)

Output of Lambda is (num_rows, 1).

I get ValueError: An operation has None for gradient. Please make sure that all of your ops have a gradient defined (i.e. are differentiable). Common ops without gradient: K.argmax, K.round, K.eval.

Why is that? I use Keras loss...

python keras regression loss-function

share|improve this question

asked Mar 28 at 9:58

Myron LeskivMyron Leskiv

566

$endgroup$

add a comment | 

2

$begingroup$

I have a Lambda layer that takes input from previous layer, makes some preprocessing. Output of the Lambda layer is a prediction, and keras.losses.mean_squared_error is used.

#model
inputs = Input(shape=(len_train_data_columns,))
dense1 = Dense(777, activation='relu')(inputs)
dropout1 = Dropout(0.4)(dense1)
softmax = Dense(3, activation='softmax')(dropout1)
predictions = Lambda(custom_layer,
 output_shape= custom_layer_output_shape,
 arguments= 'experiment_config': experiment_config,
 )(softmax)

model = Model(inputs = inputs, outputs = predictions)
model.compile(optimizer=adam(lr=0.0001), loss=keras.losses.mean_squared_error, metrics=keras.losses.mean_squared_error)

Output of Lambda is (num_rows, 1).

I get ValueError: An operation has None for gradient. Please make sure that all of your ops have a gradient defined (i.e. are differentiable). Common ops without gradient: K.argmax, K.round, K.eval.

Why is that? I use Keras loss...

python keras regression loss-function

share|improve this question

asked Mar 28 at 9:58

Myron LeskivMyron Leskiv

566

$endgroup$

add a comment | 

$begingroup$

I have a Lambda layer that takes input from previous layer, makes some preprocessing. Output of the Lambda layer is a prediction, and keras.losses.mean_squared_error is used.

#model
inputs = Input(shape=(len_train_data_columns,))
dense1 = Dense(777, activation='relu')(inputs)
dropout1 = Dropout(0.4)(dense1)
softmax = Dense(3, activation='softmax')(dropout1)
predictions = Lambda(custom_layer,
 output_shape= custom_layer_output_shape,
 arguments= 'experiment_config': experiment_config,
 )(softmax)

model = Model(inputs = inputs, outputs = predictions)
model.compile(optimizer=adam(lr=0.0001), loss=keras.losses.mean_squared_error, metrics=keras.losses.mean_squared_error)

Output of Lambda is (num_rows, 1).

I get ValueError: An operation has None for gradient. Please make sure that all of your ops have a gradient defined (i.e. are differentiable). Common ops without gradient: K.argmax, K.round, K.eval.

Why is that? I use Keras loss...

python keras regression loss-function

share|improve this question

asked Mar 28 at 9:58

Myron LeskivMyron Leskiv

566

$endgroup$

#model
inputs = Input(shape=(len_train_data_columns,))
dense1 = Dense(777, activation='relu')(inputs)
dropout1 = Dropout(0.4)(dense1)
softmax = Dense(3, activation='softmax')(dropout1)
predictions = Lambda(custom_layer,
 output_shape= custom_layer_output_shape,
 arguments= 'experiment_config': experiment_config,
 )(softmax)

model = Model(inputs = inputs, outputs = predictions)
model.compile(optimizer=adam(lr=0.0001), loss=keras.losses.mean_squared_error, metrics=keras.losses.mean_squared_error)

share|improve this question

asked Mar 28 at 9:58

Myron LeskivMyron Leskiv

566

share|improve this question

asked Mar 28 at 9:58

Myron LeskivMyron Leskiv

566

asked Mar 28 at 9:58

Myron LeskivMyron Leskiv

566

asked Mar 28 at 9:58

Myron LeskivMyron Leskiv

566