unable to add layer in keras

Question

I am trying to following this suggestion.

outputs = Conv2DTranspose(3, (1, 1), activation='sigmoid') (c9)
model = Model(inputs=[inputs], outputs=[outputs])
model = multi_gpu_model(model, gpus=8)
model.compile(optimizer='adam', loss = bce, metrics = [mean_iou])
model.add(Lambda(lambda x: K.batch_flatten(x)))

But at that last line of code, I receive the following error:

'Model' object has no attribute 'add'

I understand that since I didn't instantiate model as sequential() as in linked post, the function add() might not be available to me. However, I'm not sure how to work around this.

Is there something wrong if you add the Lambda layer after the Conv2DTranspose layer, i.e. `outputs = Lambda(lambda x: K.batch_flatten(x))(outputs)`? — today, Jul 09 '18 at 21:45

swiftg · Answer 1 · 2018-07-10T00:33:24.527

1

Corrected to reflect the working solution:

outputs = Conv2DTranspose(3, (1, 1), activation='sigmoid') (c9)
outputs = Lambda(lambda x: K.batch_flatten(x))(outputs)
model = Model(inputs=[inputs], outputs=[outputs])
model = multi_gpu_model(model, gpus=8)
model.compile(optimizer='adam', loss = bce, metrics = [mean_iou])

edited Jul 10 '18 at 00:33

answered Jul 09 '18 at 21:47

swiftg

346
1
9

IN that situation, I got this error: `Output tensors to a Model must be the output of a TensorFlow Layer (thus holding past layer metadata). Found: ` – Jonathan Jul 09 '18 at 21:59

score 0 · Accepted Answer · answered Aug 10 '18 at 20:01

0

Going off @Today's answer in the OP's comments,

outputs = Lambda(lambda x: K.batch_flatten(x))(outputs)

answered Aug 10 '18 at 20:01

Jonathan

1,876
2
20
56

unable to add layer in keras

2 Answers2