python (12.9k questions)

javascript (9.2k questions)

reactjs (4.7k questions)

java (4.2k questions)

java (4.2k questions)

c# (3.5k questions)

c# (3.5k questions)

html (3.3k questions)

Questions - tensorflow2.0

Tensorflow: Incompatible shapes: [1,2] vs. [1,4,4,2048]

I have the following tensorflow model: img_width, img_height = 120, 120 dg = DataGenerator('/mnt/e/Shared/Stfc/Images', target_size=(img_height, img_width), batch_size=1) input_tensor = tf.keras.Inp...
test-img

Ian Newson

python

python-3.x

tensorflow

keras

tensorflow2.0

Votes: 0

Answers: 1

Latest Answer

The ResNet50 model outputs a tensor with the shape (4,4,2048) and you are expecting a shape of (2,), so you will definitely have to reduce the size of that tensor by applying further dense layers. Her...
test-img

AloneTogether

Does tensorflow re-initialize weights when training in a for loop?

I'm training a model within a for loop, because...I can. I know there are alternative like tf.Dataset API with generators to stream data from disk, but my question is on the specific case of a loop. D...
test-img

Yoan B. M.Sc

python

tensorflow

deep-learning

tensorflow2.0

Votes: 0

Answers: 1

Latest Answer

Weights are initialized when the layers are defined (before fit). It does not re-initialize weights afterward - even if you call fit multiple times. To show this is the case, I plotted the decision bo...
test-img

Galletti_Lance

ValueError: Can not squeeze dim[1], expected a dimension of 1 for '{{node binary_crossentropy/weighted_loss/Squeeze}}

I'm trying to fit a LSTM-model to my data with a Masking Layer in front and I get this error: ValueError: Can not squeeze dim[1], expected a dimension of 1, got 4 for '{{node binary_crossentropy/weigh...
test-img

Tobias Braun

python

tensorflow

keras

lstm

tensorflow2.0

Votes: 0

Answers: 1

Latest Answer

I don't think the problem is the Masking layer. Since you set the parameter return_sequences to True in the LSTM layer, you are getting a sequence with the same number of time steps as your input and ...
test-img

AloneTogether

Precison issue with sigmoid activation function for Tensorflow/Keras 2.3.1

Assuming the following forward pass in a classic ANN (Based on https://mattmazur.com/2015/03/17/a-step-by-step-backpropagation-example/): Now let's use a sigmoid activation on that, I get: So...
test-img

Greg7000

neural-network

tensorflow2.0

tf.keras

Votes: 0

Answers: 1

Latest Answer

Tensorflow perform the Dense layer row to column: It multiplies each row of your input with a column in the weights matrix, You need to transpose your weights matrix, if you do it you will get the cor...
test-img

JumbaMumba

Posts

Questions

Blogs

Jobs