-
Got a prelim SWWAE going in the most recent release (1.0.1), but facing a few issues.
Paper: http://arxiv.org/abs/1506.02351
The biggest one has to do with what we do when our cost function has co…
-
Hello,
I am new to Theano and Keras so maybe I am asking something silly but have been a few days trying to get this working and I can not.
I want to build a siamese architecture that takes 2 vector…
-
I'm using a siamese network with three different outputs.
Two of them are the classification and the other is an additional label I use.
The question is, how the loss given in the callback is comput…
-
dear @layumi
when i train the siamese net, the loss of verification shakes widly. and it is down in a very difficult way to understand.
(1)how about you view of the change(down) of the verific…
-
Hi,
I am trying to efficiently implement a Siamese network (http://yann.lecun.com/exdb/publis/pdf/chopra-05.pdf) in CNTK. The network learns a projection that maps the input samples into a d-dimensi…
-
Hi,
I have two questions related to the input requirements for RNN layer.
1.) Is it possible to provide two separate inputs (not merged) to RNN layer so that both inputs have its individual weight m…
-
Hi, I'm trying to train this Siamese architecture (referenced here https://github.com/fchollet/keras/issues/242#issuecomment-122418675 )
```
leg = Sequential()
leg.add(Dense(128, input_dim=400, init=…
-
I am using the following layers for training:
seq = Sequential()
seq.add(Embedding(100000, 32, input_length=input_dim))
seq.add(Dropout(0.1))
seq.add(LSTM(64))
seq.ad…
-
Great library!
The implementation for RandomPairSampler is missing from utils/data/sampler.py. Will it be implemented any time soon? It sounds like something useful for loading input data for a verif…
-
The siamese network example for mnist (https://github.com/fchollet/keras/blob/master/examples/mnist_siamese_graph.py) uses the following function to compute accuracy
```
def compute_accuracy(predi…