-
Hello Beniz,
I keep getting linker errors when I'm trying to install:
"deepdetect/build/caffe_dd/src/caffe_dd/build/lib/libcaffe.so: undefined reference to `cudaEventRecord' "
Any idea which Makefi…
-
I created a Siamese Network for paraphrase classification. Here is my code
```
input_sentence = Input(shape=(25,))
input_a = Input(shape=(25,))
input_b = Input(shape=(25,))
input_embedding…
-
Hi Nick,
get_bach function in 06_siamese_similarity_driver.ipynb generates data with targets -1 or 1, however the loss function in siamese_similarity_model.py seems to be configured to work with tar…
-
The finetuned CNN is a Siamese network which usually has two branches. However, I found each of the fine-tuned models you provided has one branch. Is this because the training samples are tuples cons…
-
I am using the mnist_siamese_graph.py as an example for my own data, but the loss (below) in each epoch was not decreased. My data is different from the data being used in the mnist_siamese_graph exam…
-
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…
-
Updated theano and keras to latest version from github. Running python mnist_siamese_graph.py gives following error:
Traceback (most recent call last):
File "mnist_siamese_graph.py", line 111, in
…
xpact updated
7 years ago
-
Hi,
I was testing the graph models and could not get to run the "mnist_siamese_graph.py" file in the examples folder. I did not get the same error when I used Keras 0.3.2.
Using Theano backend.
Trac…
-
I am trying to replace the `g.fit` part in the `mnist_siamese_graph.py` example
```
g.fit({'input_a': tr_pairs[:, 0], 'input_b': tr_pairs[:, 1], 'output': tr_y},
validation_data={'input_a': te_pairs[…
-
In the `siamese_net.py` in the `contrastive_loss` function I think the definition of the loss is implemented wrong.
The output of the function is the following:
`return T.mean(y * d + (1.0 - y) * …