-
We should add support for various memory modules:
MERLIN - buffer of memory encodings through predictive coding and retroactive updating
(https://arxiv.org/pdf/1803.10760.pdf)
SPTM - topological m…
-
The goal is to implement data-parallel multi-GPU training with gradient-averaging properly in Keras (at least explicitly for TensorFlow backend).
In this issue I'd like to discuss a particular appr…
-
New books Keras neural network works like so:
* Train on all books x books, simply to learn the "cosine similarity" function in general
* Fine-tune per user: take all books which have been scored, a…
-
I was experimenting with a few variants of BERT to test for semantics. However, they are what they were trained on. So, I was wondering if these transformers work on training on short phrases (like ke…
-
I am trying to use your example_mnist_siamese code. I have my own data where `x_train.shape = (100, 3)` and `y_train.shape = (100,)`. I am having trouble defining the shape for the siamese model. For…
-
Hello.
**Intorduction:**
I am writing a neural network that analyses video. For analyzing different frames I use shared vision model (the same set of layers and weights is applied over various i…
-
Hello,
I'm trying to create a PairData class. I overrided the constructor and the ```__inc__``` function as mentioned by the document. Here is my toy test code:
```Python
"""
Dataloader for t…
-
Actually I am trying to predict the similarity between two images based on the predicted feature vector.
Was trying to change the final layer head with distance ie distance = Lambda(self.euclidean_di…
-
Hello @bamos, how are you?
Congratulations on the project.
I wonder if you have plans to implement the detection of people still untrained and display as unknown.
I would like to collaborate with th…
-
I tried writing a custom layer for the [Caffe Absolute Value Layer](http://caffe.berkeleyvision.org/tutorial/layers/absval.html). As per your [IDZ post](https://software.intel.com/en-us/forums/compute…