-
@fmassa @apaszke and I started working on a FFI based functional lua-free C-backend for torch/nn. The development takes place in [this fork](https://github.com/fmassa/nn/tree/THNN) in the THNN branch,…
-
Hi, I meet error when running the demo.
Traceback (most recent call last):
File "faster_rcnn/demo.py", line 12, in
from lib.networks.factory import get_network
File "/home/dyc/workspace/T…
-
Hello, I have some question about the formula in your program
**Dense Tensor Layer: f_i = a( xV_ix^T + W_ix^T + b_i)**
Your formula is different of socher's, What is x represent for in above fo…
-
Hi all,
thanks again for releasing this very powerful toolkit. I read the doc and run the MNIST example. In this example the "mnist_convert.py" resizes the 2d digit images in a feature vector of lengt…
-
### What?
Over the weekend I worked on a solution to design arbitrary RNNs using Keras API. The result allow us write a vanilla RNN as:
``` python
self.input_dim = 2
self.state_dim = 2
self.model =…
-
In image segmentation, if one image has N pixpels, the number of labels is also N(not one), so the Softmax operator in mxnet can't handle it(just my opinion);
I want solve it through:
1. add a new…
-
[**TL;DR:** We're designing a new input pipeline API for TensorFlow, and we'd like to collect your feature requests on this issue.]
We've noticed that one of the biggest challenges in getting start…
-
Hi!,
I'm really interested on contribute in my spare time on this project, it would be great for me port the Python libraries to Go, or help with this task, the problem is that after read the "Contri…
-
Here are the key features that we will have in Keras by the time it hits v1.0.
- Visualization tools, possibly built on top of Bokeh. You should be able to see everything that's going on in your expe…
-
I'm using ghc 8.0.1, maybe something has changed?
I'm quite interested in the idea of using category-syntax for defining neural networks, which would seem like a natural fit - it's a toss up between …