-
I'm finding the TensorGraph API kind of cumbersome to work with. This is mainly because you have to call `add_layer()` for every layer, which forces you to create a variable for every layer. For exa…
-
Hi,
I am not sure if this is a bug in some TF function or Keras has just some clever ways to pull things off.
I was prototyping a simple logistic regression model with Keras and trying to write the …
-
Hi,
I saw the example code of using LSTM cells in TFLearn, classifying mnist images.
I want to classify an image sequence. I'm not sure though how to achieve this in TFLearn, but I thought maybe to g…
-
For example,
How to concatenate image embedding and word embeddings together as one sequence which is then fed to LSTM just like what is done in Google's image caption generation paper http://arxiv.or…
-
I am working on windows 10, Python 3.6 and tensorflow 1.4.0. I tested the code on two laptops, one with gpu and another without, both of them had this problem.
This is my code:
`def network(self…
-
### System information
- **Have I written custom code (as opposed to using a stock example script provided in TensorFlow)**: Yes
- **OS Platform and Distribution (e.g., Linux Ubuntu 16.04)**: Ubuntu…
footh updated
6 years ago
-
We complete the most jobs for fluid release, but still there are several tasks remains.
[tasks.dot.txt](https://github.com/PaddlePaddle/Paddle/files/1494524/tasks.dot.txt)
:
img = Image.open(dataset_p…
-
Currently, seq2seq decoder class only supports classification which uses 1D softmax with embedding. The library is very good for this particular task. However, seq2seq is also extremely useful in regr…
-
Hello,
There is an old PR #1112 for clockwork RNN implementation in Keras, but I am not able to find in it current version of Keras. Can anyone point me in right direction?
thanks