fold

fold copied to clipboard

As the title suggest, could anyone help me figure out how to call 2 or more gpus in Fold?

penelope24

About the support for tensorflow 1.2.1

1

um...As I found in the previous issue, the fold does not support for tensorflow v1.2 right now. So I'd like to know when will it be v1.2 supported? I've tried...

penelope24

Hello, during installation of tensorflow/fold I noticed that in > For Python 3.3+ and/or GPU, see [here](https://www.tensorflow.org/versions/r1.0/get_started/os_setup#using_pip) for the full list of available TF binaries. the link doesn't work anymore....

EgorBu

GPU memory growth failed

1

Hi, i use [Allowing GPU memory growth](https://www.tensorflow.org/tutorials/using_gpu#allowing-gpu-memory-growth) like followings which worked well in tensorflow: ``` config = tf.ConfigProto() config.gpu_options.allow_growth = True session = tf.Session(config=config, ...) ``` But it still occupies...

tadpole

I tried to run the example script in sentiment.ipynb and quick.ipynb, but every time I run to the function "td.Compiler.create()", the jupyter notebook crashed down, said "kernel restarted". What is...

penelope24

Suppose that I have an input like this ["string1,"string2","string3]. Then I want to produce a block with produce tuple type, for example :` (array([-5., 4.], dtype=float32), array([ 5., 5.], dtype=float32),array([-5.,...

bdqnghi

Hi, I am working with tensor flow fold tree LSTM code. Before applying tree LSTM I'm doing some preprocessing on the sentence in tensorflow. To be concrete through preprocessing I'm...

abhinavg4

Fold not loading after custom compilation

2

I have succesfully compiled tensorflow r1.1 and fold in my linux machine with gcc-4.9 but python is not able to load tensorflow: ``` >>> import tensorflow_fold as fd 2017-05-29 11:40:45.075279:...

rcilla

Implementation for graph convolution neural networks

3

Hi, I would like to ask if there is an existing source code for the implementation of graph convolution neural networks.

bdqnghi

I am developing a NN for analysis for around 100000 sequences and am getting the following error raise type(e)(node_def, op, message) InvalidArgumentError: Input 0 of node Adam/update_Variable_67/ApplyAdam was passed float...

akigmm