Where communities thrive


  • Join over 1.5M+ people
  • Join over 100K+ communities
  • Free without limits
  • Create your own community
People
Repo info
Activity
    Ashwin Jeyaseelan
    @8Gitbrix
    in the python api, whats the difference between sym and symbol?
    Jiajia Geng
    @saicoco
    sym ==symbol
    I think, there are many abbreviation for short, like mx.module==mx.mod, mx.monitor==mx.mon,mx.ndarray==mx.nd,mx.visualization==mx.vis .etc
    Chih-Wei (Bert) Chang
    @lazywei
    is anyone familiar with seq2seq? Is there any ready-to-use seq2seq model in MXNET?
    Huiting Liu
    @HuitingLiu
    Does mxnet have something like feed_previous argument for seq2seq in Tensorflow? If setting feed_previous to False. This means that the decoder will use decoder_inputs tensors as provided. If setting feed_previous to True, the decoder would only use the first element of decoder_inputs.
    I have looked at several examples in MXNet. Many of them only have the training part and leave the predicting part empty because there is not real data for the decoder in the predicting process. So after training the model, users don't know how to use it.
    Ashwin Jeyaseelan
    @8Gitbrix
    I'm having trouble finding the number of epochs I need in my model fit method, could someone check my error?
    Ben Hutchison
    @benhutchison

    Hi all, Im new to mxnet.

    Im trying to understand the autoencoder example. There is no documentation.

    While I have got it running on a p2.xlarge using the AWS deep learning AMI, there are many things I dont understand, eg

    1. How many layers and how many hidden units does it use?
    2. How can I interpret or visualize the results?
    mike0331123
    @mike03311231_twitter
    Hi,
    Is there any example about Visualizing and understanding convolutional networks (Zeiler, 2014)?
    abner2015
    @abner2015
    when i run "python demo.py" after install rcnn ,i get the error: Traceback (most recent call last):
    File "demo.py", line 141, in <module>
    main()
    File "demo.py", line 135, in main
    symbol = get_vgg_test(num_classes=config.NUM_CLASSES, num_anchors=config.NUM_ANCHORS)
    File "/home/zhixian/new/software/mxnet/example/rcnn/rcnn/symbol/symbol_vgg.py", line 276, in get_vgg_test
    rois = mx.symbol.Proposal(
    AttributeError: 'module' object has no attribute 'Proposal'
    how can i solve it
    Ashwin Jeyaseelan
    @8Gitbrix
    does anyone know how to plot the AUC score?
    Ashwin Jeyaseelan
    @8Gitbrix
    When i try to use AUC metric on binary classification I get an error
    For auc metric I get: ValueError: Only one class present in y_true. ROC AUC score is not defined in that case.
    When i try auc I get: ValueError: Reordering is not turned on, and the x array is not increasing:
    What am I doing wrong?
    Ashwin Jeyaseelan
    @8Gitbrix
    In MXNet, in model.fit, is X = no longer a parameter?
    abner2015
    @abner2015
    2017-03-14 11:27:24屏幕截图.png
    when i run "python test.py --gpu 0 " in "mxnet\example\rcnn\"dir i get the error
    anyone know the reason?
    abner2015
    @abner2015
    why no one to answer the question
    The problem has been solved
    Qiyuan Gong
    @qiyuangong

    @Techro-Raj

    def fit(self, X, y=None, eval_data=None, eval_metric='acc', epoch_end_callback=None, batch_end_callback=None, kvstore='local', logger=None, work_load_list=None, monitor=None, eval_end_callback=LogValidationMetricsCallback(), eval_batch_end_callback=None)

    So, do not add x=, use X=.

    Ashwin Jeyaseelan
    @8Gitbrix
    thanks, i solved all my problems. I actually didn't need the X=
    cpchung
    @chakpongchung
    hi all! what is the python wrapper for mxnet?
    boost.python? swig? or what?
    hello~~~~
    skywalkerytx
    @skywalkerytx
    why in maven central there is only cpu version that supports scala 2.11? can't see things like mxnet-full_2.11-linux-x86_64-gpu
    Christian Dietz
    @dietzc
    Hi all, quick question (sorry, if you've heard this thousand times before, couldn't find an answer out there though): Is there a way to execute/convert trained keras models via/to mxnet model format?
    King of Oz
    @kingofoz
    hello
    is code available for the paper of Semantic Segmentation using Adversarial Networks ?
    kbrown42
    @kbrown42
    Hi everyone. Does anybody know if the output_mean_var parameter for BatchNorm is currently working in python mxnet? Also, are auxiliary state values accessible?
    Jordan Green
    @jordan-green
    Hey guys, I've built mxnet with the C++ package and op.h has not been generated
    any ideas why that might be?
    on ubuntu 16.04
    chenjunweii
    @chenjunweii
    do you set USE_CPP_PACKAGE = 1 ? and what's your python version
    Jordan Green
    @jordan-green
    I did use the cpp flag
    python version 2.7
    ruhshan
    @Ruhshan
    Hello people. Is this a good place to talk about a problem I'm facing to learn mxnet ?
    Xin Li
    @lx75249
    @jordan-green which build system did you use? makefile or cmake?
    Jordan Green
    @jordan-green
    @lx75249 I used cmake
    Jordan Green
    @jordan-green
    ah! when using make, it works! Thanks @lx75249 , silly me! If I think of why cmake may fail, I'll ammend and PR :)
    Hanns Holger Rutz
    @Sciss
    Hey there... I'm trying to understand which are my best options implementing something like WaveNet in Scala. So I found MxNet. The main problem I have is my Python is weak, and I don't know Tensorflow, Keras, or Torch. I'm fairly versed in signal processing, though. I would need to understand how to implement something like dilated convolution layers (https://github.com/ibab/tensorflow-wavenet/blob/12dc5df26b79c8b5ddaf608138129b328c12ded7/wavenet/model.py). Thanks for any comments.
    I'm using a laptop with Core i7 quad, unfortunately no Nvidia, so needs to run on CPU, as parallelised as possible. Tensorflow implementation is extremely slow on this machine, making one epoch every half minute. I want to change the input signal model, and I hope I can speed things up somewhere by a magnitude.
    Lambda Developer
    @chetkhatri
    Hello All, What is equivalent github path for http://mxnet.io/api/scala/index.html documentation
    Lambda Developer
    @chetkhatri
    Chihiro Shimamura
    @chicn
    Hi all. I just posted a question about here -> dmlc/mxnet#6268.
    Hope any of you may have faced same problem and know how to solve it! Any suggestion is welcomed!!
    Dominic Bou-Samra
    @dbousamra
    I'm trying to use the Scala jars provided by mvnrepository with CUDA 8.0. Are they statically linked against 7.0, because I receive errors when it tries to look for 7.0
    abdul dakkak
    @abduld
    Is there an api function to programmatically find a model's input dimensions for inference?