Friday, January 12, 2018

Keras Neural Networks and Fabrik

A screenshot of Fabrik

I tried to import several keras neural networks  to Fabrik, and this is the result:
These are the models I successfully imported:
Model LinkFabrik Link
https://github.com/anantzoid/VQA-Keras-Visual-Question-Answeringhttp://fabrik.cloudcv.org/caffe/load?id=20180105045732jmyeu
https://github.com/LemonATsu/Keras-Image-Caption
http://kodu.ut.ee/~leopoldp/2016_DeepYeast/code/caffe_model/http://fabrik.cloudcv.org/caffe/load?id=20180102135425bzkzy

And these are some models I had troubles with:
Model LinkSuccessfully Generated the JSON Model?ProblemError Message
https://github.com/ykamikawa/SegNetYesError when importingValueError: Unknown layer: MaxPoolingWithArgmax2D
https://github.com/zhixuhao/unetYesError when exporting ValueError: `Concatenate` layer requires inputs with matching shapes except for the concat axis. Got inputs shapes: [(None, 64, 64, 512), (None, 63, 63, 512)]
https://github.com/yihui-he/u-netYesError when exportingValueError: `Concatenate` layer requires inputs with matching shapes except for the concat axis. Got inputs shapes: [(None, -1, 19, 256), (None, 0, 20, 256)]
https://github.com/aitorzip/Keras-ICNetYesError when importing
ValueError: bad marshal data (unknown type code)
https://github.com/preddy5/segnetYesError when importingCannot import layer of Layer type
https://github.com/k3nt0w/FCN_via_keras/NoValueError: The input must have 3 channels; got `input_shape=(3, 224, 224)`
https://github.com/0bserver07/Keras-SegNet-BasicNo
ValueError: total size of new array must be unchanged

5 comments:

  1. Master in Machine Learning workshop, Artificial Intelligence workshop and Big Data workshop as part of the AI and Deep Learning training. machine learning certification

    ReplyDelete
    Replies
    1. Keras is a high-level neural networks API written in Python and capable of running on top of TensorFlow, Microsoft Cognitive Toolkit, Theano, or PlaidML. It allows for easy and fast prototyping, supports both convolutional networks and recurrent networks, and can run seamlessly on both CPU and GPU.

      Deep Learning Projects for Final Year Students

      Delete
  2. After I read and listened to the discussion of the article that you made, I found a lot of interesting information that I just found out.
    경마
    토토

    ReplyDelete
  3. Great article. I’m dealing with a few of these issues as well..파워볼게임

    ReplyDelete
  4. great to be here in your article or post, whatever, I figure I ought to likewise buckle down for my own site like I see some great and refreshed working in your site. 카지노사이트

    ReplyDelete

Simple Image Classification with Keras

Keras logo There are several kind of image classification: Binary classification Multiclass classification Multi label classificat...