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

1 comment:

  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

Simple Image Classification with Keras

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