Bing Xu

For kaggle bowl example, I made it long ago so I am not sure whether it is capable for new version. There is a nicer config at https://github.com/auroraxie/Kaggle-NDSB

Currently conf file / string is only way to define network

I think a quick fix is using an extra python script to convert xavier/kaiming to normal gaussin/uniform conf file.

Sample usage: https://github.com/dmlc/mxnet/blob/master/example/notebooks/predict-with-pretrained-model.ipynb

You need to modify the code: 1. if you have fullc in your net, add a reshape layer to reshape it back to [batch, channel, x, y] 2. modify the...

The model is converted from TensorFlow model. Note preprocessing code is different, see preprocessing.py in the zip. Also 1008 is from Google, and 1-1000 is ILVRC2012 label.

I am not sure what is your problem, but on my side it works well, and I verified on ILSVRC 2012 validation set and TensorFlow sample image.

First, resize the raw image into 384, then you can do in this way (code I used a month ago) ``` import mxnet as mx import numpy as np val...

The synset is correct. Again, in Google's released model, there is only 1008 outputs. There is a mapping in old synset and new synset, which I have provided code above....

You can find old_synset.txt in old Inception-BN model. On Thu, Jan 14, 2016 at 4:07 PM, Shuo Zhang [email protected] wrote: > The question is where can we find the old_synset.txt?...