aonotas / deep-crf

An implementation of Conditional Random Fields (CRFs) with Deep Learning Method

Home Page:http://deep-crf.com

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Will it support Chainer v3.0.0?

massongit opened this issue · comments

I plan to use it for fine-tuning. However, L.NStepBiLSTM can be fine-tuning only in Chainer v 3.0.0 or later. This is because __init__ function of neural networks for fine tuning must have two parameters initialW and initial_bias. So I would like to ask if it supports Chainer v 3.0.0.

I'm sorry for the late reply.

L.NStepBiLSTM can be fine-tuning only in Chainer v 3.0.0 or later.

I think v 2.00 can also fine-tuning.

# load model
serializers.load_hdf5(model_filename, net)

# re-train (fine-tuning)

Anyway, I will modify deep-crf to support Chainer v3.

Thank you for your reply.
I would like to think about the experimental method based on your advice.