JA

Released Neural Network Libraries v.1.0.16! New Pre-Trained Model and New Solvers are Now Available!

Friday, April 19, 2019

News , Release

Posted by Takuya Yashima

We have released Neural Network Libraries v.1.0.16!
Added InceptionV3 Model and AdaBound/AMSBound!

Spotlight

AdaBound & AMSBound

AdaBound optimizer applies dynamic bounds on learning rates of Adam, and AMSBound does the same to AMSGrad.

See this paper for more details!

import nnabla.solvers as S
solver = S.AdaBound(lr=1e-3)
solver.set_parameters(nn.get_parameters())

for itr in range(num_itr):
    x.d = ... # set data
    t.d = ... # set label
    loss.forward()
    solver.zero_grad()  # All gradient buffer being 0
    loss.backward()
    solver.weight_decay(decay_rate)  # Apply weight decay
    solver.update()  # updating parameters

New Model:

See this paper for details.

Functions

Utilities

Format Converter

Build

Bug Fix