import chainer import chainer.functions as F import chainer.optimizers as Opt import numpy from glob import iglob import cv2

model definition

layers

enc_layer = [ F.Linear(10000, 2000), F.Linear(2000, 300), F.Linear(300, 100), ]

dec_layer = [ F.Linear(100, 300), F.Linear(300, 2000), F.Linear(2000, 10000) ]

model = chainer.FunctionSet( enc1=enc_layer[0], enc2=enc_layer[1], enc3=enc_layer[2], dec1=dec_layer[0], dec2=dec_layer[1], dec3=dec_layer[2], ).to_gpu()

layerwise = [ chainer.FunctionSet(enc=enc_layer[0], dec=dec_layer[2]).to_gpu(), chainer.FunctionSet(enc=enc_layer[1], dec=dec_layer[1]).to_gpu(), chainer.FunctionSet(enc=enc_layer[2], dec=dec_layer[0]).to_gpu(), ]

def encode(x, layer, train): if train: x = F.dropout(x, ratio=0.2)

if layer == 0:
    return x

h = F.sigmoid(enc_layer[0](x))
if layer == 1:
    return h

h = F.sigmoid(enc_layer[1](h))
if layer == 2:
    return h

h = F.sigmoid(enc_layer[2](h))
if layer == 3:
    return h

h = F.sigmoid(enc_layer[3](h))
if layer == 4:
    return h

chainer.cuda.get_device(0).use()

data に学習データを放り込む

data = numpy.array(...) N = len(data)

batchsize = 50 opt = Opt.Adam()

for epoch in range(2000): print('epoch : %d' % (epoch + 1)) with open('dae.log', mode='a') as f: f.write("\n%d " % (epoch + 1))

perm = numpy.random.permutation(N)
data = data[perm]

for l in range(1, 4):
    opt.setup(layerwise[l - 1])

    sum_err = 0.

    for i in range(0, N, batchsize):
        x_batch = chainer.cuda.cupy.asarray(data[perm[i:i + batchsize]])
        x = chainer.Variable(x_batch)
        targ = encode(x, l - 1, train=True)
        enc = encode(x, l, train=True)
        y = F.dropout(F.sigmoid(dec_layer[3 - l](enc)), train=True)

        opt.zero_grads()
        err = F.mean_squared_error(y, targ)
        err.backward()
        opt.update()

        sum_err += float(err.data) * len(x_batch)

    sum_err /= N
    print("\t%d %f" % (l, sum_err))
    with open('dae.log', mode='a') as f:
        f.write("%d %f" % (l, sum_err))

param = numpy.array(model.to_cpu().parameters)
numpy.save('dae.param.npy', param)
model.to_gpu()