def make_network(minibatch_size = 128):
pre_net = load_network("rand.data")
inp = pre_net.outputs[-1]
visitor = NetworkVisitor(inp).all_oprs
for i in visitor:
#if isinstance(i, BN):
# i.set_freezed()
if isinstance(i, ParamProvider):
i.set_freezed()
if isinstance(i, DataProvider):
dp = i
lay = O.ZeroGrad(inp)
chl = inp.partial_shape[1]
p = []
num_blocks = 1
for tt in range(num_blocks):
for j in range(2):
lay = deconv_bn_relu("encoder_deconv_{}{}".format(tt, j), lay, kernel_shape = 3, stride = 1, padding = 0, output_nr_channel = chl)
#lay = deconv_bn_relu("encoder_deconv_{}1".format(tt), lay, kernel_shape = 3, stride = 1, padding = 1, output_nr_channel = chl)
p.append(lay)
if tt != num_blocks:
lay = deconv_bn_relu("encoder_deconv_{}{}".format(tt, j + 1), lay, kernel_shape = 2, stride = 2, padding = 0, output_nr_channel = chl // 2)
chl = chl // 2
lay = deconv_bn_relu("outputs", lay, kernel_shape = 3, stride = 1, padding = 1, output_nr_channel = 3, isbnrelu = False)
mid = lay.partial_shape[2] // 2
lay = lay[:, :, mid-16:mid+16, mid-16:mid+16]
print(lay.partial_shape)
loss = ((lay - dp)**2).sum(axis = 3).sum(axis = 2).sum(axis = 1).mean()
network = Network(outputs = [lay, inp] + p)
network.loss_var = loss
return network
def make_network(minibatch_size = 128):
pre_net = load_network("trained.data")
inp = pre_net.outputs[-1]
visitor = NetworkVisitor(inp).all_oprs
for i in visitor:
if isinstance(i, BN):
i.set_freezed()
if isinstance(i, ParamProvider):
i.set_freezed()
if isinstance(i, DataProvider):
dp = i
lay = O.ZeroGrad(inp)
chl = inp.partial_shape[1]
p = []
for tt in range(3):
lay = deconv_bn_relu("encoder_deconv_{}0".format(tt), lay, kernel_shape = 3, stride = 1, padding = 1, output_nr_channel = chl)
lay = deconv_bn_relu("encoder_deconv_{}1".format(tt), lay, kernel_shape = 3, stride = 1, padding = 1, output_nr_channel = chl)
p.append(lay)
if tt != 2:
lay = deconv_bn_relu("encoder_deconv_{}2".format(tt), lay, kernel_shape = 2, stride = 2, padding = 0, output_nr_channel = chl // 2)
chl = chl // 2
lay = deconv_bn_relu("outputs", lay, kernel_shape = 3, stride = 1, padding = 1, output_nr_channel = 3, isbnrelu = False)
loss = ((lay - dp)**2).sum(axis = 3).sum(axis = 2).sum(axis = 1).mean()
network = Network(outputs = [lay, inp] + p)
network.loss_var = loss
return network
from megskull.network import Network
from My import MyWeightDecay
from megskull.opr.helper.elemwise_trans import ReLU, Identity
minibatch_size = 10
patch_size = 32
net_name = "test_wc"
inp = O.DataProvider("a", shape=(minibatch_size, 3))
out = O.FullyConnected("fc",
inp,
output_dim=3,
W=C(1),
nonlinearity=Identity())
W = out.inputs[1]
loss = O.ZeroGrad(out.sum())
network = Network(outputs=[loss])
network.loss_var = loss
"""
func = OptimizableFunc.make_from_loss_var(loss)
NaiveSGD(1)(func)
func.compile(loss)
print(func())
print(np.array(a.eval(), dtype = np.float32))
loss.Mul_Wc(10)
print(func())
print(np.array(a.eval()))
import megskull.opr.all as O
import numpy as np
a = O.ParamProvider('a', np.ones((10, )))
b = O.ParamProvider('b', np.ones((10, )))
loss = O.ZeroGrad((a * b).sum())
from My import MyWeightDecay
loss = MyWeightDecay(loss, {"*": 0.001})
from megskull.optimizer import NaiveSGD, OptimizableFunc
func = OptimizableFunc.make_from_loss_var(loss)
NaiveSGD(1)(func)
func.compile(loss)
print(func())
print(np.array(a.eval(), dtype=np.float32))
loss.Mul_Wc(10)
print(func())
print(np.array(a.eval()))
print(func())