def __init__(self, N, d, test_size):
self.N = N
self.d = d
self.n_d = int(N * (N - 1) / 2)
self.test_size = test_size
self.etm = Algorithm(N, d)
self.lossFun = CoordsToDMLoss(
N=N, lossFun=nn.L1Loss(reduction='mean'))
self.test_data = dataSource.generate_rand_DM(
self.N, self.test_size, isInt=True, sample_space=(1000, 1))
self.test_data = utils.minmax_norm(self.test_data, dmin=0)[0]
import numpy
from torch import nn
from mds.cmds import classicalMDS
from lossFunction import CoordsToDMLoss
torch.set_default_tensor_type('torch.DoubleTensor')
dist_func = lambda p1, p2: torch.sum(torch.abs((p2 - p1)))
cus = custom_distance(10,
3,
1000,
isInt=True,
sample_space=(1000, 1),
dist_func=dist_func)
lossFun = CoordsToDMLoss(N=10, d=2, lossFun=nn.L1Loss(reduction='mean'))
coords, dms = cus
dms = utils.minmax_norm(dms, dmin=0)[0] + 1e-8
dms = dms.detach().requires_grad_(True)
cmds_rs = []
for d in dms:
d1 = numpy.array(d.data)
cmds_rs.append(torch.tensor(classicalMDS(d1, 2)))
cmds_rs = torch.stack(cmds_rs)
print("cmds_loss: \t", lossFun(cmds_rs, dms))
import model.RNN as rnn
from shutil import copyfile
import os
# %%
data = dataSource.load_data(shape=(ss, N, d))[0]
data = utils.minmax_norm(data, dmin=0)[0]
dlr = DataLoader(data, batch_size=batch, shuffle=True)
init_lr = 1e-3
train_id = '_'.join(['Coord', 'Linear', 'M', 'MSE'])
coordLoss = CoordsToDMLoss(N, lossFun=nn.MSELoss(reduction='mean'))
reconLoss = ReconLoss(lossFun=nn.MSELoss(reduction='mean'))
mseLoss = CustomLoss(lossFun=nn.MSELoss(reduction='mean'))
lossFun = MultiLoss(lossFunList=[coordLoss])
preprocess = PrepMatrix(N)
in_dim = preprocess.get_inShape()
out_dim = 2
def get_model(nNeuron, nLayer, in_dim, out_dim):
nNeuron = nNeuron + in_dim
import model.RNN as rnn
from shutil import copyfile
import os
# %%
data = dataSource.load_data(shape=(ss, N, d))[0]
data = utils.minmax_norm(data, dmin=0)[0]
dlr = DataLoader(data, batch_size=batch, shuffle=True)
init_lr = 1e-3
train_id = '_'.join(['Coord', 'Linear', 'M', 'SML'])
coordLoss = CoordsToDMLoss(N, lossFun=sammon_loss)
reconLoss = ReconLoss(lossFun=nn.MSELoss(reduction='mean'))
mseLoss = CustomLoss(lossFun=nn.MSELoss(reduction='mean'))
lossFun = MultiLoss(lossFunList=[coordLoss])
preprocess = PrepMatrix(N)
in_dim = preprocess.get_inShape()
out_dim = 2
def get_model(nNeuron, nLayer, in_dim, out_dim):
nNeuron = nNeuron + in_dim
import model.RNN as rnn
from shutil import copyfile
import os
# %%
data = dataSource.load_data(shape=(ss, N, d))[0]
data = utils.minmax_norm(data, dmin=0)[0]
dlr = DataLoader(data, batch_size=batch, shuffle=True)
init_lr = 1e-3
train_id = '_'.join(['Coord', 'Linear', 'M', 'RLL'])
coordLoss = CoordsToDMLoss(N, lossFun=lossF.relative_loss)
reconLoss = ReconLoss(lossFun=nn.MSELoss(reduction='mean'))
mseLoss = CustomLoss(lossFun=nn.MSELoss(reduction='mean'))
lossFun = MultiLoss(lossFunList=[coordLoss])
preprocess = PrepMatrix(N)
in_dim = preprocess.get_inShape()
out_dim = 2
def get_model(nNeuron, nLayer, in_dim, out_dim):
nNeuron = nNeuron + in_dim
mid1 = int((nNeuron + in_dim) / 2)
