def make_class(subject_id=[1, 10],
crop=False,
problem='hf',
all_subject=False):
bpfilter = [0.5, 45]
if problem == "hf":
if crop:
pass
else:
X, y = get_data_multi(sub_id_range=subject_id,
event_code=[6, 10, 14],
t=[0, 4.0],
filter=bpfilter)
if problem == "lr":
if crop:
X, y, _, _ = get_crops_multi(sub_id_range=subject_id,
event_code=[4, 8, 12],
t=[0, 4.0],
filter=bpfilter,
time_window=2.0,
time_step=1.0)
else:
X, y = get_data_multi(sub_id_range=subject_id,
event_code=[4, 8, 12],
t=[0, 4.0],
filter=bpfilter)
return X, y
from braindecode.datautil.iterators import CropsFromTrialsIterator
from braindecode.torch_ext.util import np_to_var, var_to_np
import torch.nn.functional as F
from numpy.random import RandomState
import torch as th
from braindecode.experiments.monitors import compute_preds_per_trial_for_set
import os, sys
os.chdir('/home/seigyo/Documents/pytorch/brain_decoder')
from load_data import get_data, get_data_multi
# X, y = get_data(id=10, event_code=[5,6,9,10,13,14], filter=None, t=[-0.5, 4])
# train_X, train_y = X[:60], y[:60]
# test_X, test_y = X[60:], y[60:]
train_X, train_y = get_data_multi(sub_id_range=[1, 88],
event_code=[6, 10, 14],
filter=None,
t=[1, 4.1])
test_X, test_y = get_data_multi(sub_id_range=[89, 99],
event_code=[6, 10, 14],
filter=None,
t=[1, 4.1])
train_set = SignalAndTarget(train_X, y=train_y)
test_set = SignalAndTarget(test_X, y=test_y)
# Set if you want to use GPU
# You can also use torch.cuda.is_available() to determine if cuda is available on your machine.
cuda = True
set_random_seeds(seed=20170629, cuda=cuda)
# This will determine how many crops are processed in parallel
def make_class(idx=0, crop=False, problem='hf', all_subject=False):
bpfilter = [0.5, 45]
if all_subject:
if problem == "hf":
if crop:
pass
else:
X, y = get_data_multi(sub_id_range=[1, 99],
event_code=[6, 10, 14],
t=[0, 4.0],
filter=bpfilter)
if problem == "lr":
if crop:
pass
else:
X, y = get_data_multi(sub_id_range=[1, 99],
event_code=[4, 8, 12],
t=[0, 4.0],
filter=bpfilter)
else:
if problem == "hf":
if crop:
pass
else:
X, y = get_data(id=idx + 1,
event_code=[6, 10, 14],
filter=bpfilter,
t=[0., 4])
if problem == "lr":
if crop:
X, y, _, _ = get_crops(id=idx + 1,
event_code=[6, 10, 14],
filter=bpfilter,
t=[0, 4.0],
time_window=3.0,
time_step=0.1)
else:
X, y = get_data(id=idx + 1,
event_code=[4, 8, 12],
filter=bpfilter,
t=[0., 4])
if problem == "lh":
if crop:
pass
else:
Xl, yl = get_data_one_class(id=idx + 1,
event_code=[4, 8, 12],
filter=bpfilter,
t=[0, 4],
classid=2)
Xh, yh = get_data_one_class(id=idx + 1,
event_code=[6, 10, 14],
filter=bpfilter,
t=[0, 4],
classid=2)
X = np.vstack((Xl, Xh))
y = np.hstack((yl, yh + 1))
if problem == "rh":
if crop:
pass
else:
Xr, yr = get_data_one_class(id=idx + 1,
event_code=[4, 8, 12],
filter=bpfilter,
t=[0, 4],
classid=3)
Xh, yh = get_data_one_class(id=idx + 1,
event_code=[6, 10, 14],
filter=bpfilter,
t=[0, 4],
classid=2)
X = np.vstack((Xr, Xh))
y = np.hstack((yr - 1, yh + 1))
if problem == "lf":
if crop:
pass
else:
Xl, yl = get_data_one_class(id=idx + 1,
event_code=[4, 8, 12],
filter=bpfilter,
t=[0, 4],
classid=2)
Xf, yf = get_data_one_class(id=idx + 1,
event_code=[6, 10, 14],
filter=bpfilter,
t=[0, 4],
classid=3)
X = np.vstack((Xl, Xf))
y = np.hstack((yl, yf))
if problem == "rf":
if crop:
pass
else:
Xr, yr = get_data_one_class(id=idx + 1,
event_code=[4, 8, 12],
filter=bpfilter,
t=[0, 4],
classid=3)
Xf, yf = get_data_one_class(id=idx + 1,
event_code=[6, 10, 14],
filter=bpfilter,
t=[0, 4],
classid=3)
X = np.vstack((Xr, Xf))
y = np.hstack((yr - 1, yf))
return X, y