def classify(self,
decoder,
true_label,
title_text,
bar_dirs,
state='start',
prob_history=None):
"""
Run a single trial
"""
true_label_index = bar_dirs.index(true_label)
self.tm_trigger.reset()
if self.bar_bias is not None:
bias_idx = bar_dirs.index(self.bar_bias[0])
if self.logf is not None:
self.logf.write('True label: %s\n' % true_label)
tm_classify = qc.Timer(autoreset=True)
self.stimo_timer = qc.Timer()
while True:
self.tm_display.sleep_atleast(self.refresh_delay)
self.tm_display.reset()
if state == 'start' and self.tm_trigger.sec(
) > self.cfg.TIMINGS['INIT']:
state = 'gap_s'
if self.cfg.TRIALS_PAUSE:
self.viz.put_text('Press any key')
self.viz.update()
key = cv2.waitKeyEx()
if key == KEYS['esc']:
return
self.viz.fill()
self.tm_trigger.reset()
self.trigger.signal(self.tdef.INIT)
elif state == 'gap_s':
if self.cfg.TIMINGS['GAP'] > 0:
self.viz.put_text(title_text)
state = 'gap'
self.tm_trigger.reset()
elif state == 'gap' and self.tm_trigger.sec(
) > self.cfg.TIMINGS['GAP']:
state = 'cue'
self.viz.fill()
self.viz.draw_cue()
self.viz.glass_draw_cue()
self.trigger.signal(self.tdef.CUE)
self.tm_trigger.reset()
elif state == 'cue' and self.tm_trigger.sec(
) > self.cfg.TIMINGS['READY']:
state = 'dir_r'
if self.cfg.SHOW_CUE is True:
if self.cfg.FEEDBACK_TYPE == 'BAR':
self.viz.move(true_label,
100,
overlay=False,
barcolor='G')
elif self.cfg.FEEDBACK_TYPE == 'BODY':
self.viz.put_text(DIRS[true_label], 'R')
if true_label == 'L': # left
self.trigger.signal(self.tdef.LEFT_READY)
elif true_label == 'R': # right
self.trigger.signal(self.tdef.RIGHT_READY)
elif true_label == 'U': # up
self.trigger.signal(self.tdef.UP_READY)
elif true_label == 'D': # down
self.trigger.signal(self.tdef.DOWN_READY)
elif true_label == 'B': # both hands
self.trigger.signal(self.tdef.BOTH_READY)
else:
raise RuntimeError('Unknown direction %s' % true_label)
self.tm_trigger.reset()
'''
if self.cfg.FEEDBACK_TYPE == 'BODY':
self.viz.set_pc_feedback(False)
self.viz.move(true_label, 100, overlay=False, barcolor='G')
if self.cfg.FEEDBACK_TYPE == 'BODY':
self.viz.set_pc_feedback(True)
if self.cfg.SHOW_CUE is True:
self.viz.put_text(dirs[true_label], 'R')
if true_label == 'L': # left
self.trigger.signal(self.tdef.LEFREADY)
elif true_label == 'R': # right
self.trigger.signal(self.tdef.RIGHT_READY)
elif true_label == 'U': # up
self.trigger.signal(self.tdef.UP_READY)
elif true_label == 'D': # down
self.trigger.signal(self.tdef.DOWN_READY)
elif true_label == 'B': # both hands
self.trigger.signal(self.tdef.BOTH_READY)
else:
raise RuntimeError('Unknown direction %s' % true_label)
self.tm_trigger.reset()
'''
elif state == 'dir_r' and self.tm_trigger.sec(
) > self.cfg.TIMINGS['DIR_CUE']:
self.viz.fill()
self.viz.draw_cue()
self.viz.glass_draw_cue()
state = 'dir'
# initialize bar scores
bar_label = bar_dirs[0]
bar_score = 0
probs = [1.0 / len(bar_dirs)] * len(bar_dirs)
self.viz.move(bar_label, bar_score, overlay=False)
probs_acc = np.zeros(len(probs))
if true_label == 'L': # left
self.trigger.signal(self.tdef.LEFT_GO)
elif true_label == 'R': # right
self.trigger.signal(self.tdef.RIGHT_GO)
elif true_label == 'U': # up
self.trigger.signal(self.tdef.UP_GO)
elif true_label == 'D': # down
self.trigger.signal(self.tdef.DOWN_GO)
elif true_label == 'B': # both
self.trigger.signal(self.tdef.BOTH_GO)
else:
raise RuntimeError('Unknown truedirection %s' % true_label)
self.tm_watchdog.reset()
self.tm_trigger.reset()
elif state == 'dir':
if self.tm_trigger.sec() > self.cfg.TIMINGS['CLASSIFY'] or (
self.premature_end and bar_score >= 100):
if not hasattr(
self.cfg,
'SHOW_RESULT') or self.cfg.SHOW_RESULT is True:
# show classfication result
if self.cfg.WITH_STIMO is True:
if self.cfg.STIMO_FULLGAIT_CYCLE is not None and bar_label == 'U':
res_color = 'G'
elif self.cfg.TRIALS_RETRY is False or bar_label == true_label:
res_color = 'G'
else:
res_color = 'Y'
else:
res_color = 'Y'
if self.cfg.FEEDBACK_TYPE == 'BODY':
self.viz.move(bar_label,
bar_score,
overlay=False,
barcolor=res_color,
caption=DIRS[bar_label],
caption_color=res_color)
else:
self.viz.move(bar_label,
100,
overlay=False,
barcolor=res_color)
else:
if self.cfg.FEEDBACK_TYPE == 'BODY':
self.viz.move(bar_label,
bar_score,
overlay=False,
barcolor=res_color,
caption='TRIAL END',
caption_color=res_color)
else:
self.viz.move(bar_label,
0,
overlay=False,
barcolor=res_color)
self.trigger.signal(self.tdef.FEEDBACK)
# STIMO
if self.cfg.WITH_STIMO is True and self.cfg.STIMO_CONTINUOUS is False:
if self.cfg.STIMO_FULLGAIT_CYCLE is not None:
if bar_label == 'U':
self.ser.write(
self.cfg.STIMO_FULLGAIT_PATTERN[0])
logger.info('STIMO: Sent 1')
time.sleep(self.cfg.STIMO_FULLGAIT_CYCLE)
self.ser.write(
self.cfg.STIMO_FULLGAIT_PATTERN[1])
logger.info('STIMO: Sent 2')
time.sleep(self.cfg.STIMO_FULLGAIT_CYCLE)
elif self.cfg.TRIALS_RETRY is False or bar_label == true_label:
if bar_label == 'L':
self.ser.write(b'1')
logger.info('STIMO: Sent 1')
elif bar_label == 'R':
self.ser.write(b'2')
logger.info('STIMO: Sent 2')
# FES event mode mode
if self.cfg.WITH_FES is True and self.cfg.FES_CONTINUOUS is False:
if bar_label == 'L':
stim_code = [0, 30, 0, 0, 0, 0, 0, 0]
self.stim.UpdateChannelSettings(stim_code)
logger.info('FES: Sent Left')
time.sleep(0.5)
stim_code = [0, 0, 0, 0, 0, 0, 0, 0]
self.stim.UpdateChannelSettings(stim_code)
elif bar_label == 'R':
stim_code = [30, 0, 0, 0, 0, 0, 0, 0]
self.stim.UpdateChannelSettings(stim_code)
time.sleep(0.5)
logger.info('FES: Sent Right')
stim_code = [0, 0, 0, 0, 0, 0, 0, 0]
self.stim.UpdateChannelSettings(stim_code)
if self.cfg.DEBUG_PROBS:
msg = 'DEBUG: Accumulated probabilities = %s' % qc.list2string(
probs_acc, '%.3f')
logger.info(msg)
if self.logf is not None:
self.logf.write(msg + '\n')
if self.logf is not None:
self.logf.write('%s detected as %s (%d)\n\n' %
(true_label, bar_label, bar_score))
self.logf.flush()
# end of trial
state = 'feedback'
self.tm_trigger.reset()
else:
# classify
probs_new = decoder.get_prob_smooth_unread()
if probs_new is None:
if self.tm_watchdog.sec() > 3:
logger.warning(
'No classification being done. Are you receiving data streams?'
)
self.tm_watchdog.reset()
else:
self.tm_watchdog.reset()
if prob_history is not None:
prob_history[true_label].append(
probs_new[true_label_index])
probs_acc += np.array(probs_new)
'''
New decoder: already smoothed by the decoder so bias after.
'''
probs = list(probs_new)
if self.bar_bias is not None:
probs[bias_idx] += self.bar_bias[1]
newsum = sum(probs)
probs = [p / newsum for p in probs]
'''
# Method 2: bias and smoothen
if self.bar_bias is not None:
# print('BEFORE: %.3f %.3f'% (probs_new[0], probs_new[1]) )
probs_new[bias_idx] += self.bar_bias[1]
newsum = sum(probs_new)
probs_new = [p / newsum for p in probs_new]
# print('AFTER: %.3f %.3f'% (probs_new[0], probs_new[1]) )
for i in range(len(probs_new)):
probs[i] = probs[i] * self.alpha_old + probs_new[i] * self.alpha_new
'''
''' Original method
# Method 1: smoothen and bias
for i in range( len(probs_new) ):
probs[i] = probs[i] * self.alpha_old + probs_new[i] * self.alpha_new
# bias bar
if self.bar_bias is not None:
probs[bias_idx] += self.bar_bias[1]
newsum = sum(probs)
probs = [p/newsum for p in probs]
'''
# determine the direction
# TODO: np.argmax(probs)
max_pidx = qc.get_index_max(probs)
max_label = bar_dirs[max_pidx]
if self.cfg.POSITIVE_FEEDBACK is False or \
(self.cfg.POSITIVE_FEEDBACK and true_label == max_label):
dx = probs[max_pidx]
if max_label == 'R':
dx *= self.bar_step_right
elif max_label == 'L':
dx *= self.bar_step_left
elif max_label == 'U':
dx *= self.bar_step_up
elif max_label == 'D':
dx *= self.bar_step_down
elif max_label == 'B':
dx *= self.bar_step_both
else:
logger.debug('Direction %s using bar step %d' %
(max_label, self.bar_step_left))
dx *= self.bar_step_left
# slow start
selected = self.cfg.BAR_SLOW_START['selected']
if self.cfg.BAR_SLOW_START[
selected] and self.tm_trigger.sec(
) < self.cfg.BAR_SLOW_START[selected]:
dx *= self.tm_trigger.sec(
) / self.cfg.BAR_SLOW_START[selected][0]
# add likelihoods
if max_label == bar_label:
bar_score += dx
else:
bar_score -= dx
# change of direction
if bar_score < 0:
bar_score = -bar_score
bar_label = max_label
bar_score = int(bar_score)
if bar_score > 100:
bar_score = 100
if self.cfg.FEEDBACK_TYPE == 'BODY':
if self.cfg.SHOW_CUE:
self.viz.move(bar_label,
bar_score,
overlay=False,
caption=DIRS[true_label],
caption_color='G')
else:
self.viz.move(bar_label,
bar_score,
overlay=False)
else:
self.viz.move(bar_label,
bar_score,
overlay=False)
# send the confidence value continuously
if self.cfg.WITH_STIMO and self.cfg.STIMO_CONTINUOUS:
if self.stimo_timer.sec(
) >= self.cfg.STIMO_COOLOFF:
if bar_label == 'U':
stimo_code = bar_score
else:
stimo_code = 0
self.ser.write(bytes([stimo_code]))
logger.info('Sent STIMO code %d' %
stimo_code)
self.stimo_timer.reset()
# with FES
if self.cfg.WITH_FES is True and self.cfg.FES_CONTINUOUS is True:
if self.stimo_timer.sec(
) >= self.cfg.STIMO_COOLOFF:
if bar_label == 'L':
stim_code = [
bar_score, 0, 0, 0, 0, 0, 0, 0
]
else:
stim_code = [
0, bar_score, 0, 0, 0, 0, 0, 0
]
self.stim.UpdateChannelSettings(stim_code)
logger.info('Sent FES code %d' % bar_score)
self.stimo_timer.reset()
if self.cfg.DEBUG_PROBS:
if self.bar_bias is not None:
biastxt = '[Bias=%s%.3f] ' % (
self.bar_bias[0], self.bar_bias[1])
else:
biastxt = ''
msg = '%s%s prob %s acc %s bar %s%d (%.1f ms)' % \
(biastxt, bar_dirs, qc.list2string(probs_new, '%.2f'), qc.list2string(probs, '%.2f'),
bar_label, bar_score, tm_classify.msec())
logger.info(msg)
if self.logf is not None:
self.logf.write(msg + '\n')
elif state == 'feedback' and self.tm_trigger.sec(
) > self.cfg.TIMINGS['FEEDBACK']:
self.trigger.signal(self.tdef.BLANK)
if self.cfg.FEEDBACK_TYPE == 'BODY':
state = 'return'
self.tm_trigger.reset()
else:
state = 'gap_s'
self.viz.fill()
self.viz.update()
return bar_label
elif state == 'return':
self.viz.set_glass_feedback(False)
if self.cfg.WITH_STIMO:
self.viz.move(bar_label,
bar_score,
overlay=False,
barcolor='B')
else:
self.viz.move(bar_label,
bar_score,
overlay=False,
barcolor='Y')
self.viz.set_glass_feedback(True)
bar_score -= 5
if bar_score <= 0:
state = 'gap_s'
self.viz.fill()
self.viz.update()
return bar_label
self.viz.update()
key = cv2.waitKeyEx(1)
if key == KEYS['esc']:
return
elif key == KEYS['space']:
dx = 0
bar_score = 0
probs = [1.0 / len(bar_dirs)] * len(bar_dirs)
self.viz.move(bar_dirs[0], bar_score, overlay=False)
self.viz.update()
logger.info('probs and dx reset.')
self.tm_trigger.reset()
elif key in ARROW_KEYS and ARROW_KEYS[key] in bar_dirs:
# change bias on the fly
if self.bar_bias is None:
self.bar_bias = [ARROW_KEYS[key], BIAS_INCREMENT]
else:
if ARROW_KEYS[key] == self.bar_bias[0]:
self.bar_bias[1] += BIAS_INCREMENT
elif self.bar_bias[1] >= BIAS_INCREMENT:
self.bar_bias[1] -= BIAS_INCREMENT
else:
self.bar_bias = [ARROW_KEYS[key], BIAS_INCREMENT]
if self.bar_bias[1] == 0:
self.bar_bias = None
else:
bias_idx = bar_dirs.index(self.bar_bias[0])
def stream_player(server_name,
fif_file,
chunk_size,
auto_restart=True,
wait_start=True,
repeat=np.float('inf'),
high_resolution=False,
trigger_file=None):
"""
Input
=====
server_name: LSL server name.
fif_file: fif file to replay.
chunk_size: number of samples to send at once (usually 16-32 is good enough).
auto_restart: play from beginning again after reaching the end.
wait_start: wait for user to start in the beginning.
repeat: number of loops to play.
high_resolution: use perf_counter() instead of sleep() for higher time resolution
but uses much more cpu due to polling.
trigger_file: used to convert event numbers into event strings for readability.
Note: Run neurodecode.set_log_level('DEBUG') to print out the relative time stamps since started.
"""
raw, events = pu.load_raw(fif_file)
sfreq = raw.info['sfreq'] # sampling frequency
n_channels = len(raw.ch_names) # number of channels
if trigger_file is not None:
tdef = trigger_def(trigger_file)
try:
event_ch = raw.ch_names.index('TRIGGER')
except ValueError:
event_ch = None
if raw is not None:
logger.info_green('Successfully loaded %s' % fif_file)
logger.info('Server name: %s' % server_name)
logger.info('Sampling frequency %.3f Hz' % sfreq)
logger.info('Number of channels : %d' % n_channels)
logger.info('Chunk size : %d' % chunk_size)
for i, ch in enumerate(raw.ch_names):
logger.info('%d %s' % (i, ch))
logger.info('Trigger channel : %s' % event_ch)
else:
raise RuntimeError('Error while loading %s' % fif_file)
# set server information
sinfo = pylsl.StreamInfo(server_name, channel_count=n_channels, channel_format='float32',\
nominal_srate=sfreq, type='EEG', source_id=server_name)
desc = sinfo.desc()
channel_desc = desc.append_child("channels")
for ch in raw.ch_names:
channel_desc.append_child('channel').append_child_value('label', str(ch))\
.append_child_value('type','EEG').append_child_value('unit','microvolts')
desc.append_child('amplifier').append_child('settings').append_child_value(
'is_slave', 'false')
desc.append_child('acquisition').append_child_value(
'manufacturer',
'NeuroDecode').append_child_value('serial_number', 'N/A')
outlet = pylsl.StreamOutlet(sinfo, chunk_size=chunk_size)
if wait_start:
input('Press Enter to start streaming.')
logger.info('Streaming started')
idx_chunk = 0
t_chunk = chunk_size / sfreq
finished = False
if high_resolution:
t_start = time.perf_counter()
else:
t_start = time.time()
# start streaming
played = 1
while played < repeat:
idx_current = idx_chunk * chunk_size
chunk = raw._data[:, idx_current:idx_current + chunk_size]
data = chunk.transpose().tolist()
if idx_current >= raw._data.shape[1] - chunk_size:
finished = True
if high_resolution:
# if a resolution over 2 KHz is needed
t_sleep_until = t_start + idx_chunk * t_chunk
while time.perf_counter() < t_sleep_until:
pass
else:
# time.sleep() can have 500 us resolution using the tweak tool provided.
t_wait = t_start + idx_chunk * t_chunk - time.time()
if t_wait > 0.001:
time.sleep(t_wait)
outlet.push_chunk(data)
logger.debug('[%8.3fs] sent %d samples (LSL %8.3f)' %
(time.perf_counter(), len(data), pylsl.local_clock()))
if event_ch is not None:
event_values = set(chunk[event_ch]) - set([0])
if len(event_values) > 0:
if trigger_file is None:
logger.info('Events: %s' % event_values)
else:
for event in event_values:
if event in tdef.by_value:
logger.info('Events: %s (%s)' %
(event, tdef.by_value[event]))
else:
logger.info('Events: %s (Undefined event)' % event)
idx_chunk += 1
if finished:
if auto_restart is False:
input(
'Reached the end of data. Press Enter to restart or Ctrl+C to stop.'
)
else:
logger.info('Reached the end of data. Restarting.')
idx_chunk = 0
finished = False
if high_resolution:
t_start = time.perf_counter()
else:
t_start = time.time()
played += 1
def _daemon(self,
classifier,
probs,
probs_smooth,
pread,
t_problast,
running,
return_psd,
psd_ctypes,
lock,
interleave=None,
label=None):
"""
Runs Decoder class as a daemon.
"""
pid = os.getpid()
ps = psutil.Process(pid)
if os.name == 'posix':
# Unix
ps.nice(
0
) # A negative value increases priority but requires root privilages
else:
# Windows
ps.nice(psutil.HIGH_PRIORITY_CLASS)
logger.debug('[DecodeWorker-%-6d] Decoder worker process started' %
(pid))
decoder = BCIDecoder(self.amp_name,
classifier,
buffer_size=self.buffer_sec,
fake=self.fake,
label=label)
if self.fake == False:
psd = ctypeslib.as_array(psd_ctypes)
else:
psd = None
if interleave is None:
# single-core decoding
with running.get_lock():
running.value = 1
while running.value == 1:
# compute features and likelihoods
probs[:], t_prob = decoder.get_prob(True)
probs_smooth_sum = 0
for i in range(len(probs_smooth)):
probs_smooth[i] = probs_smooth[i] * self.alpha_old + probs[
i] * self.alpha_new
probs_smooth_sum += probs_smooth[i]
for i in range(len(probs_smooth)):
probs_smooth[i] /= probs_smooth_sum
pread.value = 0
t_problast.value = t_prob
# copy back PSD values only when requested
if self.fake == False and return_psd.value == 1:
lock.acquire()
psd[:] = decoder.psd_buffer[-1].reshape((1, -1))
lock.release()
return_psd.value = 0
else:
# interleaved parallel decoding
t_start = interleave['t_start']
period = interleave['period']
running.value = 1
t_next = t_start + math.ceil(
((time.time() - t_start) / period)) * period
while running.value == 1:
# end of the current time slot
t_next += period
# compute likelihoods
t_prob_wall = time.time()
probs_local, t_prob_lsl = decoder.get_prob(True)
# update the probs only if the current value is the latest
##################################################################
# TODO: use timestamp to compare instead of time.time()
##################################################################
if t_prob_wall > t_problast.value:
lock.acquire()
probs[:] = probs_local
for i in range(len(probs_smooth)):
probs_smooth[i] = probs_smooth[
i] * self.alpha_old + probs[i] * self.alpha_new
pread.value = 0
t_problast.value = t_prob_wall
lock.release()
# copy back PSD values only when requested
if self.fake == False and return_psd.value == 1:
lock.acquire()
psd[:] = decoder.psd_buffer[-1].reshape((1, -1))
lock.release()
return_psd.value = 0
# get the next time slot if didn't finish in the current slot
if time.time() > t_next:
t_next_new = t_start + math.ceil(
((time.time() - t_start) / period)) * period
logger.warning('[DecodeWorker-%-6d] High decoding delay (%.1f ms): t_next = %.3f -> %.3f' %\
(pid, (time.time() - t_next + period) * 1000, t_next, t_next_new))
t_next = t_next_new
# sleep until the next time slot
t_sleep = t_next - time.time()
if t_sleep > 0.001:
time.sleep(t_sleep)
logger.debug('[DecodeWorker-%-6d] Woke up at %.3f' %
(pid, time.time()))