def run_detection(self, spec, chunk_duration, detection_thresh, low_res=True):
"""audio is the raw samples should be 1D vector
sampling_rate should be divided by 10 if the recordings are not time
expanded
"""
# run the cnn - low_res will be faster but less accurate
if low_res:
prob = self.eval_network(spec)
scale_fact = 8.0
else:
prob_1 = self.eval_network(spec)
prob_2 = self.eval_network(spec[:, 2:])
prob = np.zeros(prob_1.shape[0]*2, dtype=np.float32)
prob[0::2] = prob_1
prob[1::2] = prob_2
scale_fact = 4.0
f_size = self.smooth_op_prediction_sigma / scale_fact
nms_win = np.round(self.nms_win_size / scale_fact)
# smooth the outputs - this might not be necessary
prob = gaussian_filter1d(prob, f_size)
# perform non maximum suppression
call_time, call_prob = nms.nms_1d(prob, nms_win, chunk_duration)
# remove detections below threshold
if call_prob.shape[0] > 0:
inds = (call_prob >= detection_thresh)
call_prob = call_prob[inds]
call_time = call_time[inds]
return call_time, call_prob
def test(self, file_name=None, file_duration=None, audio_samples=None, sampling_rate=None):
# compute features and perform classification
features = self.create_or_load_features(file_name, audio_samples, sampling_rate)
y_prediction = self.test_fn(features)[:, np.newaxis]
# smooth the output prediction
if self.params.smooth_op_prediction:
y_prediction = gaussian_filter1d(y_prediction, self.params.smooth_op_prediction_sigma, axis=0)
# perform non max suppression
pos, prob = nms.nms_1d(y_prediction[:,0].astype(np.float), self.params.nms_win_size, file_duration)
return pos, prob, y_prediction
def test(self,
file_name=None,
file_duration=None,
audio_samples=None,
sampling_rate=None):
# compute features
features = self.create_or_load_features(file_name, audio_samples,
sampling_rate)
# make prediction
y_prediction = self.forest.test(features)[:, 1][:, np.newaxis]
# smooth the output
if self.params.smooth_op_prediction:
y_prediction = gaussian_filter1d(
y_prediction, self.params.smooth_op_prediction_sigma, axis=0)
pos, prob = nms.nms_1d(y_prediction[:, 0], self.params.nms_win_size,
file_duration)
return pos, prob, y_prediction
def test_nms():
import matplotlib.pyplot as plt
import numpy as np
#import pyximport; pyximport.install(reload_support=True)
import nms as nms_fast
y = np.sin(np.arange(1000) / 100.0 * np.pi)
y = y + np.random.random(y.shape) * 0.5
win_size = int(0.1 * y.shape[0] / 2.0)
pos, prob = nms_1d(y, win_size, y.shape[0])
pos_f, prob_f = nms_fast.nms_1d(y, win_size, y.shape[0])
print('diff between implementations =',
1 - np.isclose(prob_f, prob).mean())
print('diff between implementations =', 1 - np.isclose(pos_f, pos).mean())
plt.close('all')
plt.plot(y)
plt.plot((pos).astype('int'), prob, 'ro', ms=10)
plt.plot((pos_f).astype('int'), prob, 'bo') # shift so we can see them
plt.show()
def test(self, file_name=None, file_duration=None, audio_samples=None, sampling_rate=None):
# compute features and perform classification
features = self.create_or_load_features(file_name, audio_samples, sampling_rate)
# predictions for max classes
y_predictions = self.test_fn(features)
# trying to get rid of rows with 0 highest
call_predictions = y_predictions
call_predictions = call_predictions[:,1:]
high_preds = np.array([np.max(x) for x in call_predictions])[:, np.newaxis]
classes = np.array([np.argmax(x)+1 for x in call_predictions])[:, np.newaxis]
# smooth the output prediction
if self.params.smooth_op_prediction:
high_preds = gaussian_filter1d(high_preds, self.params.smooth_op_prediction_sigma, axis=0)
# perform non max suppression
pos, prob, classes = nms.nms_1d(high_preds[:,0].astype(np.float), classes,self.params.nms_win_size, file_duration)
return pos, prob, high_preds, classes
